The model catalog
912 known model families from 122 providers, each with its own tracking page: context window, modalities, pricing per million tokens, and the price history we have recorded since tracking began. Merged nightly across multiple routing providers — a price confirmed across sources is a market change; a price that appears at only one provider is that provider's rate.
catalog sources: OpenRouter · TrustedRouter · Vercel AI Gateway · Cloudflare · updated 2026-11-14 · weights & model cards on Hugging Face
Abliterate #148
abliterate-0.3-balanced via TrustedRouter. When Abliterate omits usage, successful prepaid calls are billed using up to twice the locally estimated input and output tokens. The added buffer is limited by the authorize…
Abliterate #149
abliterate-0.3-clever via TrustedRouter. When Abliterate omits usage, successful prepaid calls are billed using up to twice the locally estimated input and output tokens. The added buffer is limited by the authorized…
Abliterate #150
abliterate-0.3-fast via TrustedRouter. When Abliterate omits usage, successful prepaid calls are billed using up to twice the locally estimated input and output tokens. The added buffer is limited by the authorized re…
Abliteration #151
Abliterated Large Flash via TrustedRouter
Abliteration #152
Abliterated Large v2 via TrustedRouter
Abliteration #153
Abliterated Model via TrustedRouter
AI Singapore #154
@cf/aisingapore/gemma-sea-lion-v4-27b-it via TrustedRouter
AI4Bharat
indictrans2 is the first open-source transformer-based multilingual nmt model that supports high-quality translations across all the 22 scheduled indic languages
Aion Labs #155
Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each...
Aion Labs #156
Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It is the smaller, lower-cost sibling of Aion 3.5 and uses...
Aion Labs #157
Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories, making narratives feel more engaging....
Aion Labs #158
Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute...
Aion Labs #159
Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multiple specialized models each...
Aion Labs #160
Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tun…
Alibaba
Alibaba Wan 2.7 via TrustedRouter
Alibaba
Qwen3-32B is a world-class model with comparable quality to DeepSeek R1 while outperforming GPT-4.1 and Claude Sonnet 3.7. It excels in code-gen, tool-calling, and advanced reasoning, making it an exceptional model fo…
Alibaba
Efficient coding specialist balancing performance with cost-effectiveness for daily development tasks while maintaining strong tool integration capabilities.
Alibaba
alibaba's qwen 3 max is a large language model with strong coding, reasoning, and multilingual capabilities, served via dashscope's openai-compatible endpoint. llm coding reasoning multilingual
Alibaba
Compared with the snapshot as of September 23, 2025, the Qwen-3 series Max model in this release achieves an effective integration of thinking and non-thinking modes, resulting in a comprehensive and substantial impro…
Alibaba
alibaba's qwen 3.5 is a 397b-parameter mixture-of-experts model with 17b active parameters, offering strong reasoning capabilities with efficient inference. llm coding reasoning moe
Alibaba
The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared t…
Alibaba
The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a v…
Alibaba
The Qwen3.6 35B-A3B native vision-language model is built on a hybrid architecture that integrates linear attention mechanisms with a sparse mixture-of-experts framework, achieving higher inference efficiency. Compare…
Alibaba
Qwen 3.6 35B A3B is a mixture-of-experts model with 35 billion total parameters and 3 billion active parameters, built for coding, reasoning, and tool-based workflows.
Alibaba
The Qwen3.6 native vision-language Plus series models demonstrate exceptional performance on par with the current state-of-the-art models, with a significant improvement in overall results compared to the 3.5 series.…
Alibaba
The Qwen3.7 native vision-language Flash model series delivers a comprehensive upgrade over 3.6-Flash in multimodal understanding and agent execution. This model particularly excels in enhanced multimodal foundations…
Alibaba
Qwen3.7 is a next‑generation flagship model designed for the agent‑centric era, with its core strengths lying in the breadth and depth of its agent‑level capabilities: it excels at programming, office and productivity…
Alibaba
Among the Qwen3.7 series, the cost-effective Plus model builds on its robust text capabilities while delivering a comprehensive upgrade to its vision‑language abilities, all while preserving its full‑stack agent‑level…
Alibaba
Qwen3.8-Flash is Qwen’s fast, cost-efficient multimodal model, combining advanced reasoning and generation with a native 1M-token context window. Built for coding, agentic workflows, and visual understanding, it handl…
Alibaba
Qwen 3.8 Max is a 2.4-trillion-parameter MoE model delivering a comprehensive leap in coding and professional work. Autonomously codes and delivers complete projects spanning 10+ days. Handles hundreds of specialized…
Alibaba
Qwen 3.8 Max Prime is the high-speed edition of Qwen 3.8 Max, retaining its 2.4-trillion-parameter MoE architecture and full capabilities while delivering 1.5–2× higher output throughput. Built for coding, office auto…
Alibaba
Qwen3.8-Omni-Flash is Alibaba’s native multimodal model for understanding text, images, audio, and video and generating text. Built on Qwen3.8-Flash-Next, it supports a 1M-token context window, reasoning, and tool cal…
Alibaba
Alibaba
Mixture-of-experts LLM with advanced coding and reasoning capabilities
Alibaba
Qwen3-Coder-Next is an open-weight language model built specifically for coding, with strong performance on large-scale software engineering and agentic coding benchmarks. It uses a hybrid Mixture-of-Experts architect…
Alibaba
A new generation of open-source, non-thinking mode model powered by Qwen3. This version demonstrates superior Chinese text understanding, augmented logical reasoning, and enhanced capabilities in text generation tasks…
Alibaba
Qwen3-Next uses a highly sparse MoE design: 80B total parameters, but only ~3B activated per inference step. Experiments show that, with global load balancing, increasing total expert parameters while keeping activate…
Alibaba
The Qwen3 series VL models has been comprehensively upgraded in areas such as visual coding and spatial perception. Its visual perception and recognition capabilities have significantly improved, supporting the unders…
Alibaba
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advance…
Alibaba
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advance…
Alibaba
Open-weights release of the Qwen3.8 flagship (2.4T MoE, ~95B active); thinking always on with reasoning_effort low/medium/xhigh. The hosted Qwen 3.8 Max (vision, non-thinking, 1M default context) is Alibaba-only.
Alibaba
Built on the architectural foundation of Qwen3.5, Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks. Qwen3.8-27B brings these advances to a compact, deployme…
Alibaba
Qwen3.8-Max-0902 is an upgraded snapshot of qwen3.8-max.
Amazon
Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing...
Amazon
Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text.
Amazon
Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite...
Amazon
Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length...
Amazon
Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.
Amazon
Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December...
Anthracite Org
This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus)…
Anthropic #161
Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...
Anthropic #9
Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...
Anthropic #162
Claude Fable 5.2 is Anthropic's most capable model for the most demanding technical work, with gains over Fable 5.1 in coding, reasoning, and vision. In prerelease testing it completed otherwise-infeasible...
Anthropic #163
Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...
Anthropic #31
Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...
Anthropic
Claude Opus 4 20250514 Coding via TrustedRouter
Anthropic
Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...
Anthropic #164
Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance a…
Anthropic #165
Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...
Anthropic #166
Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...
Anthropic #84
Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...
Anthropic #27
Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...
Anthropic #4
Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...
Anthropic
Claude Sonnet 4 20250514 Coding via TrustedRouter
Anthropic #167
Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...
Anthropic #85
Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end projec…
Anthropic #35
Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high…
Anthropic #12
Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...
BAAI
baai general embedding (base) model that transforms any given text into a 768-dimensional vector
BAAI
baai general embedding (large) model that transforms any given text into a 1024-dimensional vector
BAAI
multi-functionality, multi-linguality, and multi-granularity embeddings model.
BAAI
different from embedding model, reranker uses question and document as input and directly output similarity instead of embedding. you can get a relevance score by inputting query and passage to the reranker. and the s…
BAAI
baai general embedding (small) model that transforms any given text into a 384-dimensional vector
Baichuan #168
Baichuan M2 32B via TrustedRouter
Baidu #169
CoBuddy via TrustedRouter
Baidu
ERNIE 5.5 Flash Preview is the latest foundation model in the ERNIE family, with comprehensive improvements in coding, agentic capabilities, knowledge work, and deep research. It has 280 billion total...
Baidu
ERNIE-Light-DT-1.0 is based on open-source GLM models and includes research findings from Baidu Search's Lightning large model. It features Baidu Sparse Attention (BSA), a unique sparse attention mechanism developed b…
Baseten
Elephant-1 is a 9B decision model from Baseten's Base Labs for classification, routing, and scoring. It evaluates structured context against choice, yes/no, and ordered scoring questions and returns answer probabiliti…
Baseten
Joey-1 is a 2B decision model from Baseten's Base Labs for classification, routing, and scoring. It evaluates text context against choice, yes/no, and ordered scoring questions, returning answer probabilities and conf…
Baseten
Mammoth-1 is a 27B decision model from Baseten's Base Labs, fine-tuned from Qwen3.5-27B for classification, routing, and scoring. It answers multiple-choice, yes/no, and ordered scoring questions with probabilities ov…
Black Forest Labs
FLUX.2 [flex] via TrustedRouter
Black Forest Labs
FLUX.2 [klein] 4B via TrustedRouter
Black Forest Labs
FLUX.2 [klein] 9B via TrustedRouter
Black Forest Labs
FLUX.2 [max] via TrustedRouter
Black Forest Labs
FLUX.2 [pro] via TrustedRouter
BSC-LT #170
alia-salamandra:40b via TrustedRouter
ByteDance Seed #171
Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows. It is suited for end-to-end software delivery, multi-step task execution, and understanding visual and...
ByteDance Seed
Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noticeably lower latency, making it a practical default choice for most productio…
ByteDance Seed
Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It delivers performance comparable to ByteDance-Seed-1.6, supports…
ByteDance
ByteDance Seedance 2.0 via TrustedRouter
ByteDance
ByteDance Seedance 2.0 Fast via TrustedRouter
ByteDance
ByteDance Seedance 2.5 via TrustedRouter
ByteDance #172
ByteDance/Seed-1.8 via TrustedRouter
ByteDance #173
ByteDance/Seed-2.0-code via TrustedRouter
ByteDance #174
ByteDance/Seed-2.0-mini via TrustedRouter
ByteDance #175
ByteDance/Seed-2.0-pro via TrustedRouter
ByteDance #176
dola-seed-2-1-turbo via TrustedRouter
ByteDance #177
Doubao Seed 1.6 via TrustedRouter
ByteDance #178
Doubao Seed 1.6 Flash via TrustedRouter
ByteDance #179
Doubao Seed 1.8 via TrustedRouter
ByteDance #180
Doubao Seed 2.0 Code Preview via TrustedRouter
ByteDance #181
Doubao Seed 2.0 Lite via TrustedRouter
ByteDance #182
Doubao Seed 2.0 Mini via TrustedRouter
ByteDance #183
Doubao Seed 2.0 Pro via TrustedRouter
ByteDance #184
Doubao Seed 2.1 Pro via TrustedRouter
ByteDance #185
Doubao Seed 2.1 Turbo via TrustedRouter
ByteDance #186
Doubao Seed Character via TrustedRouter
ByteDance #187
Doubao Seed Evolving via TrustedRouter
ByteDance
Seed 2.1 Turbo is ByteDance’s multimodal language model supporting text, image, and video inputs with text output. It offers a 262,144-token context window, reasoning, function calling, and structured JSON output.
ByteDance #188
seed-2-0-code via TrustedRouter
ByteDance #189
seed-2-0-lite via TrustedRouter
ByteDance #190
seed-2-0-mini via TrustedRouter
ByteDance #191
seed-2-0-pro via TrustedRouter
ByteDance #192
UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework w…
Callstack
Apex is Callstack’s agentic coding model for mobile and web development, optimized for React Native, React, and Next.js. With a 256K context window, it supports feature development, debugging, code reviews, testing, a…
Cerebras #193
OpenAI GPT OSS via TrustedRouter
Cloudflare
clef is a 27b multimodal decision model that turns a state and a schema of typed questions into decisions. it reads the state as text, json, images, or video, and returns a probability for every allowed option of ever…
Cloudflare
clef-omni is a multimodal decision model built on a 30b-parameter mixture-of-experts (3b active) backbone. it turns a state and a schema of typed questions into decisions, reads the state as text, json, images, audio,…
Cloudflare #194
Preview typed extraction model: extract, compute, estimate or forecast values. Input-only billing, with confidence scores and distributions. Not a conversational model. Weights are not yet public.
Cloudflare #195
Cloudflare Clef-Flash via TrustedRouter
Cognitivecomputations
Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct…
Cohere #196
Cohere Embed English v3.0 via TrustedRouter
Cohere #197
Cohere Embed Multilingual v3.0 via TrustedRouter
Cohere #198
Cohere Embed v4.0 via TrustedRouter
Cohere #199
Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...
Cohere
Command A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supports native tool calling with strict tool schemas, structured...
Cohere
command-r-08-2024 is an update of the Command R with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and...
Cohere
command-r-plus-08-2024 is an update of the Command R+ with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint...
Cohere
Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning...
Cohere
North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...
ConvAI Innovations
Laya is Convai Innovations’ System One evaluation model for fast, structured decisions. It evaluates shared state against choice, score, and yes/no questions and returns typed answers with probabilities in a single fo…
Coralbricks #200
deepseek-v4.1-flash via TrustedRouter
Coralbricks #201
deepseek-v4.1-flash-value via TrustedRouter
Daily
phonellm is an open model tuned for voice agents. the model is based on nemotron nano 30b base capabilities and excels at typical voice agent tasks with thinking disabled.
Dealignai #202
DeepSeek V4.1 Flash Uncensored via TrustedRouter
Decart
Decart Lucy 2.5 via TrustedRouter
Decart
Decart Lucy Restyle 2 via TrustedRouter
Decart
Decart Lucy VTON 3.5 via TrustedRouter
Decart
Lucy Image 2 via TrustedRouter
Decisionmodelsio Eu #203
Fast open typed-decision profile for text decisions; noul/choice/score answers with probabilities in milliseconds. An alias for the current Fast version (see model_version in every response and the S1-Model-Version he…
Decisionmodelsio Eu #204
Current Fast version: a 26B-A4B open typed-decision model; noul/choice/score answers with probabilities. Text only, exactly one question per request, at most 16,192 input tokens and 16 options per question. Billed at…
Decisionmodelsio Eu #205
Larger open typed-decision profile for text decisions; noul/choice/score answers with probabilities. An alias: in the EU tier s1-pro-5 (mammoth-1 27B, MIT, FP8), or s1-pro-3 (vLLM-SR d3 26B, Apache-2.0, FP8) if it can…
Decisionmodelsio Eu #206
Previous Pro version, kept for customers who pin it: Perplexity Decider v1.1 27B, an open typed-decision model served in NVFP4; noul/choice/score answers with probabilities. Available through 30 November 2026. Text on…
Decisionmodelsio Eu #207
Previous Pro version, available through at least 27 January 2027: vLLM-SR d3 26B, an open typed-decision model (Apache-2.0, by the vLLM Semantic Router project), served in FP8; noul/choice/score answers with probabili…
Decisionmodelsio Eu #208
Pinned Pro version: mammoth-1 (baselabs/mammoth-1 revision 61cec44c281c693992e3d6ebeb44dd3402dfa186), a 27B open typed-decision model served in FP8; noul/choice/score answers with probabilities. Text only; up to 3 que…
Decisionmodelsio Eu
Decision Models s1-vision (EU) via TrustedRouter
Decisionmodelsio #209
Fast open typed-decision profile for text decisions; noul/choice/score answers with probabilities in milliseconds. An alias for the current Fast version (see model_version in every response and the S1-Model-Version he…
Decisionmodelsio #210
Current Fast version: a 26B-A4B open typed-decision model; noul/choice/score answers with probabilities. Text only, exactly one question per request, at most 16,192 input tokens and 16 options per question. Billed at…
Decisionmodelsio #211
Larger open typed-decision profile for text decisions; noul/choice/score answers with probabilities. An alias: in the EU tier s1-pro-5 (mammoth-1 27B, MIT, FP8), or s1-pro-3 (vLLM-SR d3 26B, Apache-2.0, FP8) if it can…
Decisionmodelsio #212
Previous Pro version, kept for customers who pin it: Perplexity Decider v1.1 27B, an open typed-decision model served in NVFP4; noul/choice/score answers with probabilities. Available through 30 November 2026. Text on…
Decisionmodelsio #213
Previous Pro version, available through at least 27 January 2027: vLLM-SR d3 26B, an open typed-decision model (Apache-2.0, by the vLLM Semantic Router project), served in FP8; noul/choice/score answers with probabili…
Decisionmodelsio
Decision Models s1-vision (GLOBAL) via TrustedRouter
DeepSeek #214
@cf/deepseek-ai/deepseek-r1-distill-qwen-32b via TrustedRouter
DeepSeek #215
Fetch a public web page as Markdown. Billed per successful nonempty response, not tokens.
DeepSeek #216
DeepSeek OCR via TrustedRouter
DeepSeek #86
DeepSeek OCR 2 via TrustedRouter
DeepSeek
DeepSeek R1 Distill Qwen3 8B 0528 via TrustedRouter
DeepSeek #217
DeepSeek R1 Turbo via TrustedRouter
DeepSeek
DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the DeepSeek V3 model and performs really well...
DeepSeek
DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...
DeepSeek #218
DeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizin…
DeepSeek #40
DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse…
DeepSeek #219
DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attent…
DeepSeek
DeepSeek‑V3.2 from DeepSeek harmonizes high computational efficiency with superior reasoning and agent performance. It builds on three main techniques: DeepSeek Sparse Attention for long‑context efficiency, a scalable…
DeepSeek #6
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...
DeepSeek #5
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....
DeepSeek #87
DeepSeek V4 Flash 0731 Fast via TrustedRouter
DeepSeek #88
DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731 from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...
DeepSeek #42
DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...
DeepSeek #55
DeepSeek V4 Pro 0423 via TrustedRouter
DeepSeek #220
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.
DeepSeek #2
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
DeepSeek #221
DeepSeek V4.1 Flash via TrustedRouter
DeepSeek #222
DeepSeek V4.1 Flash (rolling) via TrustedRouter
DeepSeek #9
DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name. V4.1 Flash is a sparse mixture-of-experts model...
DeepSeek #223
DeepSeek V4.1 Flash 1017 Fast via TrustedRouter
DeepSeek #224
DeepSeek V4.1 Flash 1017 Ultrafast via TrustedRouter
DeepSeek #225
DeepSeek V4.1 Flash 1017 Uncensored via TrustedRouter
DeepSeek #226
DeepSeek V4.1 Flash DST via TrustedRouter
DeepSeek #227
DeepSeek V4.1 Flash Fast via TrustedRouter
DeepSeek #228
DeepSeek V4.1 Flash Uncensored via TrustedRouter
DeepSeek #89
deepseek-ai/DeepSeek-V3 via TrustedRouter
DeepSeek
DeepSeek-R1 provides customers a state-of-the-art reasoning model, optimized for general reasoning tasks, math, science, and code generation.
DeepSeek #229
DeepSeek-V4-Flash-0423 via TrustedRouter
DeepSeek #230
deepseek/deepseek-v4-flash-0731-p via TrustedRouter
DeepSeek #231
deepseek/deepseek-v4-pro-0813-p via TrustedRouter
DeepSeek #56
May 28th update to the original DeepSeek R1 Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...
Dots Studio
Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total. It is the lightest model in the Dots 3 family and is...
ElevenLabs #232
Text-to-speech, billed per input character, not per token.
ElevenLabs #233
Text-to-speech, billed per input character, not per token.
ElevenLabs
A speech-to-speech voice agent optimized for complex instructions, reasoning, and multi-step tool use, with speech recognition, turn-taking, and voice generation tuned as one system. Supports more than 90 languages th…
ElevenLabs
A speech-to-speech voice agent optimized for fast, natural conversation, with speech recognition, turn-taking, interruption handling, and voice generation tuned as one system. Supports more than 90 languages through a…
ElevenLabs #234
Text-to-speech, billed per input character, not per token.
ElevenLabs #235
Text-to-speech, billed per input character, not per token.
Elorian
Glimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical world. It reasons directly over images and video rather than...
Fal
FLUX.1 Schnell on FAL via TrustedRouter
Fireworks
Ember-1 is a specialized reasoning model from Fireworks Research, built on Kimi K3. It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40%...
Fortanix #236
GLM 5.3 Flash hosted by Fortanix in Santa Clara, California (operator-declared location). Managed-route ZDR. Introductory pricing: $0.01 per million input tokens and $0.01 per million output tokens. The standard $0.00…
Gmicloud
ricursiveAI/Ripple-65B-Preview via TrustedRouter
embeddinggemma 2 is an open multimodal embedding model built by google deepmind which maps text (incl. code), images, video, and audio inputs—and combinations thereof—into a single, unified 768-dimensional vector space.
Google #47
Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to prov…
Google #43
Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...
Google #57
Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhance…
Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhance…
Google's most intelligent model built for speed, combining frontier intelligence with superior search and grounding.
Google #26
Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...
Google #41
Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...
Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across...
Google #32
Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the…
Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party...
Google #90
Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...
Google #91
Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.
Transcription by google
Google #92
Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...
Google #93
Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...
Google #21
Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.
Google #237
Text-to-speech, billed from reported text input and audio output tokens.
Google #238
Text-to-speech, billed from reported text input and audio output tokens.
Gemini 3.8 Live is Google's model for real-time audio conversations. It supports spoken interactions for developers building voice assistants, conversational experiences, and applications that respond to users through…
Gemini 3.8 Live Extended Thinking is Google's real-time audio model with extended thinking capabilities. It combines spoken interaction with additional reasoning for voice assistants and other conversational applicati…
Google #22
Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...
Google #94
Gemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work. It takes text, image, audio, video and file input, supports long decode...
Google #239
Gemini 4 Hydrogen is the high-efficiency workhorse model of the Gemini 4 family from Google, built for high-throughput agentic workflows, coding and multi-model routing at lower cost and latency than...
Gemini Decisions is Google's evaluation model for classification, routing, and scoring. It answers structured questions with Boolean probabilities, choices, and scores, returning confidence values and probability dist…
Google #240
Gemini Embedding 001 via TrustedRouter
Google #241
Gemini Omni 1.1 Flash is Google's native multimodal video generation and editing model, the generally available successor to Gemini Omni Flash Preview. It is suited for text-to-video, image-to-video, first and...
Gemini Omni 1.2 Flash is Google's native multimodal video generation and editing model, the successor to Gemini Omni 1.1 Flash. It generates clips up to 15 seconds long with native...
Gemini Omni Flash (Preview) is a multimodal model designed for video, image, and text tasks. It is optimized for video generation, offering video output alongside text responses in a single model.
Gemma 2 27B by Google is an open model built from the same research and technology used to create the Gemini models. Gemma models are well-suited for a variety of...
gemma 2 2b it via TrustedRouter
Google #31
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabili…
Google #28
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabili…
Google #95
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabili…
Google #19
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
Google #34
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
Google #242
Gemma 4 Uncensored via TrustedRouter
Google #96
gemma-4-12B-it via TrustedRouter
Google Gemini Omni Flash via TrustedRouter
Google Veo 3.1 via TrustedRouter
Google Veo 3.1 Fast via TrustedRouter
Google #243
google/gemini-3.1-pro via TrustedRouter
Google #244
google/gemma-4-31B-it-turbo via TrustedRouter
Google #245
google/gemma-4-31B-it-Ultra via TrustedRouter
Google #246
google/gemma-4-31B-turbo via TrustedRouter
30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate...
Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality, 48kHz...
google's fast image generation model producing high-quality images from text prompts. image generation fast
Gemini 2.5 Flash Image, a.k.a. "Nano Banana," is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation,...
google's second-generation image generation model with improved quality and speed. image generation fast high quality
Google #247
Gemini 3.1 Flash Image Preview, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines...
Google #248
Gemini 3.1 Flash Image, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...
google's fastest gemini image generation model for rapid image creation and iteration. image generation fast image editing
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image ge…
Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization,...
google's nano banana 2.1 image generation and editing model, optimized for a balance of quality and performance. image generation image editing fast high quality
google's higher-quality image generation model with improved detail and prompt adherence. image generation high quality
Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...
Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...
Google #249
nvidia/Gemma-4-31B-IT-NVFP4 via TrustedRouter
Gryphe #250
One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge
Hugging Face
distilled bert model that was finetuned on sst-2 for sentiment classification
Humansand
Ampersand v0.1 is a collaborator model from Humans& for shared goals, group conversations, and long-running collaboration. Its Responses API supports text, reasoning, client-side function tools, and implicit prompt ca…
IBM Granite
granite 4.0 instruct models deliver strong performance across benchmarks, achieving industry-leading results in key agentic tasks like instruction following and function calling. these efficiencies make the models wel…
IBM Granite #251
granite-4.1-8b via TrustedRouter
IBM Granite #97
Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort,...
Inception #252
Inception: Mercury 2 via TrustedRouter
Inception #253
Inception: Mercury 2.5 via TrustedRouter
Inception #254
Inception: Mercury 3 via TrustedRouter
Inception
Mercury Coder Small is ideal for code generation, debugging, and refactoring tasks with minimal latency.
InclusionAI #98
Ling-3.0-flash is a 124B-parameter Mixture-of-Experts (MoE) model, with approximately 5.1B parameters activated per token. The model is designed with token efficiency and production-scale agentic inference as key prio…
InclusionAI
inclusionAI: Ling 3.0 Flash Fin via TrustedRouter
InclusionAI
inclusionAI: Ling 3.0 Flash Sante via TrustedRouter
InclusionAI #255
Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding native visual perception and advanced visual...
InclusionAI
Ling 3.0 Tiny is a mixture-of-experts model from InclusionAI, with 1.3B active parameters out of 7.9B total. It is designed for responsive agents, instruction following, and multi-turn conversations, with switchable...
InclusionAI
Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.
InclusionAI
Ling 3.2 Flash is a hybrid reasoning model from inclusionAI that accepts text and image input, with a 1M-token context window and up to 200 images per request. Thinking can...
InclusionAI
Ling 3.1 Flash 1019 is InclusionAI's updated hybrid reasoning language model for coding, multi-step analysis, and tool-using agents. Its mixture-of-experts architecture has 560B total parameters with 25B active per to…
Inference Net
Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and long pages. Extraction instructions must be supplied through a JSON sch…
Inference Net
Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads. Extraction instructions must be supplied through a JSON schema in…
Intel #256
Intel: Qwen3 Coder 480B A35B Instruct INT4 Mixed AR via TrustedRouter
Interfaze
Interfaze is an AI model built on a new architecture that merges specialized DNN/CNN models with LLMs for developer tasks that require deterministic output and high consistency like OCR, scraping, classification, STT…
Intfloat
Multilingual E5 Large Instruct via TrustedRouter
Jina AI #257
Jina AI: Jina Clip v1 via TrustedRouter
Jina AI #258
Jina AI: Jina Clip v2 via TrustedRouter
Jina AI #259
Jina AI: Jina Code Embeddings 0.5b via TrustedRouter
Jina AI #260
Jina AI: Jina Code Embeddings 1.5b via TrustedRouter
Jina AI #261
Jina AI: Jina Colbert v2 via TrustedRouter
Jina AI #262
Jina AI: Jina Embedding B EN v1 via TrustedRouter
Jina AI #263
Jina AI: Jina Embeddings v2 Base Code via TrustedRouter
Jina AI #264
Jina AI: Jina Embeddings v2 Base DE via TrustedRouter
Jina AI #265
Jina AI: Jina Embeddings v2 Base EN via TrustedRouter
Jina AI #266
Jina AI: Jina Embeddings v2 Base ES via TrustedRouter
Jina AI #267
Jina AI: Jina Embeddings v2 Base ZH via TrustedRouter
Jina AI #268
Jina AI: Jina Embeddings v3 via TrustedRouter
Jina AI #269
Jina AI: Jina Embeddings v4 via TrustedRouter
Jina AI #270
Jina AI: Jina Embeddings v5 Omni Nano via TrustedRouter
Jina AI #271
Jina AI: Jina Embeddings v5 Omni Small via TrustedRouter
Jina AI #272
Jina AI: Jina Embeddings v5 Text Nano via TrustedRouter
Jina AI #273
Jina AI: Jina Embeddings v5 Text Small via TrustedRouter
Kling
Kling Video 3.0 Omni Pro via TrustedRouter
Kling
Kling Video 3.0 Pro via TrustedRouter
Krea
Krea 2 Medium via TrustedRouter
KT
Mi:dm K 3.0 Pro is a Mixture-of-Experts reasoning model from KT, with 120B total and 12B active parameters. It uses a hybrid architecture that mixes Mamba, MoE and attention layers.
Kwaipilot #274
KAT Coder Air V2.5 via TrustedRouter
Lightricks
Lightricks LTX 2.3 via TrustedRouter
Lightricks
Lightricks LTX 2.3 Fast via TrustedRouter
Liquid AI
LFM2.5-24B-A2B is a text-generation model from Liquid AI with a 128,000-token context window.
Liquid AI
Liquid d1 is a decision model for classification, routing, and scoring. It evaluates shared state against typed Choice, Score, and yes/no questions and returns structured answers with calibrated probabilities through…
Liquid AI
Liquid d1-ultra is a multimodal decision model for classification, routing, and scoring across text and images, with a 32,768-token context window. It returns calibrated probabilities for yes/no, multiple-choice, and…
Liquid AI
LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid...
Liquid AI
A compact 1.7B-parameter text model with a 256K-token context, post-trained for agents, tool calling, and structured outputs. It reasons before it answers. Prompts and outputs may be retained and used...
Mancer
An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations.
Meituan Longcat #275
LongCat 2.0 via TrustedRouter
Meituan
LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic...
Meituan
LongCat 2.5 is Meituan’s native multimodal model for coding and long-running agent workflows. It combines visual understanding with multi-step reasoning and tool use to work across complex codebases and full-project d…
Meta Llama #276
@cf/meta/llama-3.1-8b-instruct-fp8 via TrustedRouter
Meta Llama #277
@cf/meta/llama-3.2-11b-vision-instruct via TrustedRouter
Meta Llama #278
@cf/meta/llama-3.3-70b-instruct-fp8-fast via TrustedRouter
Meta Llama #279
Llama 3.2 3B via TrustedRouter
Meta Llama #280
Llama 3.3 70B via TrustedRouter
Meta Llama #99
Llama 4 Maverick Instruct via TrustedRouter
Meta Llama #58
Llama 4 Scout Instruct via TrustedRouter
Meta Llama
Meta Llama 3.1 8B Instruct via TrustedRouter
Meta Llama #281
meta-llama/Llama-3.3-70B-Instruct-Turbo via TrustedRouter
Meta Llama #282
meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo via TrustedRouter
Meta Llama
Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong...
Meta Llama #59
Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...
Meta Llama #283
Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate...
Meta Llama #284
Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transf…
Meta Llama #21
The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...
Meta Llama #100
Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...
Meta Llama
Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...
Meta Llama #101
Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...
Meta Llama #285
meta/llama-3.2-90b-vision-instruct via TrustedRouter
Meta Models #286
meta-models/Muse-Glimmer-30B via TrustedRouter
Meta Models #102
Muse Spark Open via TrustedRouter
Meta
An update to Meta Llama 3 70B Instruct that includes an expanded 128K context length, multilinguality and improved reasoning capabilities.
Meta
An update to Meta Llama 3 8B Instruct that includes an expanded 128K context length, multilinguality and improved reasoning capabilities.
Meta
Where performance meets efficiency. This model supports high-performance conversational AI designed for content creation, enterprise applications, and research, offering advanced language understanding capabilities, i…
Meta
As a general purpose LLM, Llama 4 Maverick contains 17 billion active parameters, 128 experts, and 400 billion total parameters, offering high quality at a lower price compared to Llama 3.3 70B.
Meta
Llama 4 Scout is the best multimodal model in the world in its class and is more powerful than our Llama 3 models, while fitting in a single H100 GPU. Additionally, Llama 4 Scout supports an industry-leading context w…
Meta
llama 3.1 8b quantized to fp8 precision
Meta
the llama 3.2-vision instruction-tuned models are optimized for visual recognition, image reasoning, captioning, and answering general questions about an image.
Meta
the llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks.
Meta
the llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks.
Meta
llama 3.3 70b quantized to fp8 precision, optimized to be faster.
Meta
meta's llama 4 scout is a 17 billion parameter model with 16 experts that is natively multimodal. these models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image underst…
Meta
llama guard 3 is a llama-3.1-8b pretrained model, fine-tuned for content safety classification. similar to previous versions, it can be used to classify content in both llm inputs (prompt classification) and in llm re…
Meta
multilingual encoder-decoder (seq-to-seq) model trained for many-to-many multilingual translation
Meta
Muse Ember is the smallest and most efficient model from Meta that’s designed for complex reasoning execution and the work agents repeat all day: tool calls, coding agent subtasks, routing,...
Meta
Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...
Meta #287
Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, and PDF documents and returns text, with a 1M-token context window....
Meta #288
Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, and PDF documents, returns text, and offers a 1M-token context window....
Meta
Muse Spark 1.2 contributor tier is a reasoning model from Meta designed for developers who want to start building at an even lower cost. It’s meaningfully cheaper than Muse Spark...
Meta #289
Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It is designed to keep track of information across extended tasks, work through...
Meta #23
Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and early-stage agentic, multi-agent, and coding workflows. It is designed to track…
Meta
Muse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase understanding across the…
Meta
Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with...
Microsoft #290
Text-to-speech, billed per input character, not per token.
Microsoft #291
Text-to-speech, billed per input character, not per token.
Microsoft #292
Microsoft Decision-1 via TrustedRouter
Microsoft #293
Microsoft Research Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...
Microsoft #294
WizardLM 2 8x22B via TrustedRouter
Mindai #295
Macaron V1 Tall via TrustedRouter
Mindai #296
Macaron V1 Venti via TrustedRouter
MiniMax
MiniMax H3 Max via TrustedRouter
MiniMax
MiniMax Hailuo 3 (H3) via TrustedRouter
MiniMax #297
MiniMax M1 via TrustedRouter
MiniMax
MiniMax-M2.1-lightning is a faster version of MiniMax-M2.1, offering the same performance but with significantly higher throughput (output speed ~100 TPS, MiniMax-M2 output speed ~60 TPS).
MiniMax #32
MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...
MiniMax #298
MiniMax M2.5 via TrustedRouter
MiniMax
M2.5 highspeed: Same performance, faster and more agile (output speed approximately 100 tps)
MiniMax #103
MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic…
MiniMax #299
MiniMax M2.7 via TrustedRouter
MiniMax
minimax's m2.7 language model with multilingual capabilities. llm multilingual
MiniMax
M2.7 Highspeed: Same performance, faster and more agile (output speed approximately 100 tps)
MiniMax #17
MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...
MiniMax #300
MiniMax M3 Preview via TrustedRouter
MiniMax #19
MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built f…
MiniMax
minimax m3.1 flash is a fast, cost-efficient multimodal model for agentic tasks, coding, and computer use. it accepts text, image, and video input, always reasons before answering with adjustable effort, and has a 1m-…
MiniMax #104
minimax-m2 via TrustedRouter
MiniMax #301
minimax-m2.1 via TrustedRouter
Mistral AI #302
devstral-2-123b via TrustedRouter
Mistral AI #303
magistral-small-2509 via TrustedRouter
Mistral AI
Ministral 3 14B is the largest model in the Ministral 3 family, offering state-of-the-art capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. Optimized for local deployment, it del…
Mistral AI #105
Ministral 3 14B Instruct via TrustedRouter
Mistral AI
A compact, efficient model for on-device tasks like smart assistants and local analytics, offering low-latency performance.
Mistral AI
A more powerful model with faster, memory-efficient inference, ideal for complex workflows and demanding edge applications.
Mistral AI #304
ministral-3-3b-instruct via TrustedRouter
Mistral AI #305
ministral-3-8b-instruct via TrustedRouter
Mistral AI
This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement here....
Mistral AI
Mistral Large 3 2512 is Mistral’s most capable model to date. It has a sparse mixture-of-experts architecture with 41B active parameters (675B total).
Mistral AI #306
mistral-medium-3.5-128b via TrustedRouter
Mistral AI #307
Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. Blog Post
Mistral AI
Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...
Mistral AI #308
The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...
Mistral AI #309
The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.
Mistral AI #310
A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.
Mistral AI #106
Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.
Mistral AI
Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with up...
Mistral AI #311
Mistral: Mistral Large 4 via TrustedRouter
Mistral AI
Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal p…
Mistral AI
Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It b…
Mistral AI
Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...
Mistral AI
A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...
Mistral AI #312
Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions design…
Mistral AI #313
Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning…
Mistral AI
Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 sig…
Mistral AI #107
Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...
Mistral AI
Mistral's official instruct fine-tuned version of Mixtral 8x22B. It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,...
Mistral AI
Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on cura…
Mistral AI #314
Text-to-speech, billed per request over an attested connection.
Mistral AI #315
Text-to-speech, billed per input character, not per token.
Mistral AI
Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio unde…
Mistral AI #316
mistralai/mistral-large-4-1t-a52b via TrustedRouter
Mistral AI #108
mistralai/Mistral-Nemo-Instruct-2407 via TrustedRouter
Mistral AI #109
mistralai/Mistral-Small-3.2-24B-Instruct-2506 via TrustedRouter
Mistral AI #317
File transcription, billed per request or audio duration, not text tokens.
Mistral AI #318
File transcription, billed per request or audio duration, not text tokens.
Mistral AI #319
File transcription, billed from reported audio input and text output tokens.
Mixedbread
Built for knowledge-intensive questions, multi-step retrieval, and evidence synthesis. Toast 1 can work with any backend exposed through function calling.
Moondream
Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over images, with...
Moondream
Moondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and...
Moonshot AI #110
Kimi K2 Instruct via TrustedRouter
Moonshot AI #320
Kimi K2.8 Preview via TrustedRouter
Moonshot AI #321
Kimi K3 via TrustedRouter
Moonshot AI #322
Kimi K3 Fast via TrustedRouter
Moonshot AI #323
Kimi K3 Fast on Fireworks via TrustedRouter
Moonshot AI #111
Kimi K3.1 Pro Highspeed via TrustedRouter
Moonshot AI
Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...
Moonshot AI #324
Kimi K2 0905 is the September update of Kimi K2 0711. It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...
Moonshot AI #112
MoonshotAI: Kimi K2 Instruct 0905 via TrustedRouter
Moonshot AI #60
Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introdu…
Moonshot AI #26
Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mix…
Moonshot AI #10
Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, R…
Moonshot AI #15
MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...
Moonshot AI #17
Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...
Moonshot AI #8
Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...
Moonshot AI #113
moonshotai/Kimi: K2.7-Code-Highspeed via TrustedRouter
Morph #325
Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <c…
Morph #326
Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</…
Motif Technologies
Motif 3 is a Mixture-of-Experts language model from Motif Technologies, with 314B total and 13.2B active parameters. It is a general-purpose multilingual model for English and Korean, particularly strong at...
Nace AI
Drex 2.0 is Nace AI's text evaluation model for boolean, choice, and score questions over shared text or JSON state. It returns calibrated probabilities for routing, classification, and scoring, with a 131,072-token s…
Nace AI
Drex Max Finance is Nace AI's multimodal evaluation model for financial workflows. It answers boolean, choice, and score questions over text and images with calibrated probabilities. Its 262,144-token limit covers the…
Nace AI
Drex Max v1.1 is Nace AI's multimodal evaluation model for boolean, choice, and score questions over text and images. It returns structured answers and probability distributions. Its 262,144-token limit applies to the…
Neurometric #327
Classifies one or more requests against a caller-defined taxonomy and uses an explicit fallback when no supplied label applies.
Neurometric #328
Converts a labeled business conversation into a structured current-state summary of the final decision, status, open actions, owners, deadlines, and risks.
Neurometric #329
Extracts caller-selected fields from invoices, contracts, forms, tickets, and other document text into typed JSON.
Neurometric #330
Answers questions only from supplied document chunks, cites the supporting chunk, and abstains when the answer is not present.
Neurometric #331
tool-choice via TrustedRouter
Nex AGI
Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...
Nex AGI
Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...
Nex AGI
Nex-N2.6 is an agentic model from Nex AGI, built on GLM-5.3-Flash with about 321B parameters. It is suited for computer use, coding, and long-horizon tasks that involve tools. Compared with...
Nomic AI #332
Nomic Embed Text via TrustedRouter
Nous Research
Hermes 2 Pro Llama 3 8B via TrustedRouter
Nous Research #333
Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...
NVIDIA #334
@cf/nvidia/nemotron-3-120b-a12b via TrustedRouter
NVIDIA #114
NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...
NVIDIA #335
NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...
NVIDIA #61
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...
NVIDIA #28
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
NVIDIA
NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...
NVIDIA #62
NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...
NVIDIA
Nemotron 3.5 Lightning is an open-weight reasoning and chat model for long-running agents, sub-agent work, chatbots, and RAG systems. The model has 30B parameters with 3B active per token, in a hybrid Mixture-of-Exper…
NVIDIA #18
NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...
NVIDIA #115
Nemotron 3.5 Super VL via TrustedRouter
NVIDIA #336
nemotron-nano-12b-v2 via TrustedRouter
NVIDIA #337
nemotron-nano-9b-v2 via TrustedRouter
NVIDIA
The model is an auto-regressive vision language model that uses an optimized transformer architecture. The model enables multi-image reasoning and video understanding, along with strong document intelligence, visual Q…
NVIDIA #338
nvidia/nemotron-3.5-bolt-e4b via TrustedRouter
NVIDIA #63
nvidia/Nemotron-3.5-Lightning-30B-A3B via TrustedRouter
NVIDIA #339
nvidia/Nemotron-Content-Safety-3.5 via TrustedRouter
NVIDIA
Switchyard is an open-source model routing system that switches between multiple models to optimize the cost of requests. By default it will use OpenRouter market data to select the most...
OpenAI
decisions uses gpt-6 luna to evaluate shared text or image evidence against typed questions. it returns probabilities, fixed choices, or rubric scores for low-latency classification, routing, and prioritization workfl…
OpenAI
An upgraded version of GPT-5 that adapts thinking time more precisely to the question to spend more time on complex questions and respond more quickly to simpler tasks.
OpenAI #340
GPT 5.6 Luna via TrustedRouter
OpenAI #341
GPT 5.6 Sol via TrustedRouter
OpenAI #342
GPT 5.6 Sol via TrustedRouter
OpenAI #343
GPT 5.6 Terra via TrustedRouter
OpenAI #344
GPT 6 Sol via TrustedRouter
OpenAI
The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced...
OpenAI
A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Input is priced at $0.60 per million...
OpenAI
openai's image generation model that creates and edits images from text prompts, supporting multiple quality levels and output sizes. image generation image editing multimodal
OpenAI
openai's next-generation image model that creates and edits images from text prompts, with support for multiple quality levels, sizes, and output formats. note: transparent backgrounds are not supported — use openai/g…
OpenAI #345
GPT Image 2.5 Flare via TrustedRouter
OpenAI #346
GPT Image 2.5 Sunburst via TrustedRouter
OpenAI
GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data up to Sep 2021.
OpenAI
This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up...
OpenAI
OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning...
OpenAI
The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to December 2023.
OpenAI #347
GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o…
OpenAI #348
GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...
OpenAI
For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...
OpenAI #349
GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of GPT-4 Turbo while being twice as...
OpenAI
GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of GPT-4 Turbo while being twice as...
OpenAI
The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more here. GPT-4o ("o" for "omni") is...
OpenAI
The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded...
OpenAI
GPT-4o mini Transcribe is a speech-to-text model that uses GPT-4o mini to transcribe audio. It offers improvements to word error rate and better language recognition and accuracy compared to original Whisper models. U…
OpenAI
GPT-4o Transcribe is a speech-to-text model that uses GPT-4o to transcribe audio. It offers improvements to word error rate and better language recognition and accuracy compared to original Whisper models. Use it for…
OpenAI #350
GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...
OpenAI
GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...
OpenAI #351
GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and acc…
OpenAI
GPT-5 Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior in…
OpenAI
GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by GPT-5 Mini, with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, t…
OpenAI #116
GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....
OpenAI #352
GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...
OpenAI
GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...
OpenAI
GPT-5-Codex is a version of GPT-5 optimized for agentic coding tasks in Codex or similar environments.
OpenAI #353
GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive…
OpenAI
GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineerin…
OpenAI
GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic...
OpenAI
GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex
OpenAI #44
GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding qui…
OpenAI
GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on...
OpenAI
GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...
OpenAI
GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engine…
OpenAI
GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It…
OpenAI
GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...
OpenAI
GPT-5.4 Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding,…
OpenAI #354
GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...
OpenAI #45
GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...
OpenAI
GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...
OpenAI #117
GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...
OpenAI
GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for...
OpenAI #30
GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoni…
OpenAI
GPT-5.6 Luna Pro is the same underlying model as GPT-5.6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more...
OpenAI #29
GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...
OpenAI #39
GPT-5.6 Sol Pro is the same underlying model as GPT-5.6 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more...
OpenAI #15
GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...
OpenAI
GPT-5.6 Terra Pro is the same underlying model as GPT-5.6 Terra, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more...
OpenAI #10
GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-…
OpenAI #16
GPT-6 Astra Pro is the same underlying model as GPT-6 Astra, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more...
OpenAI #7
GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...
OpenAI #11
GPT-6 Luna Decisions evaluates classification and scoring questions against shared text and image input using OpenAI's Decisions API. It supports predicate, choice, and score questions with probabilities and confidenc…
OpenAI
GPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more...
OpenAI #118
GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional...
OpenAI
GPT-6 Sol Pro is the same underlying model as GPT-6 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more...
OpenAI #13
GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional...
OpenAI
GPT-6.1 Sol Pro is the same underlying model as GPT-6.1 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more...
OpenAI
GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots...
OpenAI
GPT-6.1 Terra Pro is the same underlying model as GPT-6.1 Terra, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more...
OpenAI #119
GPT-OSS Safeguard 120B via TrustedRouter
OpenAI #6
gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forwa…
OpenAI #20
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...
OpenAI #355
gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, L…
OpenAI
GPT-Realtime mini is capable of responding to audio and text inputs in realtime over WebRTC, WebSocket, or SIP connections.
OpenAI
GPT-Realtime-1.5 is our flagship audio model for voice agents and customer support.
OpenAI
GPT Realtime 2 is our most capable realtime voice model. It supports speech-to-speech interactions with configurable reasoning effort, stronger instruction following, and more reliable tool use for complex voice-agent…
OpenAI
GPT-Realtime-2.1 updates GPT-Realtime-2 with improved alphanumeric recognition, silence and noise handling, and interruption behavior. It supports speech-to-speech interactions with configurable reasoning effort, inst…
OpenAI
o1 is OpenAI's flagship reasoning model, designed for complex problems that require deep thinking. It provides strong reasoning capabilities with improved accuracy for complex multi-step tasks.
OpenAI #356
o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....
OpenAI
OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the reasoning_effort parameter, which can be set to...
OpenAI
The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently...
OpenAI
OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive…
OpenAI
OpenAI Sora 2 via TrustedRouter
OpenAI
OpenAI Sora 2 Pro via TrustedRouter
OpenAI #357
OpenAI Text Embedding 3 Large via TrustedRouter
OpenAI #358
OpenAI Text Embedding 3 Small via TrustedRouter
OpenAI #359
OpenAI Text Embedding Ada 002 via TrustedRouter
OpenAI #360
File transcription, billed per request or audio duration, not text tokens.
OpenAI #361
openai/gpt-oss-120b-Ultra via TrustedRouter
OpenAI #362
File transcription, billed per request or audio duration, not text tokens.
OpenAI #363
File transcription, billed per request or audio duration, not text tokens.
OpenRouter
Auto Code is OpenRouter’s router built specifically for coding agents and harnesses. It uses the same routing engine as the Auto Router, with every request treated as part of an...
OpenRouter
Auto is OpenRouter’s flagship model router, built for general-purpose usage. It adapts to each request, choosing cost-optimal models and adjusting reasoning effort. It balances task difficulty, benchmark results, live…
OpenRouter
The experimental version of our Auto Router where we test new improvements. Use it to get the latest and greatest version of our general purpose auto router, but expect beta...
OpenRouter
Transform your natural language requests into structured OpenRouter API request objects. Describe what you want to accomplish with AI models, and Body Builder will construct the appropriate API calls. Example:...
OpenRouter
The simplest way to get free inference. openrouter/free is a router that selects free models at random from the models available on OpenRouter. The router smartly filters for models that...
OpenRouter
Fusion turns your prompt into a small multi-model deliberation. A panel of expert models (see below) analyzes your prompt in parallel with web search and web fetch enabled, then a...
OpenRouter
The Pareto Router maintains a tiered shortlist of strong coding models, ranked by Artificial Analysis coding percentiles. Set min_coding_score between 0 and 1 on the pareto-router plugin to control how...
Orcarouter #364
qwen-3.8-27b-uncensored via TrustedRouter
Paddlepaddle
PaddleOCR VL via TrustedRouter
Paper Instruments
Ultramarine 1 Flash is an open-weight multimodal reasoning model from Paper Instruments, post-trained from GLM-5.3 Flash for knowledge work in enterprise operations, finance, law, and consulting. It supports long-cont…
Parasail
Parasail Liberty 2.0 via TrustedRouter
Particle AI
Particle-1 is a token-efficient agentic coding model from Particle AI, post-trained on DeepSeek V4.1 Flash. It is suited for software engineering work such as terminal workflows, codebase changes, and data...
Perceptron
Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning. It accepts image and video inputs paired with natural language queries, and produces detailed visual un…
Perceptron
Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with text plus optional structured annotations: points, boxes, polygons, track…
Perplexity
Perplexity Decider Flash V1.2 is a 4B multimodal decision model for high-volume classification, routing, labeling, and filtering. It evaluates text, structured JSON, and images against yes/no questions, custom choices…
Perplexity
Perplexity Decider Flash V1.3 is a multimodal decision model for high-volume classification, routing, labeling, and filtering. It evaluates text, structured JSON, and images against yes/no questions, custom choices, a…
Perplexity #33
Perplexity Decider V1.2 is a 27B multimodal decision model for classification, routing, and scoring. It evaluates text, structured JSON, and images against yes/no questions, custom choices, and ordered rubrics, return…
Perplexity
Perplexity Decider V1.3 is a multimodal decision model for classification, routing, and scoring. It evaluates text, structured JSON, and images against yes/no questions, custom choices, and ordered rubrics, returning…
Perplexity
Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features...
Perplexity
Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it ga…
Perplexity
Note: Sonar Pro pricing includes Perplexity search pricing. See details here For enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like...
Perplexity
Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based...
Perplexity
Note: Sonar Pro pricing includes Perplexity search pricing. See details here Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for...
PFN
plamo-embedding-1b is a japanese text embedding model developed by preferred networks, inc. it can convert japanese text input into numerical vectors and can be used for a wide range of applications, including inform…
Pixverse
PixVerse C1 via TrustedRouter
Poolside #365
Laguna-S-2.1 via TrustedRouter
Poolside #366
poolside/laguna-xs-2.1 via TrustedRouter
Prism ML
Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window. Ternary compression shrin…
Prism ML
Ternary Bonsai 2 9B is PrismML’s compact, open-weight language model for conversational AI, reasoning, and tool use. Built on Qwen3.5, it uses ternary weights packed into 2 bits for efficient...
Prism ML #367
Ternary Bonsai 27B via TrustedRouter
QuiverAI
SVG generation model with agentic refinement and tool calling.
QuiverAI
Higher-refinement Arrow 2 variant combining Arrow's speed with frontier-model reasoning.
Qwen #368
@cf/qwen/qwen2.5-coder-32b-instruct via TrustedRouter
Qwen #369
@cf/qwen/qwen3-30b-a3b-fp8 via TrustedRouter
Qwen #370
@cf/qwen/qwq-32b via TrustedRouter
Qwen #371
Qwen 3 Next 80b via TrustedRouter
Qwen #372
Qwen 3.6 Plus Uncensored via TrustedRouter
Qwen #373
Qwen 3.7 Max via TrustedRouter
Qwen #374
Qwen 3.7 Plus via TrustedRouter
Qwen #375
Qwen 3.8 2.4T via TrustedRouter
Qwen #376
Qwen 3.8 Flash via TrustedRouter
Qwen #377
Qwen 3.8 Max via TrustedRouter
Qwen #378
Qwen Flash via TrustedRouter
Qwen #379
Qwen Flash 2025 07 28 via TrustedRouter
Qwen #380
Qwen MT Flash via TrustedRouter
Qwen #381
Qwen MT Lite via TrustedRouter
Qwen #120
Qwen MT Plus via TrustedRouter
Qwen #382
Qwen Plus 2025 07 28 via TrustedRouter
Qwen #383
Qwen Plus 2025 09 11 via TrustedRouter
Qwen #384
Qwen Plus 2025 12 01 via TrustedRouter
Qwen #385
Qwen Plus Character via TrustedRouter
Qwen #386
Qwen VL OCR via TrustedRouter
Qwen #387
Qwen VL OCR 2025 11 20 via TrustedRouter
Qwen #388
Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.
Qwen #389
Qwen/Qwen-AgentWorld-35B-A3B via TrustedRouter
Qwen #390
Qwen/Qwen2.5-72B-Instruct via TrustedRouter
Qwen
Qwen/Qwen3-235B-A22B-Instruct-2507-FP8 via TrustedRouter
Qwen
Qwen/Qwen3-235B-A22B-Thinking-2507-FP8 via TrustedRouter
Qwen #391
Qwen/Qwen3-4B-Instruct-2507 via TrustedRouter
Qwen #392
Qwen/Qwen3-4B-Thinking-2507 via TrustedRouter
Qwen
Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 via TrustedRouter
Qwen #121
Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo via TrustedRouter
Qwen #393
Qwen/Qwen3-VL-2B-Instruct via TrustedRouter
Qwen #394
Qwen/Qwen3-VL-32B-Instruct via TrustedRouter
Qwen #395
Qwen/Qwen3-VL-4B-Instruct via TrustedRouter
Qwen #396
Qwen/Qwen3.5-2B via TrustedRouter
Qwen #397
Qwen/Qwen3.5-4B via TrustedRouter
Qwen #398
Qwen/Qwen3.8-Flash-Next via TrustedRouter
Qwen #399
Qwen/Qwen3Guard-Gen-0.6B via TrustedRouter
Qwen #400
Qwen/Qwen3Guard-Gen-8B via TrustedRouter
Qwen #401
Qwen/WebWorld-8B via TrustedRouter
Qwen
Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...
Qwen
Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in code gener…
Qwen #402
Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.
Qwen #48
Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for...
Qwen
Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpo…
Qwen #122
Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively sup…
Qwen #123
Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...
Qwen #124
Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction fo…
Qwen #125
Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for...
Qwen #403
Qwen: Qwen3 8B via TrustedRouter
Qwen #126
Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool us…
Qwen
Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning ov…
Qwen #404
Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling...
Qwen #405
Qwen3 Coder Flash 2025 07 28 via TrustedRouter
Qwen #64
Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...
Qwen #65
Qwen3 Embedding 8B via TrustedRouter
Qwen #33
Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowl…
Qwen
Qwen3 Next 80B A3B Thinking via TrustedRouter
Qwen #406
Qwen3 Omni 30B A3B Thinking via TrustedRouter
Qwen #407
Text-to-speech, billed per request over an attested connection.
Qwen #408
Qwen3 VL 235B via TrustedRouter
Qwen #66
Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, docume…
Qwen #67
Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. I…
Qwen
Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels...
Qwen #127
Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Inte…
Qwen #409
Qwen3 VL Plus via TrustedRouter
Qwen #410
Qwen3 VL Plus 2025 09 23 via TrustedRouter
Qwen #411
Qwen3 VL Plus 2025 12 19 via TrustedRouter
Qwen #128
qwen3-coder-480b-a35b-instruct via TrustedRouter
Qwen #412
Qwen3-Embedding 4B via TrustedRouter
Qwen
the qwen3 embedding model series is the latest proprietary model of the qwen family, specifically designed for text embedding and ranking tasks.
Qwen #22
The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. I…
Qwen #129
Qwen3.5 Flash via TrustedRouter
Qwen #413
Qwen3.5 Flash 2026 02 23 via TrustedRouter
Qwen #414
Qwen3.5 Plus 2026 02 15 via TrustedRouter
Qwen
The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a v…
Qwen #130
Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This...
Qwen #34
The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms…
Qwen #35
The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to…
Qwen #38
The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency…
Qwen #39
Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language…
Qwen
The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared t…
Qwen #24
Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs...
Qwen #13
Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...
Qwen #415
Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in...
Qwen #416
Qwen3.6 Flash 2026 04 16 via TrustedRouter
Qwen #131
Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it…
Qwen #417
Qwen3.6 Plus 2026-04-02 via TrustedRouter
Qwen #418
Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and re…
Qwen #419
Qwen3.7 Flash 2026 07 15 via TrustedRouter
Qwen #49
Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,...
Qwen #420
Qwen3.7 Max 2026 05 20 via TrustedRouter
Qwen #421
Qwen3.7 Max 2026 06 08 via TrustedRouter
Qwen #132
Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...
Qwen #422
Qwen3.7 Plus 2026 05 26 via TrustedRouter
Qwen #40
Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of Qwen3.8 Max, with 95 billion active parameters out of 2.4 trillion total. It is...
Qwen #8
Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...
Qwen #133
Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-vi…
Qwen #50
Qwen3.8 Max via TrustedRouter
Qwen
Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text,...
Qwen
Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video...
Qwen
Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization,...
Qwen #423
Qwen3.8-Flash-Next-FP8 via TrustedRouter
Recraft
Recraft V2 via TrustedRouter
Recraft
Recraft V3 via TrustedRouter
Recraft
Recraft V4 via TrustedRouter
Recraft
Recraft V4 Pro via TrustedRouter
Recraft
Recraft V4.1 via TrustedRouter
Recraft
Recraft V4.1 Pro via TrustedRouter
Recraft
Recraft V4.1 Utility via TrustedRouter
Recraft
Recraft V4.1 Utility Pro via TrustedRouter
Recursive
Flint is an open-weight mixture-of-experts model from Recursive, with about 2.5B active parameters out of 40B total, built by Recursive's autoresearch system Eureka Machine for coding agents. It is suited...
Reflection AI
beam-1.0-501b-a23b is reflection ai's open-weights mixture-of-experts model with 501b total parameters and 23b active parameters, built for coding, reasoning, and agentic workloads. text generation coding reasoning to…
Reflection #424
Beam via TrustedRouter
Reflection
Beam is Reflection’s reasoning model for coding and agentic workflows, combining strong coding capabilities with fast, low-latency inference.
Reflection #425
Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a...
Reflection #426
Reflection Beam 1.0 via TrustedRouter
Reka
Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in…
Reka #427
Reka Edge 2603 via TrustedRouter
Reka
Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring…
Relace
Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at...
Relace
The relace-search model uses 4-12 view_file and grep tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search performs agentic...
Ricursiveai
Ripple-65B-Preview by ricursiveAI, a 65B model with native tool calling, served in BF16.
Runway
Runway Gen-4.5 via TrustedRouter
Sakana AI #428
fugu-ultra-v1.1 via TrustedRouter
Sakana AI
Sakana Namazu is a Japanese-specialized LLM that combines a deep understanding of Japanese culture and business customs with high-performance language capabilities. Built on the open model Kimi K2.6 and refined with S…
Sakana AI
Fugu Max is the cost-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...
Sakana AI
Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to...
Sakana AI
Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and business contexts. It is suited for Japanese instruction following,...
Sao10K
Llama 3 70B Euryale V2.1 via TrustedRouter
Sao10K
Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge....
Sao10K #429
Llama 3 8B Stheno V3.2 via TrustedRouter
Sao10K
Euryale L3.1 70B v2.2 is a model focused on creative roleplay from Sao10k. It is the successor of Euryale L3 70B v2.1.
Sao10K #430
Sao10K/L3-8B-Lunaris-v1-Turbo via TrustedRouter
Sao10K #431
Sao10K/L3.1-70B-Euryale-v2.2 via TrustedRouter
ScaleDown
ScaleDown Classify-1 is a task-specific small language model for text classification. It assigns text to custom labels and returns probability scores, supporting intent detection, content categorization, and routing w…
ScaleDown #432
Extract is a description-driven entity extraction model from ScaleDown. Instead of a fixed set of entity types, callers describe the fields they want in plain English through provider.options.scaledown.entities, and t…
ScaleDown
ScaleDown Extract-1 is a task-specific language model for extracting structured data from unstructured text using a custom JSON schema. It identifies domain-specific entities with confidence scores, character offsets,…
ScaleDown #433
Classify source text against caller-defined labels and rubrics. Input-only billing; no output-token charge.
ScaleDown #434
Compress source text for a specific query. Input-only billing; no output-token charge.
ScaleDown #435
Summarize is an abstractive summarization model from ScaleDown. It condenses long text and documents into a fluent, faithful rewrite rather than lifting sentences from the source, and is suited for...
ScaleDown
ScaleDown Summarize-1 is a task-specific language model for abstractive summarization of long documents, transcripts, and conversations. It rewrites source text into concise summaries and accepts instructions for form…
Shengshu
ShengShu Vidu Q3 via TrustedRouter
SpaceX AI
Grok 4.20 Beta is the newest flagship model from xAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering…
SpaceX AI
Grok 4.20 Beta is the newest flagship model from xAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering…
SpaceX AI
Multiple agents collaborate in parallel to perform deep research tasks.
SpaceX AI
Multiple agents collaborate in parallel to perform deep research tasks.
SpaceX AI
Grok 4.20 Beta is the newest flagship model from xAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherence, delivering…
SpaceX AI
Grok 4.20 Beta is the newest flagship model from xAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherence, delivering…
SpaceX AI
Grok 4.3 is a new model matching the scale of Grok 4.20 with an improved architecture and a December 2025 knowledge cutoff.
SpaceX AI
SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.
SpaceX AI
Grok 4.6 builds on Grok 4.5 with a particular focus on long-running agents and more ambitious interactive and visual work. It stays with complex tasks across many steps, whether researching a topic, analyzing informat…
SpaceX AI
Grok 4.7 is SpaceXAI’s advanced AI model for coding and professional knowledge work, built to tackle complex, multi-hour tasks with improved self-verification and long-context handling. It strengthens software enginee…
SpaceX AI
xAI's fast coding model trained specifically for agentic coding.
Stealth
Glyph Cluster is an anonymous reasoning model in early access. Prompts and outputs will be retained by the provider.
StepFun #436
Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....
StepFun #437
Step 3.5 Flash 2603 via TrustedRouter
StepFun #134
Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11…
StepFun #1
Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional...
Swiss AI #438
apertus-70b via TrustedRouter
Tencent #439
Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark...
Tencent
Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, g…
Tencent
Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextu…
Tencent
Hy-MT2-7B is a 7B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-base…
Tencent #37
Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning ef…
Tencent
Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...
Tencent #24
The official release of Hy4 delivers comprehensive and substantial improvements over Hy4 Preview, with particularly strong gains in agentic capabilities and performance across a wide range of long-horizon, real-world…
Tencent #14
Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...
Tencent
Hy-MT2-Lite is Tencent Cloud Hunyuan’s lightweight 1.8B translation model, combining efficient performance with an 8K-token context window and broad multilingual coverage. It supports translation across 33 languages a…
Tencent
Hy-MT2-Plus is Tencent Cloud Hunyuan’s 7B translation model, offering an 8K-token context window and broad multilingual coverage. Optimized for translation across 33 languages and five ethnic Chinese and dialect varia…
Tencent
Hy-MT2-Pro is Tencent Cloud Hunyuan’s flagship translation model, featuring 30B-A3B parameters and an 8K-token context window. It delivers bidirectional translation across 33 core language pairs, plus five minority-la…
TheDrummer #440
Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.
TheDrummer #441
Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling.
TheDrummer
UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios.
Thinking Machines #442
Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use system…
Thinking Machines #135
Inkling 2 Small is an open-weight multimodal mixture-of-experts reasoning model from Thinking Machines Lab, with 17B active parameters out of 594B total. It is the first model in the second...
Thinking Machines
the 256k-context variant of inkling, thinking machines' open-weights hybrid reasoning moe model. same hybrid reasoning, tool-use, and streaming support as the base model, with an extended context window for longer con…
Thinking Machines #136
Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...
TrustedRouter
TrustedRouter selects a model for your task, then runs it. Responses API only. Standard privacy, not ZDR or confidential. $0.05 per million selector prompt tokens plus the selected model's normal token charges; genera…
TrustedRouter
TrustedRouter Advanced via TrustedRouter
TrustedRouter
TrustedRouter Advisor via TrustedRouter
TrustedRouter
TrustedRouter Archimedes 1.0 via TrustedRouter
TrustedRouter
TrustedRouter Aristotle 1.0 via TrustedRouter
TrustedRouter
TrustedRouter Aristotle 1.1 via TrustedRouter
TrustedRouter
TrustedRouter Aristotle 2.0 via TrustedRouter
TrustedRouter
TrustedRouter Athena 1.0 via TrustedRouter
TrustedRouter
TrustedRouter Athena 2.0 via TrustedRouter
TrustedRouter
TrustedRouter Auto via TrustedRouter
TrustedRouter
TrustedRouter Cheap via TrustedRouter
TrustedRouter
TrustedRouter Confidential via TrustedRouter
TrustedRouter
TrustedRouter Dev 1.0 via TrustedRouter
TrustedRouter
TrustedRouter E2E via TrustedRouter
TrustedRouter
TrustedRouter Efficient via TrustedRouter
TrustedRouter
TrustedRouter EU via TrustedRouter
TrustedRouter
TrustedRouter Fast via TrustedRouter
TrustedRouter
TrustedRouter Free via TrustedRouter
TrustedRouter
TrustedRouter Frontier via TrustedRouter
TrustedRouter
TrustedRouter Gemmev 1.0 via TrustedRouter
TrustedRouter
TrustedRouter Gev 1.0 via TrustedRouter
TrustedRouter
TrustedRouter Green via TrustedRouter
TrustedRouter
TrustedRouter Iris 1.0 via TrustedRouter
TrustedRouter
TrustedRouter Iris 2.0 via TrustedRouter
TrustedRouter
TrustedRouter Iris 3.0 via TrustedRouter
TrustedRouter
TrustedRouter Iris Code via TrustedRouter
TrustedRouter
TrustedRouter Iris Code 1.0 via TrustedRouter
TrustedRouter
TrustedRouter Lev 1.0 via TrustedRouter
TrustedRouter
TrustedRouter Liberty 1.0 via TrustedRouter
TrustedRouter
TrustedRouter Liberty 1.0 1M via TrustedRouter
TrustedRouter
TrustedRouter Liberty 2.0 via TrustedRouter
TrustedRouter
TrustedRouter Liberty 3.0 via TrustedRouter
TrustedRouter
TrustedRouter Liberty 4.0 via TrustedRouter
TrustedRouter
TrustedRouter Liberty 4.1 via TrustedRouter
TrustedRouter
TrustedRouter MapReduce via TrustedRouter
TrustedRouter
TrustedRouter Mev 1.0 via TrustedRouter
TrustedRouter
TrustedRouter Oev 1.0 via TrustedRouter
TrustedRouter
TrustedRouter OpenPatcher-A1 via TrustedRouter
TrustedRouter
TrustedRouter OpenPatcher-Fast1 via TrustedRouter
TrustedRouter
TrustedRouter OpenPatcher-G1 via TrustedRouter
TrustedRouter
TrustedRouter OpenPatcher-G2 via TrustedRouter
TrustedRouter
TrustedRouter OpenPatcher-G3 via TrustedRouter
TrustedRouter
TrustedRouter OpenPatcher-S1 via TrustedRouter
TrustedRouter
TrustedRouter OpenPatcher-S2 via TrustedRouter
TrustedRouter
TrustedRouter OpenPatcher-S3 via TrustedRouter
TrustedRouter
TrustedRouter Plato 1.0 via TrustedRouter
TrustedRouter
TrustedRouter Plato 3.0 via TrustedRouter
TrustedRouter
TrustedRouter Plato 4.0 via TrustedRouter
TrustedRouter
TrustedRouter Plato Pro 1.0 via TrustedRouter
TrustedRouter
TrustedRouter Plato Pro 2.0 via TrustedRouter
TrustedRouter
TrustedRouter Professional via TrustedRouter
TrustedRouter
TrustedRouter Prometheus 1.0 via TrustedRouter
TrustedRouter
TrustedRouter Prometheus 1.0 1M via TrustedRouter
TrustedRouter
TrustedRouter Prometheus 2.0 via TrustedRouter
TrustedRouter
TrustedRouter Prometheus 3.0 via TrustedRouter
TrustedRouter
TrustedRouter Prometheus 4.0 via TrustedRouter
TrustedRouter
TrustedRouter Prometheus Code 1.0 via TrustedRouter
TrustedRouter
TrustedRouter Selector via TrustedRouter
TrustedRouter
TrustedRouter Socrates 1.0 via TrustedRouter
TrustedRouter
TrustedRouter Socrates 1.1 via TrustedRouter
TrustedRouter
TrustedRouter Socrates 2.0 via TrustedRouter
TrustedRouter
TrustedRouter Socrates 3.0 via TrustedRouter
TrustedRouter
TrustedRouter Socrates Pro 1.0 via TrustedRouter
TrustedRouter
TrustedRouter Socrates Pro Plus 1.0 via TrustedRouter
TrustedRouter
TrustedRouter Subagent via TrustedRouter
TrustedRouter
TrustedRouter Synth via TrustedRouter
TrustedRouter
TrustedRouter Synth Code via TrustedRouter
TrustedRouter
TrustedRouter Trev 1.0 via TrustedRouter
TrustedRouter
TrustedRouter Trusted via TrustedRouter
TrustedRouter
TrustedRouter ZDR via TrustedRouter
TrustedRouter
TrustedRouter Zeus 1.0 via TrustedRouter
TrustedRouter
TrustedRouter Zeus 1.0 Mini via TrustedRouter
TrustedRouter
TrustedRouter Zeus 2.0 via TrustedRouter
TrustedRouter
TrustedRouter Zeus 3.0 via TrustedRouter
TrustedRouter
TrustedRouter Zeus Code 1.0 via TrustedRouter
TrustedRouter
TrustedRouter Zev 1.0 via TrustedRouter
TypeSafe
Jev 1.13.0 is TypeSafe AI’s System One evaluation model for fast, structured decisions in software. It evaluates shared state against typed questions and returns choices, scores, and boolean probabilities, supporting…
TypeSafe
Jev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost. It runs on Jev, TypeSafe's first System One model, and adapts as your...
TypeSafe
TypeSafe AI Jev via TrustedRouter
Unbiased
Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.
Unbiased
Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks. This is a preview of the...
Unbiased
Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.
Undi95 #443
A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge
Upstage
Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context window. It is built for agentic use cases where response...
Upstage #444
Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intens…
Voyage #445
Voyage 3 Large via TrustedRouter
Writer
Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-leading speed and efficiency on context windows up to 1 million...
Writer #446
palmyra-vision-7b via TrustedRouter
xAI
xai's grok 4.20 multi-agent model with a 2m-token context window. multiple agents collaborate in parallel to perform deep research tasks, with function calling, structured outputs, and reasoning capabilities. llm agen…
xAI
xai's grok 4.20 non-reasoning model. skips the thinking trace for fast, single-pass responses while keeping the same training as the reasoning variant. llm coding writing
xAI
xai's grok 4.20 reasoning model. uses extended thinking to work through complex problems, returning a reasoning trace alongside the final answer. llm reasoning coding agentic
xAI
Grok 4.6 via TrustedRouter
xAI #447
Text-to-speech, billed per input character, not per token.
xAI #448
grok-4-1-fast-non-reasoning via TrustedRouter
xAI #449
grok-4-1-fast-reasoning via TrustedRouter
xAI #450
grok-4-20-non-reasoning via TrustedRouter
xAI #137
grok-4.20-0309-reasoning via TrustedRouter
xAI #451
Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...
xAI
Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize informati…
xAI #138
Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...
xAI #139
Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.
xAI #46
Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by Grok 4.7.
xAI #36
Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and...
xAI #140
Grok Build 0.1 is SpaceXAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding...
xAI
xAI Grok Imagine Video via TrustedRouter
Xiaomi #68
MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understandin…
Xiaomi #141
MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal,…
Xiaomi #20
MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for...
Xiaomi #38
MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability for the most demanding...
Xiaomi #452
MiMo-V2.6-Pro-UltraSpeed is the fast speed edition of Xiaomi's flagship foundation model, MiMo-V2.6-Pro. Built from the same 1T MiMo-V2.6-Pro checkpoint, it matches the original model in quality while delivering rough…
Xiaomi #453
XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B via TrustedRouter
Xiaomi #454
XiaomiMiMo/MiMo-V2.6-Flash-RL via TrustedRouter
Z.ai #455
AutoGLM Phone 9B Multilingual via TrustedRouter
Z.ai
GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers si…
Z.ai #456
GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact…
Z.ai #457
GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art result…
Z.ai #41
Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...
Z.ai #458
GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts...
Z.ai #29
GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing com…
Z.ai #42
As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task plannin…
Z.ai
GLM-4.7-Flash balances high performance with efficiency, making it the perfect lightweight deployment option.
Z.ai #27
GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale progra…
Z.ai #459
GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows...
Z.ai #18
GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and…
Z.ai #25
GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...
Z.ai #460
GLM 5.2 Fast via TrustedRouter
Z.ai #5
GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...
Z.ai #142
GLM 5.3 Fast on Fireworks via TrustedRouter
Z.ai #3
GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...
Z.ai #69
GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and linear attention architecture...
Z.ai #461
GLM-5.3-FlashX-Legal (GLM-Legal) is Z.ai's legal-domain variant of GLM-5.3-FlashX, a native multimodal model that accepts text, image, and video input and produces text. It adds legal-domain mid-training and post-trai…
Z.ai
GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration. It supports text input and output with a 1M-tok…
Z.ai #70
GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex…
Z.ai
Proxy: zai-org/GLM-4.7 via TrustedRouter
Z.ai #462
zai-org/glm-5.3-p via TrustedRouter
Zero G #463
0GM-1.0-35B-A3B via TrustedRouter
Zero G #464
0GM-1.0-35B-A3B-SIA via TrustedRouter
Zro #465
Abyss 1 via TrustedRouter
Zro #466
Dolly 2 Security via TrustedRouter