The Orchestrator › Models › DeepSeek
DeepSeek: DeepSeek V4 Flash 0423
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...
Specifications
| Provider | DeepSeek |
| Model ID | deepseek/deepseek-v4-flash |
| Context window | 1.0M tokens (1,048,576) |
| Modalities | text → text |
| Tokenizer | DeepSeek |
| Router sources | OpenRouter, TrustedRouter, Vercel AI Gateway |
| Released | 2026-04-24 |
| Tracked since | 2026-11-14 |
| Popularity | #6 by usage · peak 15.1% spend share in an OpenRouter category |
| Reasoning | Supported |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | deepseek/deepseek-v4-flash | $0.09 | $0.18 | 1.0M |
| standard | TrustedRouter | deepseek/deepseek-v4-flash | $0.095 | $0.19 | 1.0M |
| standard | Vercel AI Gateway | deepseek/deepseek-v4-flash | $0.13 | $0.26 | 1M |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.13 | $0.26 | 1M |
| 2026-11-14 | $0.095 | $0.19 | 1.0M |
| 2026-11-14 | $0.09 | $0.18 | 1.0M |
Capabilities
Agentic tool useStructured outputs1M+ context windowControllable reasoningNo content storage (attested)Zero data retention
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
frequency_penalty, include_reasoning, logit_bias, logprobs, max_completion_tokens, max_tokens, min_p, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_a, top_k, top_logprobs, top_p