The Orchestrator › Models › OpenAI
OpenAI: gpt-oss-120b
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 forward pass and is optimized...
Specifications
| Provider | OpenAI |
| Model ID | openai/gpt-oss-120b |
| Context window | 131K tokens (131,072) |
| Modalities | text → text |
| Tokenizer | GPT |
| Router sources | OpenRouter, TrustedRouter, Vercel AI Gateway, Cloudflare |
| Released | 2025-08-05 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | Mandatory |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | openai/gpt-oss-120b | $0.15 | $0.6 | 131K |
| batch | OpenRouter | openai/gpt-oss-120b:batch | $0.03 | $0.136 | 131K |
| standard | TrustedRouter | openai/gpt-oss-120b | $0.032 | $0.179 | 131K |
| standard | Vercel AI Gateway | openai/gpt-oss-120b | $0.1 | $0.5 | 131K |
| standard | Cloudflare | openai/gpt-oss-120b | $0.35 | $0.75 | — |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.35 | $0.75 | — |
| 2026-11-14 | $0.1 | $0.5 | 131K |
| 2026-11-14 | $0.032 | $0.179 | 131K |
| 2026-11-14 | $0.15 | $0.6 | 131K |
Capabilities
Agentic tool useStructured outputsReasoning (always on)Controllable reasoningNo content storage (attested)Zero data retentionNo training on inputs (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
frequency_penalty, include_reasoning, logit_bias, logprobs, 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