The Orchestrator › Models › OpenAI
OpenAI: gpt-oss-20b
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...
Specifications
| Provider | OpenAI |
| Model ID | openai/gpt-oss-20b |
| 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-20b | $0.03 | $0.13 | 131K |
| batch | OpenRouter | openai/gpt-oss-20b:batch | $0.024 | $0.112 | 131K |
| standard | TrustedRouter | openai/gpt-oss-20b | $0.01 | $0.047 | 131K |
| standard | Vercel AI Gateway | openai/gpt-oss-20b | $0.03 | $0.14 | 131K |
| standard | Cloudflare | openai/gpt-oss-20b | $0.2 | $0.3 | — |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.2 | $0.3 | — |
| 2026-11-14 | $0.03 | $0.14 | 131K |
| 2026-11-14 | $0.01 | $0.047 | 131K |
| 2026-11-14 | $0.03 | $0.13 | 131K |
| 2026-11-14 | $0.018 | $0.09 | 131K |
| 2026-11-14 | $0.03 | $0.13 | 131K |
| 2026-11-14 | $0.018 | $0.09 | 131K |
| 2026-11-14 | $0.03 | $0.13 | 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_k, top_logprobs, top_p