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.
function_calling| Date | Input | Output | Cache read | Change |
|---|---|---|---|---|
| Mar 21, 2026 | $0.039 | $0.19 | — | — |
| May 2, 2026bc0fb7d | $0.039 | $0.18 | — | ↑0.0% |
| May 18, 202673d11c6 | $0.039 | $0.19 | — | ↑0.0% |
| May 23, 20269e091d8 | $0.039 | $0.18 | — | ↑0.0% |
| Jun 30, 202688d97e5 | $0.03 | $0.15 | — | ↓23% |
| Jul 10, 2026105275d | $0.036 | $0.18 | — | ↑20% |
| Jul 17, 202620c73ac | $0.037 | $0.17 | — | ↑3% |
| Aug 13, 20263cddff5 | $0.03 | $0.17 | $0.03 | ↓19% |
| Aug 31, 2026e3d7ded | $0.037 | $0.17 | $0.03 | ↑23% |
| Sep 18, 20262ae168f | $0.15 | $0.6 | $0.075 | ↑305% |
| Sep 30, 20266e8bf55 | $0.037 | $0.17 | $0.075 | ↓75% |
Input is ↓5% since Mar 21, 2026, from $0.039 to $0.037 per 1M tokens.
| Provider | Input | Output | Since launch |
|---|---|---|---|
| DeepInfracheapest | $0.04 | $0.17 | ↓5% |
| OpenRoutercheapest | $0.04 | $0.17 | ↓5% |
| Cloudflare AI Gateway | $0.04 | $0.19 | — |
| Novita AI | $0.05 | $0.25 | — |
| Groq | $0.15 | $0.6 | — |
| SambaNova Cloud | $0.22 | $0.59 | — |
| Cerebras | $0.35 | $0.75 | — |
| Vercel AI Gateway | $0.35 | $0.75 | — |
| Model | Context | Max out | Pricing |
|---|---|---|---|
| OpenAI: gpt-oss-120b (free) | 131K | 131K | |
| OpenAI: gpt-oss-20b (free) | 131K | 33K | |
| OpenAI: gpt-oss-20b | 131K | 33K | $0.02$0.09 |
| OpenAI: gpt-oss-20b (batch) | 131K | 118K | $0.02$0.11 |
| OpenAI: gpt-oss-120b (batch) | 131K | 118K | $0.03$0.14 |
| OpenAI: gpt-oss-120b | 131K | 118K | $0.04$0.17 |
| OpenAI: gpt-oss-safeguard-20b | 131K | 66K | $0.08$0.3 |
/v1/models/openrouter/openai/gpt-oss-120b