`gpt-oss-20b` is our medium-sized open-weight model for low latency, local, or specialized use-cases (21B parameters with 3.6B active parameters).
| Model | Context | Max out | Pricing |
|---|---|---|---|
| OpenAI: gpt-oss-20b:free | — | — | — |
| OpenRouter: openai/gpt-oss-120b:free | — | — | — |
| OpenRouter: openai/gpt-oss-20b:free | — | — | — |
| OpenAI: gpt-oss-20b | 131K | 131K | $0.03$0.14 |
| OpenRouter: openai/gpt-oss-20b | — | — | $0.03$0.14 |
| OpenAI: gpt-oss-120b | 131K | 131K | $0.04$0.19 |
| OpenRouter: openai/gpt-oss-120b | — | — | $0.04$0.19 |
| OpenAI: gpt-oss-120b:exacto | — | — | $0.05$0.24 |
| OpenRouter: openai/gpt-oss-120b:exacto | — | — | $0.05$0.24 |
| Google Vertex AI: openai/gpt-oss-20b-maas | — | — | $0.07$0.25 |
| Groq: openai/gpt-oss-20b | — | — | $0.08$0.3 |
| OpenAI: gpt-oss-safeguard-20b | — | — | $0.08$0.3 |
| OpenRouter: openai/gpt-oss-safeguard-20b | — | — | $0.08$0.3 |
| Google Vertex AI: openai/gpt-oss-120b-maas | — | — | $0.09$0.36 |
| Baseten: openai/gpt-oss-120b | — | — | $0.1$0.5 |
| Groq: openai/gpt-oss-120b | — | — | $0.15$0.6 |
| Cerebras: gpt-oss-120b | — | — | $0.25$0.69 |
| cerebras: gpt-oss-120b | — | — | $0.25$0.69 |
/v1/models/cloudflare-ai-gateway/openai/gpt-oss-20b`gpt-oss-20b` is our medium-sized open-weight model for low latency, local, or specialized use-cases (21B parameters with 3.6B active parameters).