- Context
- 131K
- Max output
- 131K
- Reasoning
- Yes
- Included in
- 1 plan
API priceUSD / 1M tokens
Open-weight model. OpenAI does not publish a hosted per-token rate for this model; third-party routes set their own prices.
API token estimate
Token estimate unavailable
No current Standard API list price is recorded for this exact model. Prices for another model or processing tier cannot supply an estimate.
Capabilities & limitsProvider specifications
- Context window
- 131,072
- Maximum output
- 131,072
- Input
- text
- Output
- text
- Reasoning
- Supported
- Tool calling
- Supported
- Structured output
- Supported
Benchmarks
Open benchmark sheet →No benchmark evidence recorded for this exact release.
Where you can use itPublished access · 1 subscriptions
Pricing, assumptions & evidence
- Official developer identity documentation checked Sep 30, 2026
- Official developer identity documentation checked Sep 30, 2026
- OpenAI release announcement for both GPT-OSS models checked Sep 30, 2026
Missing token-category prices are not zero. Workload pricing applies exact recorded categories and admitted routes. No benchmark score or quality ranking is inferred from prices.
Aliases, routes and identity
Catalog ID gpt-oss-20b
Model release (kind: release)
Developer: OpenAI