gpt-oss-20B
OpenAIOpen weights131k context
gpt-oss-20B is an open-weights model from OpenAI with a 131k-token context window. 6 providers list it, from $0.03 per million input tokens and $0.14 per million output tokens (DeepInfra).
- Maker
- OpenAI
- Licence
- Open weights
- Context window
- 131k
- Providers listed
- 6
- Lowest input, per 1M
- $0.03
- Lowest output, per 1M
- $0.14
- Effort settings
- Low, Medium, High
Providers serving gpt-oss-20B
Cheapest first, by the blended rate of three input tokens to one output token. Prices in US dollars per million tokens, as of 26 Oct 2026.
| Provider | Input | Output | Context | Tools | JSON mode | OpenAI-compatible | Model ID |
|---|---|---|---|---|---|---|---|
DeepInfra | $0.03 | $0.14 | 131k | Yes | Yes | No | openai/gpt-oss-20b |
Google Vertex | $0.07 | $0.25 | 131k | Yes | Yes | No | openai/gpt-oss-20b-maas |
Amazon Bedrock | $0.07 | $0.30 | 131k | Yes | Yes | No | openai.gpt-oss-20b-1:0 |
Databricks Billed in DBUs; converted at Databricks' $0.07 per DBU (AWS). | $0.07 | $0.30 | 131k | Yes | Yes | Yes | databricks-gpt-oss-20b |
Groq | $0.075 | $0.30 | 131k | Yes | Yes | No | openai/gpt-oss-20b |
Cloudflare | $0.20 | $0.30 | 128k | Yes | Yes | Yes | @cf/openai/gpt-oss-20b |
Benchmark scores
Published scores only, each linked to its source. Compare every model in Bench rankings