# GPT OSS 20B API pricing

No price from the maker itself is on record for GPT OSS 20B. The lowest of 41 providers is Eden AI: $0.009 per 1M input tokens and $0.045 per 1M output tokens (as of 2026-11-12). Context window: 131K tokens, up to 32.8K output tokens per request.

- Type: Text
- Context: 131K
- Max output: 32.8K
- Released: 2025-08-05
- Open weights: Yes

## Price by provider (USD per 1M tokens)

| Provider | Model id | Input | Output | Cached | Notes |
| --- | --- | --- | --- | --- | --- |
| [Eden AI](https://docs.edenai.co) | greenference/gpt-oss-20b | $0.009 | $0.045 | $0.0045 | Lowest |
| [Kilo Gateway](https://kilo.ai) | openai/gpt-oss-20b | $0.018 | $0.09 | $0.009 |  |
| [NanoGPT](https://docs.nano-gpt.com) | openai/gpt-oss-20b | $0.018 | $0.09 | $0.009 |  |
| [Eden AI](https://docs.edenai.co) | flexai/gpt-oss-20b | $0.02 | $0.1 | $0.003 |  |
| [OpenRouter](https://openrouter.ai/models) | openai/gpt-oss-20b | $0.03 | $0.13 | $0.03 |  |
| [CoreWeave](https://docs.wandb.ai/inference) | openai/gpt-oss-20b | $0.03 | $0.13 | $0.03 |  |
| [Deep Infra](https://deepinfra.com/models) | openai/gpt-oss-20b | $0.03 | $0.14 | — |  |
| [Eden AI](https://docs.edenai.co) | deepinfra/openai/gpt-oss-20b | $0.03 | $0.14 | — |  |
| [Vercel AI Gateway](https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway) | openai/gpt-oss-20b | $0.03 | $0.14 | — |  |
| [Merge Gateway](https://docs.merge.dev/merge-gateway) | openai/gpt-oss-20b | $0.04 | $0.15 | $0.02 |  |
| [Kenari](https://kenari.id/docs) | gpt-oss-20b | $0.036 | $0.154286 | $0.003714 |  |
| [Cortecs](https://api.cortecs.ai/v1/models) | gpt-oss-20b | $0.045 | $0.167 | — |  |
| [SiliconFlow](https://cloud.siliconflow.com/models) | openai/gpt-oss-20b | $0.04 | $0.18 | — |  |
| [Clarifai](https://docs.clarifai.com/compute/inference/) | openai/chat-completion/models/gpt-oss-20b | $0.045 | $0.18 | — |  |
| [Eden AI](https://docs.edenai.co) | ovhcloud/gpt-oss-20b | $0.05 | $0.18 | — |  |
| [OVHcloud AI Endpoints](https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog//) | gpt-oss-20b | $0.05 | $0.18 | — |  |
| [DevPass (LLM Gateway)](https://llmgateway.io/docs) | gpt-oss-20b | $0.04 | $0.19 | $0.01 |  |
| [LLM Gateway](https://llmgateway.io/docs) | consensusprotocol/gpt-oss-20b | $0.04 | $0.19 | $0.01 |  |
| [IO.NET](https://io.net/docs/guides/intelligence/io-intelligence) | openai/gpt-oss-20b | $0.055 | $0.194 | $0.0275 |  |
| [Helicone](https://helicone.ai/models) | gpt-oss-20b | $0.05 | $0.2 | — |  |
| [FrogBot](https://docs.frogbot.ai) | gpt-oss-20b | $0.07 | $0.2 | — |  |
| [FastRouter](https://fastrouter.ai/models) | openai/gpt-oss-20b | $0.07 | $0.25 | $0.007 |  |
| [Amazon Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html) | openai.gpt-oss-20b | $0.07 | $0.3 | — |  |
| [Amazon Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html) | openai.gpt-oss-20b-1:0 | $0.07 | $0.3 | — |  |
| [Databricks](https://docs.databricks.com/aws/en/machine-learning/foundation-models/) | databricks-gpt-oss-20b | $0.07 | $0.3 | — |  |
| [Neon](https://neon.com/docs) | gpt-oss-20b | $0.07 | $0.3 | — |  |
| [OCI Generative AI](https://docs.oracle.com/en-us/iaas/Content/generative-ai/pretrained-models.htm) | openai.gpt-oss-20b | $0.07 | $0.3 | — |  |
| [Ollama Cloud](https://docs.ollama.com/cloud) | gpt-oss:20b | $0.07 | $0.3 | $0.035 |  |
| [Prime Inference](https://docs.primeintellect.ai/inference/overview) | openai/gpt-oss-20b | $0.07 | $0.3 | — |  |
| [Eden AI](https://docs.edenai.co) | databricks/databricks-gpt-oss-20b | $0.07 | $0.30002 | $0.007 |  |
| [Eden AI](https://docs.edenai.co) | databricks/databricks-gpt-oss-20b@eu | $0.07 | $0.30002 | $0.007 |  |
| [Eden AI](https://docs.edenai.co) | groq/openai/gpt-oss-20b | $0.075 | $0.3 | $0.0375 |  |
| [Groq](https://console.groq.com/docs/models) | openai/gpt-oss-20b | $0.075 | $0.3 | $0.0375 |  |
| [Tempr Gateway](https://temprhq.io/docs/gateway-reference.html) | groq/openai/gpt-oss-20b | $0.075 | $0.3 | $0.0375 |  |
| [AI/ML API](https://docs.aimlapi.com) | openai/gpt-oss-20b | $0.07935 | $0.3174 | $0.039675 |  |
| [Amazon Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html) | us-gov.openai.gpt-oss-20b-1:0 | $0.084 | $0.36 | — |  |
| [STACKIT](https://docs.stackit.cloud/products/data-and-ai/ai-model-serving/basics/available-shared-models) | openai/gpt-oss-20b | $0.18 | $0.29 | — |  |
| [Cloudflare Workers AI](https://developers.cloudflare.com/workers-ai/models/) | @cf/openai/gpt-oss-20b | $0.2 | $0.3 | — |  |
| [DigitalOcean](https://docs.digitalocean.com/products/gradient-ai-platform/details/models/) | openai-gpt-oss-20b | $0.05 | $0.45 | $0.01 |  |
| [Eden AI](https://docs.edenai.co) | cloudflare/@cf/openai/gpt-oss-20b | $0.2 | $0.3 | — |  |
| [Regolo AI](https://docs.regolo.ai/) | gpt-oss-20b | $0.11215 | $0.47103 | — |  |
| [LowRouter](https://lowrouter.ai/docs/models/available) | auto/openai/gpt-oss-20b | $0.113 | $0.4745 | — |  |
| [Hugging Face](https://huggingface.co/docs/inference-providers) | openai/gpt-oss-20b | $0.1 | $0.5 | — |  |
| [LLM Gateway](https://llmgateway.io/docs) | groq/gpt-oss-20b | $0.1 | $0.5 | — |  |
| [Opper](https://opper.ai/models) | gpt-oss-20b | $0.11622 | $0.488124 | — |  |
| [Thinking Machines](https://tinker-docs.thinkingmachines.ai/tinker/compatible-apis/anthropic/) | openai/gpt-oss-20b | $0.18 | $0.45 | $0.036 |  |
| [Impossibl](https://impossibl.com/docs/models) | fireworks/gpt-oss-20b | $0.07 | $0.3 | $0.035 | Deprecated |
| [Impossibl](https://impossibl.com/docs/models) | groq/gpt-oss-20b | $0.075 | $0.3 | $0.0375 | Deprecated |
| [LMStudio](https://lmstudio.ai/models) | openai/gpt-oss-20b | $0 | $0 | — |  |
| [Nvidia](https://docs.api.nvidia.com/nim/) | openai/gpt-oss-20b | $0 | $0 | — |  |
| [QVAC](https://www.npmjs.com/package/@qvac/ai-sdk-provider) | gpt-oss-20b | $0 | $0 | — |  |
| [Qiniu](https://developer.qiniu.com/aitokenapi) | gpt-oss-20b | — | — | — | Deprecated |

Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.

Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.

https://apibook.ai/models/openai/gpt-oss-20b/