tokenstat
tokenstat
OpenAI

OpenAI: gpt-oss-20b

openai/gpt-oss-20b · rates as of · How this catalog is built · Benchmarks

Open GPT reasoning model for self-hosted agents and controllable deployments

Cheapest input
$0.009
$/MTok · models.dev
Cheapest output
$0.045
$/MTok
Context
131K
tokens
Sources
3
67 listings

Price changes

Cheapest list input/output only. Rates move rarely, so this is an event log. Down means cheaper. Showing the 8 latest changes.

Input $/MTok over sampled dates
Output $/MTok
  • ↑ higherOutput $0.018 → $0.045
  • ↑ higherInput $0.004 → $0.009
  • ↓ lowerOutput $0.045 → $0.018
  • ↓ lowerInput $0.009 → $0.004
  • ↓ lowerOutput $0.07 → $0.045
  • ↓ lowerInput $0.0145 → $0.009

Sources

Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number. Free/$0 listings are hidden by default (3 omitted). Show free/$0 listings.

SourceProviderInputOutputCache readContext
models.devcheapestgreenference/gpt-oss-20bEden AI$0.009$0.045$0.0045131K
models.devopenai/gpt-oss-20bNanoGPT$0.01$0.04$0.009131K
models.devopenai/gpt-oss-20bKilo Gateway$0.011$0.047$0.01131K
LiteLLMdarkbloom/gpt-oss-20bN/A$0.0145$0.07$0.0014N/A
models.devflexai/gpt-oss-20bEden AI$0.02$0.1$0.003131K
OpenRouteropenai/gpt-oss-20b:batchOpenRouter$0.024$0.112$0131K
OpenRouteropenai/gpt-oss-20bOpenRouter$0.03$0.13$0.03131K
models.devopenai/gpt-oss-20bCoreWeave$0.03$0.13$0.03131K
models.devopenai/gpt-oss-20bDeepInfra$0.03$0.14$0.003131K
models.devdeepinfra/openai/gpt-oss-20bEden AI$0.03$0.14$0131K
models.devopenai/gpt-oss-20bVercel AI Gateway$0.03$0.14$0131K
LiteLLMopenai/gpt-oss-20bN/A$0.03$0.14$0.003N/A
models.devgpt-oss-20bKenari$0.036$0.1543$0.0037131K
models.devopenai/gpt-oss-20bMerge Gateway$0.04$0.15$0.02128K
models.devopenai/gpt-oss-20bSiliconFlow$0.04$0.18$0131K
models.devgpt-oss-20bDevPass (LLM Gateway)$0.04$0.19$0.01131K
models.devconsensusprotocol/gpt-oss-20bLLM Gateway$0.04$0.19$0.01128K
LiteLLMovhcloud/gpt-oss-20bN/A$0.04$0.15$0.004N/A
LiteLLMnovita/openai/gpt-oss-20bN/A$0.04$0.15$0.004N/A
LiteLLMinferenceapis/openai/gpt-oss-20bN/A$0.04$0.19$0.004N/A
models.devgpt-oss-20bCortecs$0.045$0.167$0131K
models.devopenai/chat-completion/models/gpt-oss-20bClarifai$0.045$0.18$0131K
models.devovhcloud/gpt-oss-20bEden AI$0.05$0.18$0131K
models.devgpt-oss-20bOVHcloud AI Endpoints$0.05$0.18$0131K
models.devgpt-oss-20bHelicone$0.05$0.2$0131K
models.devopenai-gpt-oss-20bDigitalOcean$0.05$0.45$0.01128K
LiteLLMtogether_ai/openai/gpt-oss-20bN/A$0.05$0.2$0.005N/A
models.devopenai/gpt-oss-20bIO.NET$0.055$0.194$0.027564K
models.devgpt-oss-20bFrogBot$0.07$0.2$0131K
models.devopenai/gpt-oss-20bFastRouter$0.07$0.25$0.007131K
models.devarkanecloud/openai/gpt-oss-20bEden AI$0.07$0.25$0.05131K
models.devopenai/gpt-oss-20bPrime Inference$0.07$0.3$0131K
models.devopenai.gpt-oss-20bAmazon Bedrock$0.07$0.3$0131K
models.devopenai.gpt-oss-20bOCI Generative AI$0.07$0.3$0.007128K
models.devgpt-oss-20bNeon$0.07$0.3$0131K
models.devgpt-oss:20bOllama Cloud$0.07$0.3$0.035131K
models.devdatabricks-gpt-oss-20bDatabricks$0.07$0.3$0131K
models.devfireworks/gpt-oss-20bImpossibl$0.07$0.3$0.035131K
models.devdatabricks/databricks-gpt-oss-20bEden AI$0.07$0.3$0.007131K
LiteLLMtensormesh/openai/gpt-oss-20bN/A$0.07$0.28$0N/A
LiteLLMopenai.gpt-oss-20bN/A$0.07$0.3$0.007N/A
LiteLLMaccounts/fireworks/models/gpt-oss-20bN/A$0.07$0.3$0.035N/A
LiteLLMbedrock_mantle/openai.gpt-oss-20bN/A$0.07$0.3$0.007N/A
LiteLLMfireworks_ai/accounts/fireworks/models/gpt-oss-20bN/A$0.07$0.3$0.035N/A
LiteLLMdatabricks-gpt-oss-20bN/A$0.07$0.3$0.07N/A
LiteLLMdatabricks/databricks-gpt-oss-20bN/A$0.07$0.3$0.07N/A
models.devopenai/gpt-oss-20bGroq$0.075$0.3$0.0375131K
models.devgroq/gpt-oss-20bImpossibl$0.075$0.3$0.0375131K
models.devgroq/openai/gpt-oss-20bEden AI$0.075$0.3$0.0375131K
models.devgroq/openai/gpt-oss-20bTempr Gateway$0.075$0.3$0.0375131K
models.devopenai/gpt-oss-20bAI/ML API$0.0794$0.3174$0.0397131K
LiteLLMbedrock_mantle/us-gov-east-1/openai.gpt-oss-20bN/A$0.084$0.36$0.0084N/A
LiteLLMus-gov-east-1/openai.gpt-oss-20bN/A$0.084$0.36$0.0084N/A
LiteLLMus-gov-west-1/openai.gpt-oss-20bN/A$0.084$0.36$0.0084N/A
LiteLLMreplicate/openai/gpt-oss-20bN/A$0.09$0.36$0.009N/A
models.devopenai/gpt-oss-20bHugging Face$0.1$0.5$0131K
models.devgroq/gpt-oss-20bLLM Gateway$0.1$0.5$0131K
models.devgpt-oss-20bRegolo AI$0.1121$0.471$0128K
models.devauto/openai/gpt-oss-20bLowRouter$0.113$0.4745$0131K
models.devgpt-oss-20bOpper$0.1162$0.4881$0128K
models.devopenai/gpt-oss-20bSTACKIT$0.18$0.29$0131K
models.devopenai/gpt-oss-20bThinking Machines$0.18$0.45$0.03633K
models.dev@cf/openai/gpt-oss-20bCloudflare$0.2$0.3$0128K
models.devcloudflare/@cf/openai/gpt-oss-20bEden AI$0.2$0.3$0128K
LiteLLM@cf/openai/gpt-oss-20bN/A$0.2$0.3$0.02N/A
LiteLLMgpt-oss-20bN/A$0.2$0.3$0.02N/A
LiteLLMcloudflare/@cf/openai/gpt-oss-20bN/A$0.2$0.3$0.02N/A

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Open weights
  • In: text
  • Out: text
Knowledge cutoff: 2024-06Released: 2025-08-05Output limit: 118K tokensFamily: gpt-oss

Scores

Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.

Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.

See what this model costs you

The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.

macOSDownloadWindowsPreviewCLImacOS · Linux · WindowsApp StoreDownloadGoogle PlayDownload