OpenAI · Model identity
GPT OSS 20B
Official Groq serverless token pricing for GPT OSS 20B.
3pricing routes
What published route metadata supports
CachingHugging FaceReasoningStructured outputTool use
Input modalities
Text
Supported API parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Only source-backed fields are filled
Release dateNot independently verified
Knowledge cutoffNot independently verified
Open weightsNot independently verified
OpenRouter catalog date2025-08-05
LLMPrice does not infer a release date, knowledge cutoff, or open-weight status from a model name, Hugging Face link, or pricing route.
Route savings
Cheapest on bothCheapest standard route
OpenRouterLowest published standard input and output rates for this model.
Input$0.03 / 1MOpenRouter60.0% below the next-cheapest rate
Output$0.13 / 1MOpenRouter56.7% below the next-cheapest rate
Based on current published standard rates. Batch, long-context, and other special billing variants are excluded from this summary.
Could this workload cost less?Compare GPT OSS 20B with cheaper models using the same workload.
Find cheaper alternatives →| Endpoint / route | Model ID | Input | Cached | Output | Context | Source |
|---|---|---|---|---|---|---|
| OpenRouterStandard | openai/gpt-oss-20b | $0.03 | $0.03 | $0.13 | 131K | OpenRouter API ↗ |
| OpenRouterBatch | openai/gpt-oss-20b:batch | $0.05 | — | $0.2 | 131K | OpenRouter API ↗ |
| GroqStandard | openai/gpt-oss-20b | $0.075 | — | $0.3 | 131K | Official Groq ↗ |
Hugging Face references
Presence of a Hugging Face ID is not treated as proof that model weights are open.
0 verified price changes since Aug 26, 2026
2 route availability changes recorded. No earlier prices are inferred.
- Sep 3, 2026Together AI · Standard
Pricing route removed
- Aug 28, 2026OpenRouter · Batch
New pricing route added