gpt-oss-120b
| Provider | Price | Provider model ID | Status | Context / max output | Source |
|---|---|---|---|---|---|
 OpenRouter | Router catalog Tariff not listedInput $0.037USD / 1M tokensOutput $0.17USD / 1M tokens OpenRouter · Router catalogInput: $0.037 Output: $0.17 OpenRouter route catalog price, not a direct-provider price. Routing, modality and endpoint conditions can change the actual bill. Checked 2026-10-03T12:45:17.276Z Price source ↗ | openai/gpt-oss-120b | Catalog-listedConditionsCatalog-listed; account access and regional availability may apply. | Context tokens 131072Output tokens 65536 | Official source ↗2026-09-28 |
 Groq | Standard Tariff not listedInput $0.15USD / 1M tokensOutput $0.6USD / 1M tokens Groq · StandardInput: $0.15 Output: $0.6 Checked 2026-10-03T12:45:17.276Z Price source ↗ | openai/gpt-oss-120b | Catalog-listedConditionsCatalog-listed; account access and regional availability may apply. | Context tokens 131072Output tokens 65536 | Official source ↗2026-09-28 |
 Together AI | Standard Tariff not listedInput $0.15USD / 1M tokensOutput $0.6USD / 1M tokens Together AI · StandardInput: $0.15 Output: $0.6 Serverless token list rate; verify exact deployment and quantization. Checked 2026-10-03T12:45:17.276Z Price source ↗ | openai/gpt-oss-120b | Catalog-listedConditionsCatalog-listed; account access and regional availability may apply. | Context tokens 131072 | Official source ↗2026-09-28 |
 Fireworks AI | Not collectedAwaiting verified pricing | Not yet captured | Catalog-listedConditionsServerless catalog listing verified; provider-specific API ID not yet captured. | Not supplied | Official source ↗2026-09-28 |
gpt-oss-120b accepts text and produces text. Tool calling and structured outputs are available on supported routes.
Specifications
- Catalog model ID
- openai/gpt-oss-120b
- Developer model ID / revision
- gpt-oss-120bDeveloper documentation ↗
- Input modalities
- textDeveloper documentation ↗
- Output modalities
- textDeveloper documentation ↗
- Context / input token limit
- 131,072Developer documentation ↗
- Maximum output tokens
- 131,072Developer documentation ↗
- Tool calling
- SupportedDeveloper documentation ↗
- Structured output
- SupportedDeveloper documentation ↗
- API parameters (source-specific)
- frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_a, top_k, top_logprobs, top_pOpenRouter catalog ↗
- API parameter scope
- OpenRouter API; support varies by route
- Weight access
- Open weightsDeveloper documentation ↗
- Weight license / access terms
- Apache 2.0Developer documentation ↗
- Total parameters (billions)
- 117Developer documentation ↗
- Active parameters (billions)
- 5.1Developer documentation ↗
- Download size (GB)
- Depends on checkpoint and precision; no verified file size
- Release date
- Not verified in cited sources
- Added to OpenRouter
- 2025-08-05OpenRouter catalog ↗
- Notes
- API parameter names are reported by OpenRouter and do not describe the developer’s native API. Token limits labeled OpenRouter are route catalog limits, not universal model limits. Media limits on this page describe the linked provider endpoint; other deployments may differ. Output tokens share the model context budget with input tokens. Hosted providers may impose lower output caps.
Catalog entries link to their specification and availability sources. This is a curated selection, not every model each provider offers. Best prices are the lowest collected USD tariffs, not a total-cost estimate. Token offers are selected by input price, with output from the same tariff; workload mix may change the cheapest provider. Listed variants may require batch processing, off-peak hours, or specific media settings. Price coverage varies by provider; collected tariffs include their source and observation time. Benchmark scores are a dated snapshot, not a live feed or a universal measure of quality. They apply to the shown evaluation configuration; listed prices may use different settings. Models without verified scores are not assumed to be weaker.