openai
OpenAI: gpt-oss-120b (batch)
openai/gpt-oss-120b:batch
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
openai/gpt-oss-120b:batch is OpenRouter's batch listing of OpenAI's open-weight gpt-oss-120b, a 117B-parameter Mixture-of-Experts model with 5.1B active parameters per forward pass. The catalog describes a text-to-text model with a large context window, mandatory reasoning adjustable across low, medium, and high effort, and support for tools, structured outputs, and function calling. OpenAI's model card describes the canonical model as Apache-2.0 licensed, fine-tunable, requiring the harmony response format, and sized to run on a single 80GB GPU. Evidence specific to the batch endpoint is thin; validate on your workload.[1][2]
Strengths
- OpenAI reports open weights under a permissive Apache-2.0 license, with full fine-tuning support for customization.[2]
- Reasoning effort is configurable (low, medium, high) and the card exposes the full chain-of-thought for debugging; OpenRouter confirms adjustable effort with a medium default.[1][2]
- The catalog lists a 131,072-token context window plus tool calling, structured outputs, and seed and penalty controls suited to production integrations.[1]
Limitations
- Evidence for the :batch endpoint is catalog-only; the model card documents the canonical gpt-oss-120b, so batch latency, throughput, and behavior need validation on your workload.[1]
- OpenAI states the model only works correctly with the harmony response format, an integration constraint for existing stacks.[2]
- OpenRouter marks reasoning as mandatory, which may add latency to simple prompts; inputs and outputs are text-only and the knowledge cutoff is June 2024.[1]
Where to use it
- Agentic assistants and pipelines that need function calling, web browsing, or structured outputs, per OpenAI's stated capabilities.[2]
- Self-hosted or fine-tuned production reasoning workloads for teams able to supply a single 80GB-class GPU.[2]
- High-volume, non-interactive text jobs where a batch endpoint and adjustable reasoning effort can trade latency for throughput.[1]
Sources
- [1] OpenRouter catalog · OpenAI: gpt-oss-120b (batch)Sources checked: Nov 13, 2026
- [2] Model documentation · OpenAI: gpt-oss-120b (batch)Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...
Specifications
- Model ID
- openai/gpt-oss-120b:batch
- Canonical ID
- openai/gpt-oss-120b
- Creator
- openai
- Added to OpenRouter
- 05.08.2025
- Context length
- 131,072
- Modality
- text->text
- Input modalities
- text
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.030 / out $0.136
- Knowledge cutoff
- 30.06.2024
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | CC — below the B band | reasoning: mandatory · default medium · efforts: high, medium, low · parameters: include_reasoning, reasoning, reasoning_effort |
| Coding | CC — below the B band | — |
| Agents | CC — below the B band | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: mandatory · default medium · efforts: high, medium, low · parameters: include_reasoning, reasoning, reasoning_effort |
| Document analysis | No measurement | — |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Artificial Analysis | Intelligence index | 3.8 | CC — below the B band | 13.11.2026 |
| Artificial Analysis | Coding index | 30.4 | CC — below the B band | 13.11.2026 |
| Artificial Analysis | Agentic index | 3.7 | CC — below the B band | 13.11.2026 |
| Design Arena | models · 3dwin rate 29.4% · rank 129 | 884Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · codecategorieswin rate 33.4% · rank 138 | 953Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · datavizwin rate 43.6% · rank 122 | 985Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · gamedevwin rate 40.5% · rank 127 | 982Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · uicomponentwin rate 35.7% · rank 132 | 919Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · websitewin rate 32.5% · rank 140 | 961Elo | CC — below the B band | 13.11.2026 |
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| DeepInfrabf16 | 131,072 | $0.030 | $0.136 | — | — | — |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.