openai
OpenAI: gpt-oss-20b (batch)
openai/gpt-oss-20b: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-20b:batch is an OpenRouter-listed text-to-text variant of OpenAI's gpt-oss-20b. The catalog reports a long context window, tool and structured-output controls, and mandatory reasoning with low, medium, or high effort. OpenAI's documentation for the underlying model describes Apache-2.0 open weights, a mixture-of-experts design, adjustable reasoning, chain-of-thought access, fine-tuning, and support across common inference stacks. Treat these as source-reported capabilities rather than measured results, and validate the exact batch endpoint on your workloads.[1][2]
Strengths
- The exact-variant catalog lists long context, text input/output, tools, structured outputs, and common sampling controls.[1]
- The underlying model card reports configurable reasoning effort and access to chain-of-thought for debugging, while warning it is not for end users.[2]
- OpenAI describes the underlying weights as Apache-2.0 licensed and fine-tunable for specialized use.[2]
Limitations
- Evidence for the exact :batch listing is catalog-only; it does not explain batch execution semantics, service limits, or availability.[1]
- The model documentation concerns underlying gpt-oss-20b, not this hosted batch variant, so behavior and deployment properties require endpoint-level validation.[1][2]
- OpenRouter includes third-party measurements for selected design, coding, and agentic categories, but they are not workload-specific evidence of quality.[1]
Where to use it
- Evaluate for text-only applications with long prompts that need tools or structured outputs.[1]
- Consider for agent or function-calling prototypes, while testing the hosted batch variant end to end.[1][2]
- Use adjustable reasoning as a criterion: low for faster general dialogue and high for deeper analysis, subject to validation.[1][2]
Sources
- [1] OpenRouter catalog · OpenAI: gpt-oss-20b (batch)Sources checked: Nov 13, 2026
- [2] Model documentation · OpenAI: gpt-oss-20b (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-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...
Specifications
- Model ID
- openai/gpt-oss-20b:batch
- Canonical ID
- openai/gpt-oss-20b
- 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 $0.024 / out $0.112
- 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 | No measurement | 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 | Coding index | 20.7 | CC — below the B band | 13.11.2026 |
| Artificial Analysis | Agentic index | 1.2 | CC — below the B band | 13.11.2026 |
| Design Arena | models · datavizwin rate 39.7% · rank 127 | 933Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · websitewin rate 27.9% · rank 147 | 845Elo | 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 | $0.024 | $0.112 | — | — | — |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.