OpenAI
gpt-oss-20b
Launched 2025-08-05 · Knowledge up to 2024-06 · Listed on OpenRouter 2025-08-05
Prices updated . Benchmarks updated .
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...
You send / 1M
$0.018
tokens in
It replies / 1M
$0.090
tokens out
Context
131K
tokens it can read at once
Typical request
$0.0001
1,000 words in, 400 out
Benchmarks
| Benchmark | Score | Kind | Date | Source |
|---|---|---|---|---|
| Epoch Capabilities Index | 137.8 | Independent | 2025-08-05 | Epoch AI |
| GPQA DiamondMedium effort | 60.8% | Independent | 2026-08-27 | Epoch AI |
| OTIS Mock AIMEMedium effort | 65.3% | Independent | 2026-08-27 | Epoch AI |
| Terminal-Benchagent Mini-SWE-Agent | 3.4% | Independent | 2025-11-03 | Terminal-Bench, republished by Epoch AI |
| CritPtHigh effort | 1.4% | Independent | 2025-08-05 | CritPt, republished by Epoch AI |
| Arena Elo (text) | 1,287 | Independent | 2026-10-28 | LMArena |
Rankings on this site use the Epoch Capabilities Index, an independent composite. Lab-reported rows are the lab's own figures and are kept separate.
Data privacy
No training or retention: Yes. At least one provider serves it with zero data retention.
| Provider | You send / 1M | It replies / 1M | Uptime | Privacy policy |
|---|---|---|---|---|
| AkashML · fp4 | $0.018 | $0.090 | 100% | Read |
| DeepInfra · bf16 | $0.024 | $0.112 | 93% | Read |
| CoreWeave · fp4 | $0.030 | $0.130 | 100% | Read |
| DekaLLM · bf16 | $0.029 | $0.140 | 100% | Read |
| DeepInfra · bf16 | $0.030 | $0.140 | 98% | Read |
| Amazon Bedrock | $0.070 | $0.150 | 99% | Read |
| Amazon Bedrock | $0.070 | $0.150 | 100% | Read |
| Parasail · fp4 | $0.030 | $0.150 | 100% | Read |
| PrimeIntellect · fp4 | $0.117 | $0.175 | 100% | Read |
| SiliconFlow · fp8 | $0.040 | $0.180 | 89% | Read |
| Groq | $0.075 | $0.300 | 100% | Read |
Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.
What it can do
- Reads: text
- Writes: text
- Weights: Open weights
- Reasoning: Yes
- Tool calling: Yes
- Longest reply: 131K tokens
- Repeated text is billed at $0.0090 per 1M (prompt caching)
Compare with
Appears in
Estimate your monthly cost with gpt-oss-20b
Sources and licenses
- OpenRouter: Prices, context windows, modalities and the model list come from the OpenRouter public API. Data: OpenRouter.
- Vercel AI Gateway: The no-training flag comes from the Vercel AI Gateway model list.
- models.dev: Lab launch dates, open-weights flags and knowledge cutoffs come from models.dev. Copyright (c) 2025 models.dev, MIT License.
- Epoch AI: Independent benchmark scores and the Epoch Capabilities Index (ECI) come from Epoch AI's Benchmarking Hub, used under CC BY 4.0. Epoch AI, Capabilities & benchmarking, epoch.ai/benchmarks. Scores Epoch marks as external keep their original license, and the source is named on each score.
- LMArena: Arena Elo (text, webdev and vision) comes from the LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, leaderboard date 2026-10-28.
- Lab-reported scores, when an editor has added them, are the lab's own numbers. Each one links to the source and is labeled lab-reported. They are not used to rank the lists.
- What a score measures: the benchmark guide.
