gpt-oss-120b
OpenAI · openai/gpt-oss-120b
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...
gpt-oss-120b ranks #69 of 348 models in the default AI Benchmark Hub order (quality first, then cost). At $0.10 blended per million tokens, it is cheaper than 92% of models with published API pricing. Its 131,072-token context window is 2.0× smaller than the catalog median (262,144 tokens).
Context
Max output: 117964
Pricing
Output / 1M: 0.17
Blend / 1M: 0.10
Quality
Provider
Moderated: no
Monthly cost at this blended rate
Estimated API spend if every token is billed at $0.10per million (the blend of this model's input and output prices). Real bills depend on the input/output mix.
| Tokens / month | Est. cost (USD) |
|---|---|
| 1,000,000 | $0.10 |
| 10,000,000 | $1.03 |
| 100,000,000 | $10.35 |
Related models
Same lab, similar price, or similar quality — useful next comparisons.
More from OpenAI
- GPT-5.5$17.50 / 1M · Q 80.4
- GPT-5.4$8.75 / 1M · Q 79.3
- GPT-5.2 Chat$7.88 / 1M · Q 75.2
- GPT-5.2$7.88 / 1M · Q 75.2
- GPT-5.1$5.63 / 1M · Q 75.0
Closest API price
- DeepSeek V4 Flash Latest$0.10 / 1M
- Phi 4$0.11 / 1M
- Reka Edge$0.10 / 1M
- Ministral 3 3B 2512$0.10 / 1M
- Gemma 3 12B$0.10 / 1M