gpt-oss-120b
OpenAIgpt-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...
In
$0.04
Out
$0.17
Blended
$0.07
Where to buy this model
20 access routes| Route | In | Out | Blended | vs |
|---|---|---|---|---|
| ● AkashML cheapestbf16 | $0.03 | $0.17 | $0.07 | - |
| ● CoreWeave fp4 | $0.03 | $0.17 | $0.07 | +0% |
| ● DekaLLM bf16 | $0.03 | $0.18 | $0.07 | +0% |
| $0.04 | $0.17 | $0.07 | +0% | |
| ● Crusoe bf16 | $0.05 | $0.25 | $0.10 | +43% |
| $0.05 | $0.25 | $0.10 | +43% | |
| $0.06 | $0.42 | $0.15 | +114% | |
| $0.09 | $0.36 | $0.16 | +129% | |
| ● Mancer 2 fp8 | $0.06 | $0.50 | $0.17 | +143% |
| $0.10 | $0.50 | $0.20 | +186% | |
 Amazon Bedrock | $0.15 | $0.60 | $0.26 | +271% |
| $0.15 | $0.60 | $0.26 | +271% | |
| ● SiliconFlow fp8 | $0.15 | $0.60 | $0.26 | +271% |
| ● Phala | $0.15 | $0.60 | $0.26 | +271% |
| $0.15 | $0.60 | $0.26 | +271% | |
| $0.15 | $0.60 | $0.26 | +271% | |
| $0.10 | $0.75 | $0.26 | +271% | |
| ● Mara | $0.15 | $0.75 | $0.30 | +329% |
| $0.14 | $0.95 | $0.34 | +386% | |
| $0.35 | $0.75 | $0.45 | +543% |
● official API · ● cloud platform · ● inference host · USD per 1M tokens. Same model, different providers - price and quantization vary.
- Ctx
- 131K
- max output
- 118K
- Family
- gpt
- Modalities
- text
- Features
- json · reasoning · tools
Live pricing, updated 2026-09-15.