Model
Model
OpenAI
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...
| Provider | Quantization | Input / M tokens | Output / M tokens |
|---|---|---|---|
| Near AInear-ai/fp4 | fp4 | $0.03 | $0.15 |
| Venicevenice/int4 | int4 | $0.03 | $0.15 |
| CoreWeavecoreweave/fp4 | fp4 | $0.03 | $0.17 |
| DekaLLMdekallm/bf16 | bf16 | $0.03 | $0.18 |
| AkashMLakashml/bf16 | bf16 | $0.03 | $0.187 |
| DeepInfradeepinfra/bf16 | bf16 | $0.037 | $0.17 |
| Crusoecrusoe/bf16 | bf16 | $0.05 | $0.25 |
| Mancer 2mancer/fp8 | fp8 | $0.05 | $0.25 |
| Novitanovita/fp4 | fp4 | $0.05 | $0.25 |
| DigitalOceandigitalocean | — | $0.06 | $0.42 |
| Googlegoogle-vertex/global | — | $0.09 | $0.36 |
| BaseTenbaseten/fp4 | fp4 | $0.10 | $0.50 |
| BaseTenbaseten/fp4/us | fp4 | $0.10 | $0.50 |
| Parasailparasail/fp4 | fp4 | $0.10 | $0.75 |
| SambaNovasambanova | — | $0.14 | $0.95 |
| Amazon Bedrockamazon-bedrock | — | $0.15 | $0.60 |
| Amazon Bedrockamazon-bedrock/eu-west-1 | — | $0.15 | $0.60 |
| Groqgroq | — | $0.15 | $0.60 |
| Nebiusnebius/fp4 | fp4 | $0.15 | $0.60 |
| Phalaphala | — | $0.15 | $0.60 |
| SiliconFlowsiliconflow/fp8 | fp8 | $0.15 | $0.60 |
| Togethertogether | — | $0.15 | $0.60 |
| Maramara | — | $0.15 | $0.75 |
| Cerebrascerebras/fp16 | fp16 | $0.35 | $0.75 |
Prices are what the Provider charges, synced 2026-10-21. Amber adds its platform fee to each Trial’s total; see pricing.
gpt-oss-120b
gpt-oss-120b-high