GPT OSS 120B
by Impossibl · family gpt-oss · listed Aug 2025RTW
Open GPT reasoning model for self-hosted agents and controllable deployments
Current rates USD per 1M tokens
Input$0.15
Output$0.60
Cache read$0.015
Cache write—
Against the market
On the record
- Model id
fireworks/gpt-oss-120b- Context window
- 131K tokens
- Max output
- 33K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- Jun 2024
- Released
- 2025-08-05
- Last updated
- 2025-08-05
- Provider docs
- impossibl.com/docs/models
Back of the envelope
≈
Also listed at
- QVACfree in · free out
- OrcaRouter$0.03 in · $0.17 out
- NanoGPT$0.03 in · $0.15 out
- Kilo Gateway$0.03 in · $0.15 out
- CoreWeave$0.03 in · $0.17 out
- Kenari$0.036 in · $0.20 out
- Deep Infra$0.037 in · $0.17 out
- Eden AI$0.037 in · $0.17 out
- Abacus$0.037 in · $0.17 out
- Helicone$0.04 in · $0.16 out
- SiliconFlow$0.05 in · $0.45 out
- Crusoe$0.05 in · $0.25 out
- Merge Gateway$0.05 in · $0.25 out
- Novita AI$0.05 in · $0.25 out
- DInference$0.0675 in · $0.27 out