All Models
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 to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.
Available Providers (33)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 Nvidia | openai/gpt-oss-120b | $0.00/MTok | $0.00/MTok | 128K | 8.2K | |
 Privatemode AI | gpt-oss-120b | $0.00/MTok | $0.00/MTok | 128K | 128K | |
 Cortecs | gpt-oss-120b | $0.00/MTok | $0.00/MTok | 128K | 128K | |
 IO.NET | openai/gpt-oss-120b | $0.04/MTok | $0.40/MTok | 131.1K | 4.1K | |
 Deep Infra | openai/gpt-oss-120b | $0.05/MTok | $0.24/MTok | 131.1K | 16.4K | |
 NanoGPT | openai/gpt-oss-120b | $0.05/MTok | $0.25/MTok | 128K | 16.4K | |
 DInference | gpt-oss-120b | $0.07/MTok | $0.27/MTok | 131.1K | 32.8K | |
 OpenRouter | openai/gpt-oss-120b | $0.07/MTok | $0.28/MTok | 131.1K | 32.8K | |
 Abacus | openai/gpt-oss-120b | $0.08/MTok | $0.44/MTok | 128K | 32.8K | |
 Vertex | openai/gpt-oss-120b-maas | $0.09/MTok | $0.36/MTok | 131.1K | 32.8K | |
 OVHcloud AI Endpoints | gpt-oss-120b | $0.09/MTok | $0.47/MTok | 131.1K | 131.1K | |
 Synthetic | hf:openai/gpt-oss-120b | $0.10/MTok | $0.10/MTok | 128K | 32.8K | |
 submodel | openai/gpt-oss-120b | $0.10/MTok | $0.50/MTok | 131.1K | 32.8K | |
 Vercel AI Gateway | openai/gpt-oss-120b | $0.10/MTok | $0.50/MTok | 131.1K | 131.1K | |
 Baseten | openai/gpt-oss-120b | $0.10/MTok | $0.50/MTok | 128K | 128K | |
 FastRouter | openai/gpt-oss-120b | $0.15/MTok | $0.60/MTok | 131.1K | 32.8K | |
 Nebius Token Factory | openai/gpt-oss-120b | $0.15/MTok | $0.60/MTok | 128K | 8.2K | |
 Scaleway | gpt-oss-120b | $0.15/MTok | $0.60/MTok | 128K | 32.8K | |
 Amazon Bedrock | openai.gpt-oss-120b-1:0 | $0.15/MTok | $0.60/MTok | 128K | 4.1K | |
 Groq | openai/gpt-oss-120b | $0.15/MTok | $0.60/MTok | 131.1K | 65.5K | |
 Weights & Biases | openai/gpt-oss-120b | $0.15/MTok | $0.60/MTok | 131.1K | 131.1K | |
 Fireworks AI | accounts/fireworks/models/gpt-oss-120b | $0.15/MTok | $0.60/MTok | 131.1K | 32.8K | |
 Together AI | openai/gpt-oss-120b | $0.15/MTok | $0.60/MTok | 131.1K | 131.1K | |
 Firmware | gpt-oss-120b | $0.15/MTok | $0.60/MTok | 131.1K | 32.8K | |
 Vultr | gpt-oss-120b | $0.15/MTok | $0.60/MTok | 130K | 8.2K | |
 evroc | openai/gpt-oss-120b | $0.24/MTok | $0.94/MTok | 65.5K | 65.5K | |
 Cerebras | gpt-oss-120b | $0.25/MTok | $0.69/MTok | 131.1K | 32.8K | |
 Berget.AI | openai/gpt-oss-120b | $0.30/MTok | $0.90/MTok | 128K | 8.2K | |
 Cloudflare AI Gateway | workers-ai/@cf/openai/gpt-oss-120b | $0.35/MTok | $0.75/MTok | 128K | 16.4K | |
 Cloudflare Workers AI | @cf/openai/gpt-oss-120b | $0.35/MTok | $0.75/MTok | 128K | 16.4K | |
 STACKIT | openai/gpt-oss-120b | $0.49/MTok | $0.71/MTok | 131K | 8.2K | |
 Qiniu | gpt-oss-120b | —/MTok | —/MTok | 128K | 4.1K | |
 Ollama Cloud | gpt-oss:120b | —/MTok | —/MTok | 131.1K | 32.8K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output