# 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.

## Model Information

- **Organization**: [OpenAI](/llm.txt)
- **Slug**: gpt-oss-120b
- **Available at Providers**: 72
- **Release Date**: August 5, 2025

### Benchmark Scores
- Weekly: 2.73
- HLE: 0.149
- GPQA: 0.801

## Providers

| Provider | Name | $ Input (per 1M) | $ Output (per 1M) | Free | Link |
|----------|------|-----------------|------------------|------|------|
| [AIHubMix](/llm/aihubmix.txt) | gpt-oss-120b | 0.18 | 0.90 |  | [View](https://aihubmix.com/model/gpt-oss-120b) |
| [AIMLAPI](/llm/aimlapi.txt) | GPT OSS 120B | 0.05 | 0.55 |  |  |
| [FastRouter](/llm/fastrouter.txt) | OpenAI: GPT OSS 120B | 0.15 | 0.75 |  | [View](https://fastrouter.ai/models/openai/gpt-oss-120b) |
| [Fireworks AI](/llm/fireworks.txt) | OpenAI gpt-oss-120b | 0.15 | 0.60 |  |  |
| [Helicone](/llm/helicone.txt) | OpenAI GPT-OSS 120b | 0.04 | 0.16 |  | [View](https://www.helicone.ai/model/gpt-oss-120b) |
| [Privatemode AI](/llm/privatemodeai.txt) | gpt-oss-120b | 0.00 | 0.00 | Yes |  |
| [Vultr](/llm/vultr.txt) | GPT OSS 120B | 0.20 | 0.20 |  |  |
| [Nvidia](/llm/nvidia.txt) | gpt-oss-120b | 0.00 | 0.00 | Yes | [View](https://build.nvidia.com/openai/gpt-oss-120b) |
| [Groq](/llm/groq.txt) | GPT OSS 120B | 0.15 | 0.60 |  |  |
| [Abacus](/llm/abacus.txt) | GPT-OSS 120B | 0.08 | 0.44 |  |  |
| [Nebius Token Factory](/llm/nebius.txt) | gpt-oss-120b | 0.15 | 0.60 |  | [View](https://huggingface.co/openai/gpt-oss-120b) |
| [Novita AI](/llm/novita.txt) | gpt-oss-120b | 0.05 | 0.25 |  |  |
| [Cortecs](/llm/cortecs.txt) | GPT Oss 120b | 0.00 | 0.00 | Yes |  |
| [Together AI](/llm/togetherai.txt) | OpenAI GPT-OSS 120B | 0.15 | 0.60 |  |  |
| [SiliconFlow](/llm/siliconflow.txt) | gpt-oss-120b |  |  |  |  |
| [Cloudflare AI Gateway](/llm/cloudflareaigateway.txt) | GPT OSS 120B | 0.35 | 0.75 |  |  |
| [OVHcloud AI Endpoints](/llm/ovhcloud.txt) | gpt-oss-120b | 0.09 | 0.47 |  |  |
| [DeepInfra](/llm/deepinfra.txt) | gpt-oss-120b | 0.04 | 0.19 |  |  |
| [submodel](/llm/submodel.txt) | GPT OSS 120B | 0.10 | 0.50 |  |  |
| [IO.NET](/llm/ionet.txt) | GPT-OSS 120B | 0.04 | 0.40 |  |  |
| [Scaleway](/llm/scaleway.txt) | GPT-OSS 120B | 0.15 | 0.60 |  |  |
| [Cerebras](/llm/cerebras.txt) | GPT OSS 120B | 0.25 | 0.69 |  |  |
| [Nano-GPT](/llm/nanogpt.txt) | GPT OSS 120B |  |  |  |  |
| [Nano-GPT](/llm/nanogpt.txt) | GPT-OSS 120B TEE |  |  |  |  |
| [OpenRouter](/llm/openrouter.txt) | gpt-oss-120b | 0.04 | 0.19 |  | [View](https://openrouter.ai/openai/gpt-oss-120b) |
| [Poe](/llm/poe.txt) | GPT-OSS-120B | 1200.00 |  |  | [View](https://poe.com/gpt-oss-120b/api) |
| [Replicate](/llm/replicate.txt) | gpt-oss-120b |  |  |  |  |
| [Requesty](/llm/requesty.txt) |  | 0.15 | 0.75 |  |  |
| [Synthetic.new](/llm/synthetic.txt) | openai/gpt-oss-120b | 0.10 | 0.10 |  |  |
| [ValorGPT](/llm/valorgpt.txt) | gpt-oss-120b |  |  |  | [View](https://www.valorgpt.com/models/openai-gpt-oss-120b) |
| [ValorGPT](/llm/valorgpt.txt) | gpt-oss-120b |  |  | Yes | [View](https://www.valorgpt.com/models/openai-gpt-oss-120b-free) |
| [ValorGPT](/llm/valorgpt.txt) | gpt-oss-120b (exacto) |  |  |  | [View](https://www.valorgpt.com/models/openai-gpt-oss-120b-exacto) |
| [Vercel AI Gateway](/llm/vercel.txt) | gpt-oss-120b | 0.25 | 0.69 |  |  |
| [Yupp](/llm/yupp.txt) | gpt-oss-120b (Sambanova) |  |  |  |  |
| [Yupp](/llm/yupp.txt) | gpt-oss-120b (OpenRouter) |  |  |  |  |
| [Yupp](/llm/yupp.txt) | gpt-oss-120b (exacto) (OpenRouter) |  |  |  |  |
| [Atlas Cloud](/llm/atlascloud.txt) | GPT OSS 120b | 0.10 | 0.20 |  | [View](https://www.atlascloud.ai/models/openai/gpt-oss-120b) |
| [Routeway](/llm/routeway.txt) | OpenAI: GPT OSS 120B (Free) | 0.00 | 0.00 | Yes | [View](https://routeway.ai/models) |
| [Routeway](/llm/routeway.txt) | OpenAI: GPT OSS 120B | 0.04 | 0.30 |  | [View](https://routeway.ai/models) |
| [LangDB](/llm/langdb.txt) | gpt-oss-120b |  |  |  | [View](https://langdb.ai/app/models) |
| [Kilo Code](/llm/kilocode.txt) | OpenAI: gpt-oss-120b | 0.04 | 0.19 |  | [View](https://kilo.ai/models/openai/gpt-oss-120b) |
| [Kilo Code](/llm/kilocode.txt) | OpenAI: gpt-oss-120b (exacto) | 0.04 | 0.19 |  |  |
| [Parasail](/llm/parasail.txt) | Gpt Oss 120b | 0.10 | 0.75 |  | [View](https://www.saas.parasail.io/pricing) |
| [Firmware](/llm/firmware.txt) | GPT OSS 120B | 0.15 | 0.60 |  |  |
| [Near AI](/llm/near.txt) |  | 0.15 | 0.55 |  |  |
| [RedPill](/llm/redpill.txt) | OpenAI: GPT OSS 120B | 0.10 | 0.49 |  |  |
| [SambaNova AI](/llm/sambanova.txt) | gpt-oss-120b | 0.22 | 0.59 |  |  |
| [302.AI](/llm/302ai.txt) | gpt-oss-120b | 0.20 | 1.00 |  | [View](https://302ai-en.apifox.cn/api-207705128) |
| [Weights & Biases](/llm/wandb.txt) | gpt-oss-120b |  |  |  |  |
| [Berget.AI](/llm/berget.txt) | GPT-OSS-120B | 0.30 | 0.90 |  |  |
| [Cloudflare Workers AI](/llm/cloudflareworkersai.txt) | GPT OSS 120B | 0.35 | 0.75 |  |  |
| [Google Vertex AI](/llm/googlevertex.txt) | GPT-OSS 120B |  |  |  |  |
| [Inference](/llm/inference.txt) |  |  |  |  |  |
| [Arena AI](/llm/arenaai.txt) |  |  |  |  |  |
| [Okara](/llm/okara.txt) | GPT-OSS 120B |  |  |  | [View](https://okara.ai/ai-models/gpt-oss-120b) |
| [CommonStack](/llm/commonstack.txt) | OpenAI: GPT OSS 120B | 0.05 | 0.25 |  |  |
| [Chats-LLM](/llm/chatsllm.txt) | OpenAI: gpt-oss-120b | 0.04 | 0.19 |  |  |
| [NetMind](/llm/netmind.txt) | openai-oss-120b | 0.08 | 0.40 |  |  |
| [STACKIT](/llm/stackit.txt) | GPT-OSS 120B | 0.49 | 0.71 |  |  |
| [CometAPI](/llm/cometapi.txt) |  | 0.16 | 0.80 |  |  |
| [Windsurf](/llm/windsurf.txt) | gpt-oss 120B (Medium) |  |  |  |  |
| [Qiniu](/llm/qiniuai.txt) | gpt-oss-120b |  |  |  |  |
| [CloudFerro Sherlock](/llm/cloudferrosherlock.txt) | OpenAI GPT OSS 120B | 2.92 | 2.92 |  |  |
| [ApiYI](/llm/apiyi.txt) | gpt-oss-120b |  |  |  |  |
| [WaveSpeed AI](/llm/wavespeed.txt) | gpt-oss-120b | 0.04 | 0.21 |  |  |
| [OpenRouter](/llm/openrouter.txt) | gpt-oss-120b (free) | 0.00 | 0.00 | Yes | [View](https://openrouter.ai/openai/gpt-oss-120b:free) |
| [OpenRouter](/llm/openrouter.txt) | gpt-oss-120b (exacto) | 0.04 | 0.19 |  | [View](https://openrouter.ai/openai/gpt-oss-120b:exacto) |
| [evroc](/llm/evroc.txt) | GPT OSS 120B | 0.24 | 0.94 |  |  |
| [Airforce API](/llm/airforce.txt) | gpt-oss-120b |  |  |  |  |
| [Writingmate](/llm/writingmate.txt) | OpenAI: gpt-oss-120b (exacto) |  |  |  | [View](https://writingmate.ai/models/openai/gpt-oss-120b) |
| [Blackbox AI](/llm/blackboxai.txt) | blackboxai/openai/gpt-oss-120b |  |  |  |  |
| [LLM Stats](/llm/llmstats.txt) | GPT OSS 120B |  |  |  |  |

---

[← Back to all providers](/llm.txt)