OpenAI
GPT OSS 120B
Open GPT reasoning model for self-hosted agents and controllable deployments
Model facts
- Context window
- 131K tokens
- Maximum output
- 33K tokens
- Cheapest paid input
- $0.039 per 1M tokens
- Cheapest paid output
- $0.1 per 1M tokens
- Open weights
- yes
- Providers
- 85
Capabilities and modalities
reasoning, tool calling, structured output, attachments, temperature control, open weights, text, image.
Local hardware estimate
At 4K context: Q4_K_M 72.5 GiB, Q8_0 126.9 GiB, F16 228.9 GiB working memory.
- Parameters
- 116.8 billion
- Architecture
- gptoss
- Model license
- apache-2.0
Planning estimate adapted from the MIT-licensed whichllm estimator using metadata from Hugging Face; not a vendor minimum requirement.
Artificial Analysis benchmarks
Compare this model on the full LLM benchmark leaderboard.
| Configuration | AAI | Coding | Math | Output tokens/s |
|---|---|---|---|---|
| high | 24.1 | 30.4 | 93.4 | 151.6 |
| low | 14.9 | 21.2 | 66.7 | 156.1 |
Observed price history
- 2026-08-24: $0.039 input / $0.1 output per 1M tokens
API providers
- Kenari — model id gpt-oss-120b; free input / free output per 1M tokens; provider documentation
- Nvidia — model id openai/gpt-oss-120b; free input / free output per 1M tokens; provider documentation
- Pendra — model id gpt-oss:120b; free input / free output per 1M tokens; provider documentation
- QVAC — model id gpt-oss-120b; free input / free output per 1M tokens; provider documentation
- Eden AI — model id flexai/gpt-oss-120b; $0.039 input / $0.1 output per 1M tokens; provider documentation
- DevPass (LLM Gateway) — model id gpt-oss-120b; $0.032 input / $0.14 output per 1M tokens; provider documentation
- LLM Gateway (Runware) — model id runware/gpt-oss-120b; $0.032 input / $0.14 output per 1M tokens; provider documentation
- Helicone — model id gpt-oss-120b; $0.04 input / $0.16 output per 1M tokens; provider documentation
- Kilo Gateway — model id openai/gpt-oss-120b; $0.03 input / $0.17 output per 1M tokens; provider documentation
- OrcaRouter — model id openai/gpt-oss-120b; $0.03 input / $0.17 output per 1M tokens; provider documentation
- Synthetic — model id hf:openai/gpt-oss-120b; $0.1 input / $0.1 output per 1M tokens; provider documentation
- Weights & Biases — model id openai/gpt-oss-120b; $0.03 input / $0.17 output per 1M tokens; provider documentation
- OpenRouter — model id openai/gpt-oss-120b; $0.037 input / $0.17 output per 1M tokens; provider documentation
- Deep Infra — model id openai/gpt-oss-120b; $0.037 input / $0.17 output per 1M tokens; provider documentation
- Eden AI — model id deepinfra/openai/gpt-oss-120b; $0.037 input / $0.17 output per 1M tokens; provider documentation
- TensorX — model id openai/gpt-oss-120b; $0.04 input / $0.2 output per 1M tokens; provider documentation
- Crusoe — model id openai/gpt-oss-120b; $0.05 input / $0.2 output per 1M tokens; provider documentation
- NovitaAI (OpenAI) — model id openai/gpt-oss-120b; $0.05 input / $0.25 output per 1M tokens; provider documentation
- DInference — model id gpt-oss-120b; $0.068 input / $0.27 output per 1M tokens; provider documentation
- Databricks — model id databricks-gpt-oss-120b; $0.072 input / $0.28 output per 1M tokens; provider documentation
- Venice AI (OpenAI) — model id openai-gpt-oss-120b; $0.07 input / $0.3 output per 1M tokens; provider documentation
- DigitalOcean — model id openai-gpt-oss-120b; $0.055 input / $0.385 output per 1M tokens; provider documentation
- IO.NET — model id openai/gpt-oss-120b; $0.04 input / $0.4 output per 1M tokens; provider documentation
- Merge Gateway — model id openai/gpt-oss-120b; $0.09 input / $0.36 output per 1M tokens; provider documentation
- Vertex — model id openai/gpt-oss-120b-maas; $0.09 input / $0.36 output per 1M tokens; provider documentation
- SiliconFlow — model id openai/gpt-oss-120b; $0.05 input / $0.45 output per 1M tokens; provider documentation
- Abacus — model id openai/gpt-oss-120b; $0.08 input / $0.44 output per 1M tokens; provider documentation
- OpenReason — model id openai/gpt-oss-120b; $0.105 input / $0.422 output per 1M tokens; provider documentation
- Cortecs — model id gpt-oss-120b; $0.089 input / $0.446 output per 1M tokens; provider documentation
- Eden AI — model id ovhcloud/gpt-oss-120b; $0.09 input / $0.47 output per 1M tokens; provider documentation
- OVHcloud AI Endpoints — model id gpt-oss-120b; $0.09 input / $0.47 output per 1M tokens; provider documentation
- LLM Gateway (ByteDance) — model id bytedance/gpt-oss-120b; $0.1 input / $0.5 output per 1M tokens; provider documentation
- Vercel AI Gateway — model id openai/gpt-oss-120b; $0.1 input / $0.5 output per 1M tokens; provider documentation
- submodel — model id openai/gpt-oss-120b; $0.1 input / $0.5 output per 1M tokens; provider documentation
- AKI.IO — model id gpt-oss-120b; $0.15 input / $0.55 output per 1M tokens; provider documentation
- NEAR AI Cloud — model id openai/gpt-oss-120b; $0.15 input / $0.55 output per 1M tokens; provider documentation
- CoralBricks — model id gpt-oss-120b; $0.12 input / $0.6 output per 1M tokens; provider documentation
- LLM Gateway (SCX.ai (Turbo)) — model id scx-ai/gpt-oss-120b; $0.17 input / $0.55 output per 1M tokens; provider documentation
- SCX.ai — model id gpt-oss-120b; $0.17 input / $0.55 output per 1M tokens; provider documentation
- Eden AI — model id databricks/databricks-gpt-oss-120b; $0.15 input / $0.6 output per 1M tokens; provider documentation
- Eden AI (EU) — model id databricks/databricks-gpt-oss-120b@eu; $0.15 input / $0.6 output per 1M tokens; provider documentation
- Amazon Bedrock — model id openai.gpt-oss-120b; $0.15 input / $0.6 output per 1M tokens; provider documentation
- Amazon Bedrock — model id openai.gpt-oss-120b-1:0; $0.15 input / $0.6 output per 1M tokens; provider documentation
- Eden AI — model id fireworks_ai/gpt-oss-120b; $0.15 input / $0.6 output per 1M tokens; provider documentation
- Eden AI — model id groq/openai/gpt-oss-120b; $0.15 input / $0.6 output per 1M tokens; provider documentation
- Eden AI — model id nebius/openai/gpt-oss-120b; $0.15 input / $0.6 output per 1M tokens; provider documentation
- Eden AI — model id together_ai/openai/gpt-oss-120b; $0.15 input / $0.6 output per 1M tokens; provider documentation
- FastRouter — model id openai/gpt-oss-120b; $0.15 input / $0.6 output per 1M tokens; provider documentation
- Fireworks AI — model id accounts/fireworks/models/gpt-oss-120b; $0.15 input / $0.6 output per 1M tokens; provider documentation
- FrogBot — model id gpt-oss-120b; $0.15 input / $0.6 output per 1M tokens; provider documentation
- Groq — model id openai/gpt-oss-120b; $0.15 input / $0.6 output per 1M tokens; provider documentation
- Impossibl — model id fireworks/gpt-oss-120b; $0.15 input / $0.6 output per 1M tokens; provider documentation
- Impossibl — model id groq/gpt-oss-120b; $0.15 input / $0.6 output per 1M tokens; provider documentation
- LLM Gateway (Azure) — model id azure/gpt-oss-120b; $0.15 input / $0.6 output per 1M tokens; provider documentation
- LLM Gateway (Together AI) — model id together-ai/gpt-oss-120b; $0.15 input / $0.6 output per 1M tokens; provider documentation
- Nebius Token Factory — model id openai/gpt-oss-120b; $0.15 input / $0.6 output per 1M tokens; provider documentation
- Neon — model id gpt-oss-120b; $0.15 input / $0.6 output per 1M tokens; provider documentation
- OpenRouter — model id openai/gpt-oss-120b:batch; $0.15 input / $0.6 output per 1M tokens; provider documentation
- Pioneer — model id openai/gpt-oss-120b; $0.15 input / $0.6 output per 1M tokens; provider documentation
- Scaleway — model id gpt-oss-120b; $0.15 input / $0.6 output per 1M tokens; provider documentation
- Tinfoil — model id gpt-oss-120b; $0.15 input / $0.6 output per 1M tokens; provider documentation
- Together AI — model id openai/gpt-oss-120b; $0.15 input / $0.6 output per 1M tokens; provider documentation
- ai& — model id openai/gpt-oss-120b; $0.15 input / $0.6 output per 1M tokens; provider documentation
- watsonx.ai — model id openai/gpt-oss-120b; $0.159 input / $0.636 output per 1M tokens; provider documentation
- Eden AI — model id scaleway/gpt-oss-120b; $0.174 input / $0.697 output per 1M tokens; provider documentation
- Charm Hyper — model id gpt-oss-120b; $0.188 input / $0.7 output per 1M tokens; provider documentation
- LLM Gateway (Groq) — model id groq/gpt-oss-120b; $0.15 input / $0.75 output per 1M tokens; provider documentation
- Eden AI — model id ionos/openai/gpt-oss-120b; $0.174 input / $0.755 output per 1M tokens; provider documentation
- Hugging Face — model id openai/gpt-oss-120b; $0.25 input / $0.69 output per 1M tokens; provider documentation
- GreenPT — model id gpt-oss-120b; $0.228 input / $0.798 output per 1M tokens; provider documentation
- Cerebras — model id gpt-oss-120b; $0.35 input / $0.75 output per 1M tokens; provider documentation
- Cloudflare Workers AI — model id @cf/openai/gpt-oss-120b; $0.35 input / $0.75 output per 1M tokens; provider documentation
- Eden AI — model id cerebras/gpt-oss-120b; $0.35 input / $0.75 output per 1M tokens; provider documentation
- Eden AI — model id cloudflare/@cf/openai/gpt-oss-120b; $0.35 input / $0.75 output per 1M tokens; provider documentation
- Impossibl — model id cerebras/gpt-oss-120b; $0.35 input / $0.75 output per 1M tokens; provider documentation
- LLM Gateway (Cerebras) — model id cerebras/gpt-oss-120b; $0.35 input / $0.75 output per 1M tokens; provider documentation
- NanoGPT — model id openai/gpt-oss-120b; $0.35 input / $0.75 output per 1M tokens; provider documentation
- evroc — model id openai/gpt-oss-120b; $0.23 input / $0.92 output per 1M tokens; provider documentation
- STACKIT — model id openai/gpt-oss-120b; $0.53 input / $0.76 output per 1M tokens; provider documentation
- Privatemode AI — model id gpt-oss-120b; $0.497 input / $1.96 output per 1M tokens; provider documentation
- Regolo AI — model id gpt-oss-120b; $1 input / $4.2 output per 1M tokens; provider documentation
- CloudFerro Sherlock (OpenAI) — model id openai/gpt-oss-120b; $2.92 input / $2.92 output per 1M tokens; provider documentation
- Arena — model id gpt-oss-120b; not published input / not published output per 1M tokens; provider documentation
- Ollama Cloud — model id gpt-oss:120b; not published input / not published output per 1M tokens; provider documentation
- Qiniu — model id gpt-oss-120b; not published input / not published output per 1M tokens; provider documentation