gpt-oss-120b pricing
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. Below you will find 21 current rows with input and output dollars per million. Right now the lowest input is $0.030 and the lowest output is $0.170.
Pricing across providers
Every row is a seller of gpt-oss-120b with token pricing we track. The cheapest input in this snapshot is from Wandb. The bar chart shows the same input and output dollars per million for a quick scan.
| Provider | Input / 1M | Output / 1M | Cached input | Batch |
|---|---|---|---|---|
A Azure | $0.150 | $0.600 | — | — |
B Baseten | $0.100 | $0.500 | $0.100 | — |
C Cerebras | $0.350 | $0.750 | — | — |
C Cloudflare | $0.350 | $0.750 | — | — |
C Crusoe | $0.800 | $0.800 | — | — |
D DeepInfra | $0.037 | $0.170 | — | — |
FA Fireworks AI | $0.150 | $0.600 | $0.015 | — |
G Groq | $0.150 | $0.600 | $0.075 | — |
IW Ibm Watsonx | $0.159 | $0.636 | — | — |
I Inferenceapis | $0.200 | $0.800 | — | — |
N Nebius | $0.150 | $0.600 | — | — |
N Novita | $0.050 | $0.250 | — | — |
O Openrouter | $0.150 | $0.600 | — | — |
O Ovhcloud | $0.080 | $0.400 | — | — |
R Replicate | $0.180 | $0.720 | — | — |
S Sail | $0.060 | $0.400 | $0.030 | — |
S Sambanova | $0.220 | $0.590 | — | — |
S Scaleway | $0.150 | $0.600 | — | — |
T Tensormesh | $0.150 | $0.600 | $0.0000 | — |
TA Together AI | $0.150 | $0.600 | — | — |
W Wandb | $0.030 | $0.170 | — | — |
Input vs output · per provider
Cost calculator
Use this block to stress test gpt-oss-120b cost without a spreadsheet. All estimates come from public list rates in this page.
Provider
0.015000¢ / req
0.030000¢ / req
Model specifications
These fields describe gpt-oss-120b as we store it (source: OpenAI). They sit next to price so buyers can check limits and tools in one place.
- Context window
- 131,072 tokens
- Max output
- 131,072 tokens
- Vision (images)
- No
- Tool / function calling
- Yes
- Streaming
- No
- Released
- Aug 2025
- Primary provider
- OpenAI
- Model family
- N/A
Compare gpt-oss-120b
These links open full side by side pages for gpt-oss-120b. We picked pairs that people often shop together. 6 ready to open.
Locked
Compare with
Pick a model on both sides.
Popular gpt-oss-120b comparisons
- gpt-oss-120b vs Claude Sonnet 4.6
Compare pricing side by side
- gpt-oss-120b vs Gemini 2.0 Flash
Compare pricing side by side
- gpt-oss-120b vs Llama 3.1 70B
Compare pricing side by side
- gpt-oss-120b vs Mistral 7B
Compare pricing side by side
- gpt-oss-120b vs GLM 4.7
Compare pricing side by side
- gpt-oss-120b vs Amazon Nova Lite V1 0
Compare pricing side by side
Frequently asked questions
Read these after the table if you want plain language around gpt-oss-120b rates. The short model note from our index: 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 ...
Related models
Models close to gpt-oss-120b by family, provider, and context window — each with live pricing in our catalog.