# GPT OSS 120B API Pricing

As of October 10, 2026, GPT OSS 120B costs $0.03 per 1M input tokens and $0.17 per 1M output tokens from Weights & Biases, the lowest of 22 providers. It has a 131,000-token context window and returns up to 131,072 tokens per response.

- Page: https://models.litellm.ai/models/gpt-oss-120b
- Lab: OpenAI
- LiteLLM model name: `wandb/openai/gpt-oss-120b`
- Context window: 131,000 tokens
- Max output: 131,072 tokens
- Added to LiteLLM: August 2025
- Prices updated: October 10, 2026

## Pricing by provider

Token prices in USD per 1M tokens.

| Provider | Model name | Input | Output | Cache read | Per image | Per second | Context |
|---|---|---|---|---|---|---|---|
| Weights & Biases | `wandb/openai/gpt-oss-120b` | $0.03 | $0.17 | – | – | – | 131K |
| Amazon Bedrock Mantle | `bedrock_mantle/openai.gpt-oss-120b` | $0.15 | $0.60 | – | – | – | 128K |
| Azure AI Foundry | `azure_ai/gpt-oss-120b` | $0.15 | $0.60 | – | – | – | 128K |
| Baseten | `baseten/openai/gpt-oss-120b` | $0.10 | $0.50 | $0.10 | – | – | 128K |
| Cerebras | `cerebras/gpt-oss-120b` | $0.35 | $0.75 | – | – | – | 128K |
| Cloudflare Workers AI | `cloudflare/@cf/openai/gpt-oss-120b` | $0.35 | $0.75 | – | – | – | 128K |
| Crusoe | `crusoe/openai/gpt-oss-120b` | $0.80 | $0.80 | – | – | – | 128K |
| Databricks | `databricks/databricks-gpt-oss-120b` | $0.15 | $0.60 | $0.15 | – | – | 128K |
| DeepInfra | `deepinfra/openai/gpt-oss-120b` | $0.037 | $0.17 | – | – | – | 128K |
| Fireworks AI | `fireworks_ai/accounts/fireworks/models/gpt-oss-120b` | $0.15 | $0.60 | $0.015 | – | – | 128K |
| Fireworks AI | `fireworks_ai/gpt-oss-120b` | $0.15 | $0.60 | $0.015 | – | – | 128K |
| Google Vertex AI | `vertex_ai/openai/gpt-oss-120b-maas` | $0.09 | $0.36 | – | – | – | 128K |
| Groq | `groq/openai/gpt-oss-120b` | $0.15 | $0.60 | $0.075 | – | – | 128K |
| IBM watsonx.ai | `watsonx/openai/gpt-oss-120b` | $0.159 | $0.636 | – | – | – | 128K |
| Nebius AI Studio | `nebius/openai/gpt-oss-120b` | $0.15 | $0.60 | – | – | – | 128K |
| Novita AI | `novita/openai/gpt-oss-120b` | $0.05 | $0.25 | – | – | – | 128K |
| OVHcloud | `ovhcloud/gpt-oss-120b` | $0.08 | $0.40 | – | – | – | 131K |
| Replicate | `replicate/openai/gpt-oss-120b` | $0.18 | $0.72 | – | – | – | – |
| Sail | `sail/openai/gpt-oss-120b` | $0.06 | $0.40 | $0.03 | – | – | 128K |
| SambaNova | `sambanova/gpt-oss-120b` | $0.22 | $0.59 | – | – | – | 128K |
| Scaleway | `scaleway/openai/gpt-oss-120b` | $0.15 | $0.60 | – | – | – | 128K |
| Tensormesh | `tensormesh/openai/gpt-oss-120b` | $0.15 | $0.60 | $0 | – | – | 128K |
| Together AI | `together_ai/openai/gpt-oss-120b` | $0.15 | $0.60 | – | – | – | 128K |
| Amazon Bedrock Mantle (us-gov-east-1) | `bedrock_mantle/us-gov-east-1/openai.gpt-oss-120b` | $0.18 | $0.72 | – | – | – | 128K |
| Amazon Bedrock Mantle (us-gov-west-1) | `bedrock_mantle/us-gov-west-1/openai.gpt-oss-120b` | $0.18 | $0.72 | – | – | – | 128K |

## Cost examples

1,000 requests with 2,000 input and 500 output tokens each:

- Weights & Biases: $0.145
- DeepInfra: $0.159
- Novita AI: $0.225
- Sail: $0.32

100 long-document requests with 100,000 input and 2,000 output tokens each:

- Weights & Biases: $0.334
- DeepInfra: $0.404
- Novita AI: $0.55
- Sail: $0.68

## Features

Supported: Function calling, Parallel tool calls, Structured output, Reasoning, Prompt caching, Web search.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="wandb/openai/gpt-oss-120b",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does GPT OSS 120B cost?

GPT OSS 120B costs $0.03 per 1M input tokens and $0.17 per 1M output tokens from Weights & Biases, the lowest of 22 providers.

### What is the context window of GPT OSS 120B?

GPT OSS 120B has a 131,000-token context window and returns up to 131,072 tokens per response.

### Which providers offer GPT OSS 120B?

GPT OSS 120B is available from 22 providers through LiteLLM: Weights & Biases, Amazon Bedrock Mantle, Azure AI Foundry, Baseten, Cerebras, Cloudflare Workers AI, Crusoe, Databricks, DeepInfra, Fireworks AI, Google Vertex AI and Groq and 10 more. The lowest price is on Weights & Biases.

### How do I call GPT OSS 120B with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="wandb/openai/gpt-oss-120b", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

### What features does GPT OSS 120B support?

GPT OSS 120B supports function calling, parallel tool calls, structured output, reasoning, prompt caching and web search.

### When did LiteLLM add GPT OSS 120B?

GPT OSS 120B was added to LiteLLM's model price file in August 2025.

Source: LiteLLM model price file, https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json