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.

By OpenAIModel ID wandb/openai/gpt-oss-120bPrices updated October 10, 2026Checked October 10, 2026

Input: $0.03 / 1M tokens
Output: $0.17 / 1M tokens
Context window: 131,000 tokens
Max output: 131,072 tokens
Providers: 22
Added to LiteLLM: August 2025

GPT OSS 120B pricing by provider

25 listings across 22 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

Provider	Model name in LiteLLM	Input	Output	Cache read	Cache write	Batch in	Batch out	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	$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	–	–	$0.045	$0.18	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 Mantleus-gov-east-1	`bedrock_mantle/us-gov-east-1/openai.gpt-oss-120b`	$0.18	$0.72	–	–	–	–	128K
Amazon Bedrock Mantleus-gov-west-1	`bedrock_mantle/us-gov-west-1/openai.gpt-oss-120b`	$0.18	$0.72	–	–	–	–	128K

What GPT OSS 120B costs in practice

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

GPT OSS 120B features

Function calling
Parallel tool calls
Structured output
Reasoning
Prompt caching
Web search

Use GPT OSS 120B with LiteLLM

Call GPT OSS 120B through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.

Python SDK

from litellm import completion

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

Proxy config.yaml

model_list:
  - model_name: gpt-oss-120b
    litellm_params:
      model: wandb/openai/gpt-oss-120b
      # credentials: see the provider's LiteLLM docs page

Call the proxy

curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "gpt-oss-120b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

GPT OSS 120B 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.

Sources

Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:

LiteLLM docs: Weights & Biases, Amazon Bedrock Mantle, Azure AI Foundry, Baseten, Cerebras, Cloudflare Workers AI.

Provider pages: Weights & Biases, Amazon Bedrock Mantle, Azure AI Foundry, Baseten, Cerebras, Cloudflare Workers AI, Crusoe, Databricks, DeepInfra, Fireworks AI, Google Vertex AI, Groq.