LiteLLMModels

Pixtral Large API Pricing

As of October 10, 2026, Pixtral Large costs $2.00 per 1M input tokens and $6.00 per 1M output tokens on Mistral AI, with cache reads at $0.20 per 1M tokens. It has a 128,000-token context window and returns up to 128,000 tokens per response.

By Mistral AIModel ID mistral/pixtral-large-latestPrices updated Checked
Input
$2.00 / 1M tokens
Output
$6.00 / 1M tokens
Cache read
$0.20 / 1M tokens
Context window
128,000 tokens
Max output
128,000 tokens
Providers
3
Added to LiteLLM
January 2025

Pixtral Large pricing by provider

5 listings across 3 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

ProviderModel name in LiteLLMInputOutputCache readContext
Mistral AIlatest aliasmistral/pixtral-large-latest$2.00$6.00$0.20128K
Amazon Bedrocksnapshot 2502mistral.pixtral-large-2502-v1:0$2.00$6.00–128K
Vercel AI Gatewayvercel_ai_gateway/mistral/pixtral-large$2.00$6.00–128K
Amazon BedrockEU cross-region, snapshot 2502eu.mistral.pixtral-large-2502-v1:0$2.00$6.00–128K
Amazon BedrockUS cross-region, snapshot 2502us.mistral.pixtral-large-2502-v1:0$2.00$6.00–128K

What Pixtral Large costs in practice

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

Mistral AI$7.00
Amazon Bedrock$7.00
Vercel AI Gateway$7.00

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

Mistral AI$21.20
Amazon Bedrock$21.20
Vercel AI Gateway$21.20

Pixtral Large features

Use Pixtral Large with LiteLLM

Call Pixtral Large 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="mistral/pixtral-large-latest",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: pixtral-large
    litellm_params:
      model: mistral/pixtral-large-latest
      api_key: os.environ/MISTRAL_API_KEY
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": "pixtral-large",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Pixtral Large FAQ

How much does Pixtral Large cost?

Pixtral Large costs $2.00 per 1M input tokens and $6.00 per 1M output tokens on Mistral AI, with cache reads at $0.20 per 1M tokens.

What is the context window of Pixtral Large?

Pixtral Large has a 128,000-token context window and returns up to 128,000 tokens per response.

Which providers offer Pixtral Large?

Pixtral Large is available from 3 providers through LiteLLM: Mistral AI, Amazon Bedrock and Vercel AI Gateway.

How do I call Pixtral Large with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="mistral/pixtral-large-latest", 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 Pixtral Large support?

Pixtral Large supports function calling, structured output and image input.

When did LiteLLM add Pixtral Large?

Pixtral Large was added to LiteLLM's model price file in January 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: Mistral AI, Amazon Bedrock, Vercel AI Gateway.

Provider pages: Mistral AI, Amazon Bedrock, Vercel AI Gateway.