LiteLLMModels

Mistral Small API Pricing

As of October 10, 2026, Mistral Small costs $0.10 per 1M input tokens and $0.30 per 1M output tokens on Mistral AI, with cache reads at $0.01 per 1M tokens. Across 6 providers on LiteLLM, the input price ranges from $0.10 to $0.15. It has a 32,000-token context window and returns up to 8,191 tokens per response.

By Mistral AIModel ID mistral/mistral-smallPrices updated Checked
Input
$0.10 / 1M tokens
Output
$0.30 / 1M tokens
Cache read
$0.01 / 1M tokens
Context window
32,000 tokens
Max output
8,191 tokens
Providers
6
Added to LiteLLM
December 2023

Mistral Small pricing by provider

10 listings across 6 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

ProviderModel name in LiteLLMInputOutputCache readBatch inBatch outContext
Mistral AImistral/mistral-small$0.10$0.30$0.01––32K
Mistral AIsnapshot 2603mistral/mistral-small-2603$0.15$0.60$0.015––256K
Mistral AIlatest aliasmistral/mistral-small-latest$0.15$0.60$0.015––256K
Amazon Bedrock †snapshot 2402mistral.mistral-small-2402-v1:0$1.00$3.00–$0.50$1.5032K
Azure AI Foundry †azure_ai/mistral-small$1.00$3.00–––32K
Azure AI Foundrysnapshot 2503azure_ai/mistral-small-2503$0.10$0.30–––128K
Google Vertex AIsnapshot 2503vertex_ai/mistral-small-2503$0.10$0.30–––128K
Google Vertex AIsnapshot 2503vertex_ai/mistral-small-2503@001$0.10$0.30–––32K
IBM watsonx.aisnapshot 2503watsonx/mistralai/mistral-small-2503$0.10$0.30–––32K
Vercel AI Gatewayvercel_ai_gateway/mistral/mistral-small$0.10$0.30–––32K

† This price differs from the other providers by more than 8x and is left out of the headline price. Check the provider's pricing page.

What Mistral Small costs in practice

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

Mistral AI$0.35
Azure AI Foundry$0.35
Google Vertex AI$0.35
IBM watsonx.ai$0.35

Mistral Small features

Use Mistral Small with LiteLLM

Call Mistral Small 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/mistral-small",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: mistral-small
    litellm_params:
      model: mistral/mistral-small
      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": "mistral-small",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Mistral Small FAQ

How much does Mistral Small cost?

Mistral Small costs $0.10 per 1M input tokens and $0.30 per 1M output tokens on Mistral AI, with cache reads at $0.01 per 1M tokens. Across 6 providers on LiteLLM, the input price ranges from $0.10 to $0.15.

What is the context window of Mistral Small?

Mistral Small has a 32,000-token context window and returns up to 8,191 tokens per response.

Which providers offer Mistral Small?

Mistral Small is available from 6 providers through LiteLLM: Mistral AI, Amazon Bedrock, Azure AI Foundry, Google Vertex AI, IBM watsonx.ai and Vercel AI Gateway. The lowest price is on Mistral AI.

How do I call Mistral Small with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="mistral/mistral-small", 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 Mistral Small support?

Mistral Small supports function calling, parallel tool calls, structured output, image input and reasoning.

When did LiteLLM add Mistral Small?

Mistral Small was added to LiteLLM's model price file in December 2023.

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, Azure AI Foundry, Google Vertex AI, IBM watsonx.ai, Vercel AI Gateway.

Provider pages: Mistral AI, Amazon Bedrock, Azure AI Foundry, Google Vertex AI, IBM watsonx.ai, Vercel AI Gateway.