LiteLLMModels

Mistral Medium 3 API Pricing

As of October 10, 2026, Mistral Medium 3 costs $1.50 per 1M input tokens and $7.50 per 1M output tokens on Mistral AI, with cache reads at $0.15 per 1M tokens. Across 2 providers on LiteLLM, the input price ranges from $0.40 to $1.50. It has a 262,144-token context window and returns up to 262,144 tokens per response.

By Mistral AIModel ID mistral/mistral-medium-3Prices updated Checked
Input
$1.50 / 1M tokens
Output
$7.50 / 1M tokens
Cache read
$0.15 / 1M tokens
Context window
262,144 tokens
Max output
262,144 tokens
Providers
2
Added to LiteLLM
July 2025

Mistral Medium 3 pricing by provider

5 listings across 2 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

ProviderModel name in LiteLLMInputOutputCache readContext
Mistral AImistral/mistral-medium-3$1.50$7.50$0.15256K
Google Vertex AIvertex_ai/mistral-medium-3$0.40$2.00–128K
Google Vertex AIvertex_ai/mistral-medium-3@001$0.40$2.00–128K
Google Vertex AIvertex_ai/mistralai/mistral-medium-3$0.40$2.00–128K
Google Vertex AIvertex_ai/mistralai/mistral-medium-3@001$0.40$2.00–128K

What Mistral Medium 3 costs in practice

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

Mistral AI$6.75
Google Vertex AI$1.80

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

Mistral AI$16.50
Google Vertex AI$4.40

Mistral Medium 3 features

Use Mistral Medium 3 with LiteLLM

Call Mistral Medium 3 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-medium-3",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: mistral-medium-3
    litellm_params:
      model: mistral/mistral-medium-3
      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-medium-3",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Mistral Medium 3 FAQ

How much does Mistral Medium 3 cost?

Mistral Medium 3 costs $1.50 per 1M input tokens and $7.50 per 1M output tokens on Mistral AI, with cache reads at $0.15 per 1M tokens. Across 2 providers on LiteLLM, the input price ranges from $0.40 to $1.50.

What is the context window of Mistral Medium 3?

Mistral Medium 3 has a 262,144-token context window and returns up to 262,144 tokens per response.

Which providers offer Mistral Medium 3?

Mistral Medium 3 is available from 2 providers through LiteLLM: Mistral AI and Google Vertex AI. The lowest price is on Google Vertex AI.

How do I call Mistral Medium 3 with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="mistral/mistral-medium-3", 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 Medium 3 support?

Mistral Medium 3 supports function calling, structured output, image input and reasoning.

When did LiteLLM add Mistral Medium 3?

Mistral Medium 3 was added to LiteLLM's model price file in July 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, Google Vertex AI.

Provider pages: Mistral AI, Google Vertex AI.