Mistral Medium API Pricing
As of October 10, 2026, Mistral Medium 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 3 providers on LiteLLM, the input price ranges from $0.40 to $3.00. It has a 262,144-token context window and returns up to 262,144 tokens per response.
- 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
- 3
- Added to LiteLLM
- December 2023
Mistral Medium 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.
| Provider | Model name in LiteLLM | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| Mistral AI | mistral/mistral-medium | $1.50 | $7.50 | $0.15 | 256K |
| Mistral AIsnapshot 2604 | mistral/mistral-medium-2604 | $1.50 | $7.50 | $0.15 | 256K |
| Mistral AIlatest alias | mistral/mistral-medium-latest | $1.50 | $7.50 | $0.15 | 256K |
| Azure AI Foundrysnapshot 2505 | azure_ai/mistral-medium-2505 | $0.40 | $2.00 | – | 128K |
| IBM watsonx.aisnapshot 2505 | watsonx/mistralai/mistral-medium-2505 | $3.00 | $10.00 | – | 128K |
What Mistral Medium costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| Mistral AI | $6.75 |
| Azure AI Foundry | $1.80 |
| IBM watsonx.ai | $11.00 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| Mistral AI | $16.50 |
| Azure AI Foundry | $4.40 |
| IBM watsonx.ai | $32.00 |
Mistral Medium features
- Function calling
- Parallel tool calls
- Structured output
- Image input
- Reasoning
Use Mistral Medium with LiteLLM
Call Mistral Medium 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.
from litellm import completion
response = completion(
model="mistral/mistral-medium",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: mistral-medium
litellm_params:
model: mistral/mistral-medium
api_key: os.environ/MISTRAL_API_KEYcurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "mistral-medium",
"messages": [{"role": "user", "content": "Hello!"}]
}'Mistral Medium FAQ
How much does Mistral Medium cost?
Mistral Medium 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 3 providers on LiteLLM, the input price ranges from $0.40 to $3.00.
What is the context window of Mistral Medium?
Mistral Medium has a 262,144-token context window and returns up to 262,144 tokens per response.
Which providers offer Mistral Medium?
Mistral Medium is available from 3 providers through LiteLLM: Mistral AI, Azure AI Foundry and IBM watsonx.ai. The lowest price is on Azure AI Foundry.
How do I call Mistral Medium with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="mistral/mistral-medium", 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 support?
Mistral Medium supports function calling, parallel tool calls, structured output, image input and reasoning.
When did LiteLLM add Mistral Medium?
Mistral Medium 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, Azure AI Foundry, IBM watsonx.ai.
Provider pages: Mistral AI, Azure AI Foundry, IBM watsonx.ai.