Codestral Embed API Pricing

As of October 10, 2026, Codestral Embed costs $0.15 per 1M input tokens on Mistral AI. It has an 8,192-token context window.

By Mistral AIModel ID mistral/codestral-embedPrices updated October 10, 2026Checked October 10, 2026

Input: $0.15 / 1M tokens
Cache read: $0.015 / 1M tokens
Context window: 8,192 tokens
Providers: 2
Added to LiteLLM: September 2025

Codestral Embed pricing by provider

3 listings across 2 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/codestral-embed`	$0.15	–	$0.015	8K
Mistral AIsnapshot 2505	`mistral/codestral-embed-2505`	$0.15	–	$0.015	8K
Vercel AI Gateway	`vercel_ai_gateway/mistral/codestral-embed`	$0.15	$0	–	–

What Codestral Embed costs in practice

Embedding 10,000 documents of 500 tokens each

Mistral AI	$0.75
Vercel AI Gateway	$0.75

Use Codestral Embed with LiteLLM

Call Codestral Embed through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/embeddings. LiteLLM tracks the cost of every request at these prices.

Python SDK

from litellm import embedding

response = embedding(
    model="mistral/codestral-embed",
    input=["hello world"],
)

Proxy config.yaml

model_list:
  - model_name: codestral-embed
    litellm_params:
      model: mistral/codestral-embed
      api_key: os.environ/MISTRAL_API_KEY

Call the proxy

curl http://0.0.0.0:4000/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "codestral-embed",
    "input": "hello world"
  }'

Codestral Embed FAQ

How much does Codestral Embed cost?

Codestral Embed costs $0.15 per 1M input tokens on Mistral AI.

What is the context window of Codestral Embed?

Codestral Embed has an 8,192-token context window.

Which providers offer Codestral Embed?

Codestral Embed is available from 2 providers through LiteLLM: Mistral AI and Vercel AI Gateway.

How do I call Codestral Embed with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="mistral/codestral-embed", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/embeddings from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

When did LiteLLM add Codestral Embed?

Codestral Embed was added to LiteLLM's model price file in September 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.

LiteLLM docs: Mistral AI, Vercel AI Gateway.

Provider pages: Mistral AI, Vercel AI Gateway.