Codestral Mamba API Pricing
As of October 10, 2026, Codestral Mamba costs $0.25 per 1M input tokens and $0.25 per 1M output tokens on Mistral AI, with cache reads at $0.025 per 1M tokens. It has a 256,000-token context window and returns up to 256,000 tokens per response.
- Input
- $0.25 / 1M tokens
- Output
- $0.25 / 1M tokens
- Cache read
- $0.025 / 1M tokens
- Context window
- 256,000 tokens
- Max output
- 256,000 tokens
- Providers
- 1
- Added to LiteLLM
- July 2024
Codestral Mamba pricing by provider
1 listing across 1 provider. 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 AIlatest alias | mistral/codestral-mamba-latest | $0.25 | $0.25 | $0.025 | 256K |
What Codestral Mamba costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| Mistral AI | $0.625 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| Mistral AI | $2.55 |
Use Codestral Mamba with LiteLLM
Call Codestral Mamba 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/codestral-mamba-latest",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: codestral-mamba
litellm_params:
model: mistral/codestral-mamba-latest
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": "codestral-mamba",
"messages": [{"role": "user", "content": "Hello!"}]
}'Codestral Mamba FAQ
How much does Codestral Mamba cost?
Codestral Mamba costs $0.25 per 1M input tokens and $0.25 per 1M output tokens on Mistral AI, with cache reads at $0.025 per 1M tokens.
What is the context window of Codestral Mamba?
Codestral Mamba has a 256,000-token context window and returns up to 256,000 tokens per response.
Which providers offer Codestral Mamba?
Codestral Mamba is available from Mistral AI through LiteLLM, using the model name mistral/codestral-mamba-latest.
How do I call Codestral Mamba with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="mistral/codestral-mamba-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.
When did LiteLLM add Codestral Mamba?
Codestral Mamba was added to LiteLLM's model price file in July 2024.
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.
Provider pages: Mistral AI.
