Codestral
codestral-latestPricing
List prices at Mistral AI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.30 | $0.90 | |
| Cached input 90% off input | $0.03 | 90% off input |
What it costs a month
At Mistral AI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$133
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$112
- Coding agent1,000 requests a day, 40K in / 2K out, cached$187
- Overnight batch20,000 requests a day, 4K in / 0.4K out$936
Where to run it
5 hosts serve Codestral. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Mistral AILab API codestral-latest | $0.30 / $0.90 | codestral-latest | |
Mistral CodestralLab API codestral-latest | - | codestral-latest | |
Mistral Codestral FIMLab API codestral-latest | - | codestral-latest | |
Vertex AICloud codestral@2405 | $0.20 / $0.60 −33% vs headline | codestral@2405 | |
Vercel AI GatewayGateway codestral | $0.30 / $0.90 | codestral |
Show 1 more listings: regions, snapshots and variantsHide regional listings
| Vertex AI | |||||||
| Alias codestral@latest | $0.20 / $0.60 −33% vs headline | codestral@latest | |||||
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- Text
- Produces
- Text
- Features
- Assistant prefill
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
- Vertex AI33% lesscodestral@2405$0.20 / $0.60
- Vertex AI33% lesscodestral@latest$0.20 / $0.60
Smaller Mistral AI models
- 42% less
- 42% less
- 47% less
Other frontier labs
- 56% less
- 56% less
- 42% less
Open-weight picks
- 3% less
- 18% less
- 22% less
- 42% less
Benchmarks
Scores published on the model card.
- Aider Polyglot11.1%
Call it
Using Mistral AI's API.
from litellm import completion
response = completion(
model="mistral/codestral-latest",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Codestral cost?
On Mistral AI, Codestral costs $0.30 per million input tokens and $0.90 per million output tokens. Cached input costs $0.03 per million tokens. The cheapest host is Vertex AI, at $0.20 per million input tokens and $0.60 per million output tokens.
Which APIs offer Codestral?
Codestral runs on 5 APIs: Mistral AI, Mistral Codestral, Mistral Codestral FIM, Vertex AI and Vercel AI Gateway.
What is Codestral's context window?
128K tokens, with up to 128K tokens in one reply.
Is Codestral being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Codestral?
Models that cost less and keep most of what it can do: Magistral Small on Mistral AI (42% less), Claude Haiku 5.5 on Anthropic (56% less), GPT-6 Luna on OpenAI (56% less) and MiMo V2.6 Pro on GMI Cloud (3% less). Codestral itself costs 33% less on Vertex AI. Savings are on a mix of 3 input tokens to 1 output token.
What is Codestral's API model id?
Use codestral-latest with Mistral AI. Other hosts use their own ids: codestral@2405 on Vertex AI, codestral on Vercel AI Gateway.
Sources
Raw catalog entry for codestral-latest on Mistral AI
{
"cache_read_input_token_cost": 3e-8,
"input_cost_per_token": 3e-7,
"litellm_provider": "mistral",
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 9e-7,
"source": "https://docs.mistral.ai/models/model-cards/codestral-25-08",
"supports_assistant_prefill": true,
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true
}