Codestral 2405
API id
codestral-2405Input / 1M
-
not listed
Output / 1M
-
not listed
Context window
32K
tokens
Max output
8K
tokens per reply
Hosts
2
2 listings
Released
-
date not published
Where to run it
2 hosts serve Codestral 2405. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Mistral CodestralLab API codestral-2405 | - | codestral-2405 | |
Mistral Codestral FIMLab API codestral-2405 | - | codestral-2405 |
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
Similar models
This model has no listed price, so these are current models with similar capabilities.
Smaller Mistral AI models
Other frontier labs
Open-weight picks
Model line
Newer and older versions, at each lab's own price.
- Aug 2025Codestral 2508Latest$0.30 / $0.90
- UndatedCodestral 2501$0.20 / $0.60
- UndatedCodestral 2405This pageNot listed
- UndatedCodestral 2$0.30 / $0.90
Call it
Using Mistral Codestral's API.
Python
from litellm import completion
response = completion(
model="codestral/codestral-2405",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
Which APIs offer Codestral 2405?
Codestral 2405 runs on 2 APIs: Mistral Codestral and Mistral Codestral FIM.
What is Codestral 2405's context window?
32K tokens, with up to 8K tokens in one reply.
Is Codestral 2405 being retired?
It has been retired: Mistral Codestral FIM retired it on 16 Jun 2025.
Is there a newer version of Codestral 2405?
Yes. Codestral 2508 is the newest model in this line, released on 1 Aug 2025.
What is Codestral 2405's API model id?
Use codestral-2405 with Mistral Codestral.
Sources
Raw catalog entry for codestral-2405 on Mistral Codestral
{
"deprecation_date": "2025-06-16",
"deprecation_source": "https://docs.mistral.ai/getting-started/models/",
"input_cost_per_token": 0,
"litellm_provider": "codestral",
"max_input_tokens": 32000,
"max_output_tokens": 8191,
"mode": "chat",
"output_cost_per_token": 0,
"source": "https://docs.mistral.ai/capabilities/code_generation/",
"supports_assistant_prefill": true,
"supports_tool_choice": true
}