Codestral 2508

by Mistralmistralai/codestral-2508

  • Text
  • No route yet
  • Released
  • Knowledge cutoff 31 March 2025

LLMCompare cannot run Codestral 2508 yet.No route to this model is configured on this site yet. Its prices and parameters are listed below for reference.

See the models that can be run now

Codestral 2508 at a glance

Context length
256,000 tokens
Maximum output
204,800 tokens
Accepts
Text, File
Returns
Text
Features
JSON outputTool callingPrompt caching
Reasoning effort levels
Not supported
Released
1 Aug 2025
Knowledge cutoff
31 March 2025

Model facts synced from the OpenRouter model list on 21 Oct 2026.

Codestral 2508 pricing by route

A route is the service LLMCompare calls to reach the model. Codestral 2508 has 1 route. Prices are in US dollars.

Prices of Codestral 2508 on each route
RouteOn LLMCompareInputper 1M tokensOutputper 1M tokensCache readper 1M tokensPrice verified onSource
OpenRouterDefaultNot configured$0.30$0.90$0.03openrouter.ai/mistralai/codestral-2508

The cost shown in an LLMCompare report is calculated from these prices as they were at the time of the run.

Cost calculator

Estimate what a batch of calls to Codestral 2508 costs. The starting numbers are examples. Change them to match your task.

Part of the input tokens above, billed at the cache read price.

Cost per call
$0.00075
1 credits
Cost of 100 calls
$0.075
100 credits

Calculated from the OpenRouter prices verified on 21 Oct 2026. Credits are the cost plus a 20% service fee, at $0.001 per credit, rounded up for each call, with a minimum of 1 per call. A real run is charged for the usage the provider reports.

Parameters you can set

These are the parameters LLMCompare can set when it calls the model through OpenRouter.

Parameters of Codestral 2508
ParameterTypeRange or optionsDefault
temperatureNumber0 to 2in steps of 0.1Provider default
top_pNumber0 to 1in steps of 0.05Provider default
max_tokensInteger1 to 204,800Provider default
seedInteger-2,147,483,648 to 4,294,967,295Provider default
response_formatOne oftextjson_objectProvider default

About Codestral 2508

Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.

[Blog Post](https://mistral.ai/news/codestral-25-08)

Description as published for this model. LLMCompare has not edited it.

Models to compare with Codestral 2508

Text models from the same provider and models at the nearest price. The order is not a ranking.

Models to compare with Codestral 2508
Add to comparisonModelContextMax outputInput priceper 1M tokensOutput priceper 1M tokensFeaturesReleasedOn LLMCompare
Mistral Small 3.1 24BMistralmistralai/mistral-small-3.1-24b-instruct128k102k$0.351$0.555JSONToolsVisionNo route yet
SabaMistralmistralai/mistral-saba32.8k26.2k$0.20$0.60JSONToolsCacheNo route yet
Mistral Small 4Mistralmistralai/mistral-small-2603262k210k$0.15$0.60ReasoningJSONToolsCacheVisionNo route yet
GLM 4.6VZ.aiz-ai/glm-4.6v131k32.8k$0.30$0.90JSONToolsCacheVisionNo route yet
DeepSeek V3.1DeepSeekdeepseek/deepseek-chat-v3.1164k32.8k$0.25$0.95JSONToolsCacheNo route yet
Qwen3 Next 80B A3B InstructQwenqwen/qwen3-next-80b-a3b-instruct262k16.4k$0.09$1.10JSONToolsNo route yet

Questions about Codestral 2508

How much does Codestral 2508 cost?
On the OpenRouter route, Codestral 2508 costs $0.30 per 1 million input tokens and $0.90 per 1 million output tokens, in US dollars. Input tokens that Codestral 2508 reads from the prompt cache cost $0.03 per 1 million tokens. LLMCompare verified this price on 21 Oct 2026.
What is the context length of Codestral 2508?
Codestral 2508 has a context length of 256,000 tokens and returns up to 204,800 output tokens in one call.
What inputs does Codestral 2508 accept?
Codestral 2508 accepts these inputs: Text, File. Codestral 2508 returns: Text.
Can I test Codestral 2508 on my own data?
Not yet. LLMCompare lists the prices and parameters of Codestral 2508, but no route to Codestral 2508 is configured on LLMCompare, so it cannot be selected for an evaluation.