Codestral 2508
text+file->text
Code-specialist model from Mistral. 256K context fits whole repos and 80+ programming languages.
Codestral 2508 is a efficient AI model from Mistral. It costs $0.300 per million input tokens and $0.900 per million output tokens (blended $0.480/M), with a 256,000-token context window.
Profile inherited from upstream Codestral ↗ — this is a hosted variant of the same open-weights model.
INPUT
$0.300/M
per million input tokens
OUTPUT
$0.900/M
per million output tokens
CONTEXT
256,000
tokens
What it is good at
- Code-tuned
- 256K context
- 80+ languages
Typical use cases
- IDE autocomplete
- Code review
- Repo Q&A
Benchmarks
vs. best public score
Scores inherited from Codestral — this is a hosted variant of the same open-weights model, so the underlying benchmark scores are identical.
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources, treat as directional rather than authoritative.
More from Mistral
See all 15 →Mistral Large 3
Frontier · 256,000 ctx
in $0.500/Mout $1.500/M
Mistral Medium 3.5
Balanced · 256,000 ctx
in $1.500/Mout $7.500/M
Mistral Small 4
Efficient · 128,000 ctx
in $0.100/Mout $0.300/M
Mistral Large 2
Frontier · 128,000 ctx
in $2.000/Mout $6.000/M
Pixtral Large
Vision · 128,000 ctx
in $2.000/Mout $6.000/M
Pixtral 12B
Compact Vision · 128,000 ctx
in $0.150/Mout $0.150/M
Frequently asked questions
How much does Codestral 2508 cost?
Codestral 2508 costs $0.300 per million input tokens and $0.900 per million output tokens, for a blended reference rate of $0.480 per million tokens.
What is Codestral 2508's context window?
Codestral 2508 supports up to 256,000 tokens of context in a single request.
What is Codestral 2508 best for?
Codestral 2508 is well suited to Code-tuned, 256K context and 80+ languages.
Who makes Codestral 2508?
Codestral 2508 is developed and served by Mistral.