Skip to main content
idapt
HomeAI ModelsExploreResourcesPricing
Sign inUse for Free
Mistral AI

Codestral (2508)

$$Standard
Mistral
CompareChat

Mistral's dedicated code model — August 2025 update. Optimized for fast code completion, generation, and debugging across 80+ programming languages.

▼

Codestral (2508) is somewhat expensive at $0.30/M tokens input and $0.90/M tokens output. Cached input reads are priced at $0.03/M tokens, making repeated context cheaper. The model supports a 256K context window.

Best forCost-effective

Benchmarks

CodingInsufficient data
AgenticInsufficient data
ReasoningInsufficient data
MathInsufficient data
Sources:OpenRouter

Specifications

Vision
Audio
Reasoning
256K
Context
205K
Max output

Performance

Providers

Misc

August 1, 2025
Released
CompareChat with Codestral (2508)

Compare with

OpenAIGPT 6 Astravs Codestral (2508)OpenAIGPT 6.1 Sol Provs Codestral (2508)OpenAIGPT 6.1 Solvs Codestral (2508)OpenAIGPT 6 Lunavs Codestral (2508)AnthropicClaude Fable 5.1vs Codestral (2508)AnthropicClaude Opus 5.5vs Codestral (2508)AnthropicClaude Sonnet 5.5vs Codestral (2508)GoogleGemini 3.8 Flashvs Codestral (2508)GoogleGemini 4 Argonvs Codestral (2508)GoogleGemma 4 31Bvs Codestral (2508)xAIGrok 4.7vs Codestral (2508)xAIGrok Build 0.1vs Codestral (2508)MetaMuse Spark Openvs Codestral (2508)MetaMuse Wondervs Codestral (2508)DeepSeekDeepSeek V4 Pro (0813)vs Codestral (2508)DeepSeekDeepSeek V4.1 Flash 1017vs Codestral (2508)MiniMaxMiniMax M3vs Codestral (2508)MoonshotAIKimi K3vs Codestral (2508)MoonshotAIKimi K2.7 Codevs Codestral (2508)Zhipu AIGLM 5.3vs Codestral (2508)Zhipu AIGLM 5.3 Flashvs Codestral (2508)QwenQwen3.8 Max (0902)vs Codestral (2508)QwenQwen3 Coder Nextvs Codestral (2508)NVIDIANemotron 3 Ultravs Codestral (2508)NVIDIANemotron 3.5 Super VLvs Codestral (2508)
Frequently Asked Questions about Codestral (2508)▼

When was Codestral (2508) released?

▼

Codestral (2508) was released on August 1, 2025.

Who created Codestral (2508)?

▼

Codestral (2508) was created by Mistral.

How much does Codestral (2508) cost?

▼

Codestral (2508) costs $0.30/M input tokens and $0.90/M output tokens.

What is Codestral (2508) API pricing?

▼

The Codestral (2508) API is priced at $0.30 per million input tokens and $0.90 per million output tokens. You can access Codestral (2508) through idapt.app alongside 200+ other AI models in one workspace.

Is Codestral (2508) a reasoning model?

▼

No, Codestral (2508) is not a reasoning model. It responds directly without an extended internal thinking step. For tasks requiring deep chain-of-thought reasoning, consider models like Claude, o-series from OpenAI, or Gemini Thinking.

Does Codestral (2508) support image or vision input?

▼

No, Codestral (2508) does not currently support image or vision input. It is a text-only model.

Does Codestral (2508) support audio?

▼

No, Codestral (2508) does not support audio input.

What is the context window of Codestral (2508)?

▼

Codestral (2508) has a context window of 256K tokens, meaning it can process approximately 192,000 words of context at once.

Is Codestral (2508) open source?

▼

Codestral (2508) is a proprietary model developed by Mistral. The model weights and training data are not publicly available.

Where can I use Codestral (2508)?

▼

You can chat with Codestral (2508) on idapt.app — no separate API key required. idapt is an AI workspace with 200+ models, agents, computers, and tasks. You can also access Codestral (2508) through Mistral's own API or platform.

  • Home
  • Pricing
  • AI Models
  • Skills
  • Image models
  • Voice models
  • Video models
  • Rankings
  • Multi-Model Chat
  • Agents
  • Computers
  • Drive
  • Actions
  • AI Gateway
  • All features →
  • Blog
  • About
  • Comparisons
  • Benchmarks
  • Model Match
  • Demos
  • Help center
  • FAQ
  • Privacy
  • Support
  • Developers
  • Quickstarts
  • API reference
  • API pricing
  • CLI
  • MCP
  • Migrate
  • Downloads
  • Desktop
© idapt[email protected]TermsPrivacy PolicyLegal noticeReport content
X (Twitter)Discord