Codestral 2508 (batch)
Codestral 2508 · Batch tier (Batch)
Asynchronous batch tier: discounted offline batch requests with high throughput and relaxed latency — ideal for large-scale non-real-time workloads.
Best for: Large-scale offline inference, cost-sensitive batch jobs, backfills
This page covers the Codestral 2508 Batch tier, sharing the underlying model capability with its real-time standard tier; the main difference is in billing mode and invocation method. See the Codestral 2508 standard real-time tier.
Provider：Mistral AI
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)
Key specs
- Context：256K
- Max output：204.8K
- Tokenizer：Mistral
- Released：2025-08-01
Token pricing
- Input price：$0.300 / 1M tokens
- Output price：$0.900 / 1M tokens
- Cache read：$0.030 / 1M tokens
- Blended price：$0.450 / 1M tokens
Modalities
Text, File
Use Cases
- Code Generation & Review：Auto-complete functions, generate unit tests, cross-file refactor suggestions; supports JSON Schema–constrained output for direct API integration.（≈ $0.0036/call）
- Deep Reasoning & Analysis：Process long legal docs, academic papers, financial reports; multi-hop reasoning and evidence-chain tracing across huge contexts.（≈ $0.0072/call）
- Chat & Support：FAQ auto-response, multi-turn dialogue, emotion detection — e-commerce, finance, gov.（≈ $0.0045/turn）
When to pick this model
Signals derived from public pricing and spec fields — not a benchmark. Validate with official docs and your own eval.
- Low input + output price: solid fit for high-frequency calls and batch processing.
- Long max output (>=30K tokens): strong fit for deep report / essay / document-drafting workflows.
- File / PDF input support: fit for document parsing, contract review, RAG over private data.
FAQ
- What is the token pricing of Codestral 2508 (batch)? Input price $0.300 / 1M tokens, output price $0.900 / 1M tokens, blended about $0.450 / 1M tokens. Refer to Mistral AI’s official page for the exact rate.
- What context window does Codestral 2508 (batch) support? Context window is 256K, max output about 204.8K, suitable for long documents, multi-turn chat and complex reasoning.
- What scenarios is Codestral 2508 (batch) best for? Based on its capability and pricing, Codestral 2508 (batch) fits best: Code Generation & Review, Deep Reasoning & Analysis, Chat & Support. See the Use Cases section for details and cost estimates.
- What input/output modalities does Codestral 2508 (batch) support? Supports Text, File modality.
- Is Codestral 2508 (batch) a free model? Codestral 2508 (batch) is billed per token, not a free model.
- Which provider offers Codestral 2508 (batch)? Codestral 2508 (batch) is offered by Mistral AI.
More models from Mistral AI
Full info：Codestral 2508 (batch)