Home › Frontier and closed › mistralai

Codestral 2508 mistralai

Closed weights API only frontier listed on OpenRouter 2025-08-01 (449d ago) · source Last verified 2026-10-25 06:51 UTC Docs ↗ OpenRouter ↗

Release timeline

Stages observed by the nightly radar: announced → API only → weights public → served by third parties. Each entry carries the source it was seen at.

  1. 2025-08-01 · API only source
    seeded from the earliest dated observation when first seen · observed 2026-10-07 20:20 UTC

Description

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)

via OpenRouter listing · observed 2026-10-24 21:26 UTC. The listing text is the provider's own description, not an assessment.

Where to run 2 providers · 3 endpoints

Hosted endpoints observed for Codestral 2508, sorted by input price (USD per million tokens). Each row names its observer and date; prices change daily, so check the source before quoting. Cheapest observed input price: $0.30/M.

ProviderModel refContextQuant$/M in$/M outtok/sTTFTToolsStatusObserved
Mistral
openrouter
mistralai/codestral-2508 250K unknown $0.30 $0.90 — — yes live 2026-10-24
Mistral
openrouter
mistralai/codestral-2508 250K unknown $0.33 $0.99 — — yes live 2026-10-24
Mistral (first-party)
mistral-api
codestral-2508 250K — — — — — — live 2026-10-24

No third-party providers observed beyond the lab's own endpoints. Cache-read price $0.03/M (source, observed 2026-10-24).

Facts

Context length256,000 tokens (250K) · OpenRouter listing
Modalitiestext + file → text
Max completion tokens204,800
Knowledge cutoff2025-03-31
Lab API idsMistral: codestral-2508
Supported parametersfrequency_penalty, max_tokens, prediction, presence_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_p
OpennessClosed weights · open-weights lab, name matches a closed line
StageAPI only
Confidencemedium
Pricing (USD per M tokens) in $0.30 · out $0.90 · cache read $0.03
OpenRouter list price (cheapest live endpoint) · source · observed 2026-10-24 21:26 UTC

Open alternatives 5

Nearest open-weights models by modality, context and price on this watch list. Not a quality ranking.

ModelOrgParamsContext$/M inLicenseWhy it is here
Meta-Llama-3-8B-Instruct meta-llama 8.03B — — llama3 closest by rank, context and price
MiniMax-M2.5 MiniMaxAI 229B 192K $0.27 other similar context (197K), cheaper input price ($0.27/M vs $0.3/M)
DeepSeek-R1 deepseek-ai 684B 160K $0.70 mit closest by rank, context and price
Llama-3.1-8B meta-llama 8.03B — — llama3.1 closest by rank, context and price
GLM-5 zai-org 754B 198K $0.60 mit similar context (203K)

Get alerts

Watch the release radar

Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.

Sources

Radar run: 2026-10-25 06:51 UTC · Last verified 2026-10-25 06:51 UTC