Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Mistral AI / Codestral

Codestral 25.08

Code generation and fill-in-the-middle completion.

Language models (LLMs)
availableClosed weightsCoding
Official documentation (opens in a new tab)Reviewed 12 Oct 2026
10 of 18 specification fields collected
Context window128K128,000 tokens
Maximum outputNot collectedAwaiting source review
Input / 1M tokens$0.30Mistral AI API
Output / 1M tokens$0.90USD · observed 12 Oct 2026

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
128,000 tokensSource for Context / input limit (opens in a new tab)

As displayed on the release card; decimal k converted to tokens.

Maximum output
Not collected
Input modalities
TextSource for Input modalities (opens in a new tab)
Output modalities
TextSource for Output modalities (opens in a new tab)
Reasoning
Not collected
Tool calling
SupportedSource for Tool calling (opens in a new tab)
Structured output
SupportedSource for Structured output (opens in a new tab)
Streaming
Not collected
Batch processing
SupportedSource for Batch processing (opens in a new tab)
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
2025-07-29Source for Release date (opens in a new tab)
Parameters
Not collected
Architecture
Not collected
Languages
Not collected
Supported API routes
/v1/chat/completions, /v1/conversations, /v1/batch, /v1/fim/completionsSource for Supported API routes (opens in a new tab)
API aliases
codestral-latestSource for API aliases (opens in a new tab)

Aliases shown on this release card at review time; routing can change.

Context caching
SupportedSource for Context caching (opens in a new tab)

Documented on at least one recorded endpoint. See Caching for host, lifecycle and billing restrictions.

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

Mistral AI API

Provider source (opens in a new tab)
API model ID
codestral-2508
Access
API account required; quotas and regional availability depend on configuration.
Regions
Not collected
INPUT / 1M TOKENS$0.30
OUTPUT / 1M TOKENS$0.90

Standard published token rates. Tools, caching, batch discounts, taxes and negotiated terms are not included. Cached input price: $0.03 / 1M tokens (base tier).

USD · observed 12 Oct 2026 · Pricing evidence (opens in a new tab)
Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
CodingInput1$0.301M tokens
CodingOutput1$0.901M tokens

Rate conditions

  1. Standard USD rate from the release card. Each unit is billed separately; do not combine page, audio and token rates.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

Mistral AI API

codestral-2508
Documented
Support evidence (opens in a new tab)
How it works
Prefix caching with a routing keySource for How it works (opens in a new tab)
Minimum reusable input
64-token cache blocks; fewer than 64 prompt tokens cannot hit the cache.Source for Minimum reusable input (opens in a new tab)
Lifetime & refresh
Not collected
How to enable it
Use the same prompt_cache_key for related requests and preserve their common prefix.Source for How to enable it (opens in a new tab)
Usage fields
usage.prompt_tokens_details.cached_tokensSource for Usage fields (opens in a new tab)
Billing rules
The current pricing table lists a cached-input rate. Native billing units are retained below; do not convert pages or minutes into token prices.Source for Billing rules (opens in a new tab)
Limits & data boundaries
A stable key improves the chance of reuse but does not guarantee it. A cache lifetime is not specified in the reviewed guide.Source for Limits & data boundaries (opens in a new tab)
Cache reads, writes & storage
ChargeApplies toRate / unit
Cache read1Text tokens · Base tier$0.03 / 1M tokensPricing evidence (opens in a new tab)

Rate conditions

  1. Standard published token rates. Tools, caching, batch discounts, taxes and negotiated terms are not included.

Observed 12 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.

Caching reviewed 12 Oct 2026

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

This exact release is labeled Premier and provides no public weights on its official model card. Releases with MRL/MNPL weight downloads are excluded separately, even when the internal catalog also calls them Premier.

Classification evidence (opens in a new tab)

Sources reviewed