AI Model Profile

Codestral

Codestral is Mistral AI's coding-focused model line, listed in Mistral model documentation and context-window notes.

Family
Codestral
Release date
Unknown
Status
Current
Context window
128k tokens
Output limit
Unknown
API
yes
Open weights
no
Local/self-hosted
no
Pricing
See official pricing or platform page; rates can vary by endpoint, region, tier, batch mode, and partner platform.
Evidence state
Recheck due

Benchmark Caveat

Benchmarks and provider capability notes are directional, not universal rankings. Results can shift with prompts, tool use, latency targets, pricing tier, safety filters, context length, and the workload mix a real team runs.

See the linked official model, docs, model-card, or pricing source for provider-published capability notes.

Best for

Code completion, code assistants, software-engineering experiments, and Mistral-specific developer stacks.

Skip if

Skip if a general-purpose model has better results on your repo-specific evals.

Strengths

Mistral docs list Codestral with a 128k-token context window in known limitations.

Weaknesses

Coding quality should be tested against repository-specific tasks, tests, and security constraints.

Agent suitability

Useful for agent workflows when the provider supports tool use, long context, structured outputs, or workflow-specific APIs.

Kingy AI take

Use this as a source-backed shortlist candidate, not a universal ranking. Re-check official provider docs and run a task-specific trial before production adoption.

Verification & Sources

Evidence state
Recheck due
Source links
3
Freshness
Needs recheck: checked June 24, 2026
Last updated
June 23, 2026
What this evidence state means
Definition
The claim was previously checked, but its review window expired or a material change may have invalidated it.
Required provenance
The prior evidence and check date are retained, together with the expiry or change signal that triggered recheck.
Owner
Kingy freshness queue owner and assigned editorial reviewer
Freshness rule
This is already outside its freshness rule. It must not be presented as current until reviewed against current evidence.
Disputes and corrections
Use “Suggest a correction” on the record. Kingy editorial reviews the cited evidence, records material corrections, and changes or removes the state when it is not supported.
Suggest a correction

Form submissions, correction notes, score details, URLs, and analytics events may be stored for editorial review, spam prevention, product improvement, and follow-up. Do not submit secrets, unreleased financials, private customer data, or regulated personal data through these forms.

Full Model Notes

Codestral is Mistral AI’s coding-focused model line, listed in Mistral model documentation and context-window notes.

Coding notes

Good candidate for code workflows, but compare against general frontier coding models on real tasks.

Reasoning notes

Provider capability notes are useful but should be validated on representative prompts and tools.

Creative notes

Use a small creative test set before standardizing outputs for brand, media, or customer-facing work.

Research notes

Track release notes and model lifecycle notices because availability and aliases can change.

API pricing notes

Check the official pricing page before budget decisions; Kingy does not freeze token, credit, or subscription prices in model cards.

License notes

Commercial/API terms apply unless the linked official source states otherwise.

Hardware requirements

Cloud/API model; local hardware requirements are not published as a self-hosted path.