Mistral AI · Codestral 22b V0 1 · active
Codestral-22B-v0.1
Codestral-22B-v0.1 is an open-weight language model published by Mistral AI.
mistralai/Codestral-22B-v0.1Provider availability
Serving endpoints and pricing
This page represents one immutable developer model ID. Serving endpoints, pricing, regions, quantizations, and service tiers attach separately and never create duplicate model records.
Technical specification
Capabilities
Version lineage
Explicit unknowns
- Release date
- Maximum output
- Knowledge cutoff
- API availability
- Provider pricing
Comparable peers
Related model comparisons
Questions
Codestral-22B-v0.1 FAQs
What is Codestral-22B-v0.1?+
Codestral-22B-v0.1 is an open-weight language model published by Mistral AI. It is developed by Mistral AI and its current sourced lifecycle status is active.
What inputs and outputs does Codestral-22B-v0.1 support?+
Codestral-22B-v0.1's current record lists Text as input and Text as output.
How much context does Codestral-22B-v0.1 support?+
The current record lists a 32,768-token context window and does not report a maximum output length.
Is Codestral-22B-v0.1 available through an API?+
Codestral-22B-v0.1's current primary-source record does not establish API availability. No provider endpoint is treated as available without direct provider evidence.
How large is Codestral-22B-v0.1?+
The current record lists 22.2B total parameters and an unknown active parameter count. Its architecture is MistralForCausalLM.
What capabilities and tasks does Codestral-22B-v0.1 support?+
Codestral-22B-v0.1's recorded capabilities are generation. Its supported tasks are text.
Can Codestral-22B-v0.1 be self-hosted?+
Codestral-22B-v0.1 is an open-weight model. Self-hosting is supported, and the recorded license is other.
Does Codestral-22B-v0.1 have related versions or aliases?+
No predecessor is recorded. No successor is recorded. Recorded aliases are mistralai/Codestral-22B-v0.1.
Which models can Codestral-22B-v0.1 be compared with?+
The current compatible peer set includes Phi-4-reasoning, Molmo2-8B, Olmo-3-32B-Think, Olmo-3.1-32B-Instruct, and phi-4. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →
How current is the Model Markets record for Codestral-22B-v0.1?+
Codestral-22B-v0.1 was last verified Aug 28, 2026 from Mistral AI's primary source, “mistralai/Codestral-22B-v0.1 developer model repository.” The evidence is classified as official fact.
Primary evidence