Leanstral 1.5
RetiredA Mistral AI model with a 256K-token context window, image input and tool calling. Released on the Mistral API July 2, 2026, now retired.
Access details: Mistral API
The model ID to use in API requests.
labs-leanstral-1-5Updated Sep 23, 2026
Capabilities & limits
- Context window
- 256K
- Maximum output
- 128K
- Image input
- Supported
- Tool calling
- Supported
- Structured output
- Supported
Pricing
USD / 1M tokens- Input
- No longer sold
- Output
- No longer sold
Standard rates per million tokens. Discounts and long-context rates, where offered, are on Mistral AI's pricing page.
Full rate card 3 rates
All prices in USD.
Standard input
$0.00 per 1M tokensCached input
$0.00 per 1M tokensStandard output
$0.00 per 1M tokensThe pricing page lists Input, Cached input and Output as Free; the lifecycle policy says Labs models are free of charge.
Price history
Sep 30, 2026
Input No longer sold per million tokens
Sep 30, 2026
Output No longer sold per million tokens
Technical details
- Parameters
- 119B
- Active parameters
- 6.5B
- Architecture
- Mixture of Experts (128 experts, 4 active per token)
- Training / knowledge cutoff
- Not published
- Input modalities
- Text, image
- Output modalities
- Text
From Mistral AI
Official announcement ↗Release & lifecycle
- First available
- Jul 2, 2026
- preview
- As of Sep 13, 2026
- deprecated
- As of Sep 23, 2026
- retired
- As of Oct 20, 2026