Labs Leanstral 1.5
Mistral AI
At a glance
- Price per 1M tokens (input)
- free
- Price per 1M tokens (output)
- free
- Context
- 262,144 tokens
- Free access
- yes (see below)
Refreshed daily; data verified August 15, 2026. Published August 12, 2026.
Labs Leanstral 1.5 by Mistral AI is aimed at developers and enterprises that need a language model capable of invoking external functions directly. It excels at workflows where the model must retrieve up‑to‑date data, perform calculations, or interact with APIs without manual prompting. The model’s tool‑calling ability lets it generate structured calls that are executed by the surrounding system, reducing the need for custom parsing logic. Mistral’s approach emphasizes a lightweight architecture that keeps inference fast while preserving the flexibility to extend behavior through user‑defined tools.
Specifications & pricing
| Input (per 1M tokens) | free |
|---|---|
| Output (per 1M tokens) | free |
| Context window | 262,144 tokens |
| Max output | 131,072 tokens |
| Capabilities | tool calling |
LiteLLM community dataset (MIT), verified August 15, 2026. Official Mistral AI pricing.
What Labs Leanstral 1.5 would cost on your workload — run it through the cost calculator →
Where to try Labs Leanstral 1.5 for free
- Mistral AI offers a free chat — Le Chat (free plan). A vendor's free chat may run a different model from the same family — the exact model is not guaranteed.
Frequently asked questions
Which business scenarios get the most value from tool calling?+
Any process that relies on current information, such as price lookups, inventory checks, or dynamic report generation, benefits because the model can request the exact data it needs at runtime.
How do I start using Leanstral 1.5 with my applications?+
Begin by installing Mistral’s SDK, define the functions you want the model to call using the provided schema format, and then send prompts through the API endpoint; the model will return a structured call that your code can execute.
In what ways does Leanstral 1.5 differ from other models in the Leanstral family?+
Unlike the baseline variants that produce plain text, this version is trained to recognise when a function call is appropriate and to output a machine‑readable request, enabling tighter integration with external services.
What limitations should I be aware of when deploying this model?+
The model can only invoke functions that have been explicitly described in its schema, and ambiguous or overly complex requests may fall back to textual responses rather than a call.
Compare with others
Org chart: how to move your company onto AI
A practical map: which company roles and processes AI agents can take over, where to start, and in what order to roll it out.