Codestral 2508
Mistral AI
At a glance
- Price per 1M tokens (input)
- $0.30
- Price per 1M tokens (output)
- $0.90
- Context
- 256,000 tokens
- Free access
- yes (see below)
Refreshed daily; data verified August 15, 2026. Published August 12, 2026.
The Codestral 2508 model by Mistral AI is designed for developers and organizations seeking to streamline their workflow by leveraging tool calling, which refers to the ability of a model to invoke and utilize external functions or tools to perform specific tasks. This capability makes the model particularly suited for tasks that require interfacing with other systems or services. Mistral AI's approach distinguishes itself through a focus on seamless integration and flexibility, allowing users to adapt the model to their unique needs. By providing a robust and adaptable framework, the Codestral 2508 model enables users to automate and enhance a wide range of processes, from data processing to application development. This model's versatility and customizability make it an attractive choice for businesses looking to optimize their operations and improve efficiency.
Specifications & pricing
| Input (per 1M tokens) | $0.30 |
|---|---|
| Output (per 1M tokens) | $0.90 |
| Context window | 256,000 tokens |
| Max output | 256,000 tokens |
| Capabilities | tool calling |
LiteLLM community dataset (MIT), verified August 15, 2026. Official Mistral AI pricing.
What Codestral 2508 would cost on your workload — run it through the cost calculator →
Where to try Codestral 2508 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
What is the Codestral 2508 model good for?+
The Codestral 2508 model is well-suited for tasks that involve integrating with external tools or services, such as data processing, application development, and workflow automation. Its tool calling capability allows it to leverage the strengths of other systems to perform complex tasks efficiently.
How do I get started with the Codestral 2508 model?+
To get started, users should familiarize themselves with the model's capabilities and limitations, and then design a workflow that leverages its tool calling functionality. This may involve setting up interfaces with external tools or services, and configuring the model to invoke these tools as needed.
How does the Codestral 2508 model differ from other models in the line?+
The Codestral 2508 model differs from other models in the line through its focus on tool calling and workflow automation. While other models may excel in areas such as natural language processing or data analysis, the Codestral 2508 model is specifically designed to facilitate integration with external systems and services.
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.