Govern Mistral AI models¶
WSO2 API Platform works alongside Mistral AI. Govern traffic to Mistral models, and use Mistral embeddings for semantic caching and guardrails.
AI Gateway with Mistral models¶
Route, secure, and govern traffic to Mistral AI models through WSO2 AI Gateway.
Mistral as an LLM provider¶
Register the Mistral API with the gateway, which stores the API key on behalf of your applications.
OpenAI-format requests¶
Keep clients on the OpenAI request format while the gateway routes to Mistral.
Semantic caching and guardrails¶
Semantic caching and the semantic prompt guard compare prompts by meaning, and can use a Mistral embedding model that you set in the policy or gateway configuration.
Token limits, semantic caching, and the other AI API policies work the same way for every provider. See AI APIs.
Routing, token limits, cost control, and the other AI Workspace policies work the same way for every provider. See the AI Workspace overview.
Routing, token limits, cost control, and the gateway's other policies work the same way for every provider. See the AI Gateway documentation.
Architecture and responsibility model¶
WSO2 API Platform and Mistral AI split the work like this:
| Scenario | WSO2 role | Mistral role | Runtime traffic |
|---|---|---|---|
| Applications calling Mistral models | Proxies and governs LLM requests | Hosts the models | Goes through WSO2 AI Gateway to Mistral |
| Semantic caching and guardrails | Runs the cache or guardrail policy | Returns embeddings for each prompt | The gateway calls the Mistral embeddings API alongside each request |
Learn more¶
Related pages in the Mistral documentation:
To browse every guide by goal, see the Guides overview.