List available Mistral AI models via pay-per-call MPP endpoint on Tempo L2.
What it does
This endpoint returns the list of available Mistral AI models accessible through the Locus MPP (Micropayment Protocol) gateway. It is part of a broader Mistral AI service suite hosted at mistral.mpp.paywithlocus.com that also includes chat completion, embeddings, and content moderation endpoints.
The `/mistral/models` endpoint accepts POST requests and charges $0.005 per call (5,000 base units of pathUSD with 6 decimals), settled via the Tempo L2 method. The endpoint uses the MPP charge intent, meaning each call is a one-shot payment. No request body is documented for this endpoint — it simply enumerates the models available for use across the sibling endpoints (e.g., mistral-large-latest, codestral-latest, mistral-embed, mistral-moderation-latest).
Note that the probe did not capture a live 402 challenge on HEAD or GET — the endpoint returned 404 on those methods. Since the OpenAPI spec defines this as a POST endpoint, the 404 on HEAD/GET is expected behavior for a method-restricted route. The endpoint is likely live when called with POST. Documentation is sparse: the crawled pages all return generic "not found" JSON, and the OpenAPI spec provides no response schema for this endpoint. Refer to the official Mistral AI docs at https://docs.mistral.ai and the Locus MPP docs at https://beta.paywithlocus.com/mpp/mistral.md for further details.
Capabilities
Use cases
- —Discovering which Mistral AI models are available before making chat or embedding calls
- —Building dynamic model selectors in agent workflows
- —Validating model IDs programmatically before submitting inference requests
Fit
Best for
- —Agents that need to enumerate available Mistral models at runtime
- —Workflows that dynamically select models based on availability
- —Developers exploring the Mistral model catalog via micropayments
Not for
- —Running inference or generating text (use the /mistral/chat endpoint instead)
- —Free or unauthenticated model discovery (every call costs $0.005)
Quick start
curl -X POST https://mistral.mpp.paywithlocus.com/mistral/models \
-H "Content-Type: application/json" \
-H "Authorization: <MPP-Tempo-payment-header>"Endpoint
Quality
The OpenAPI spec provides basic metadata and pricing, but the endpoint returned 404 on HEAD/GET (expected for POST-only routes). No response schema, no example responses, and all crawled pages returned generic 404 JSON. Liveness via POST is plausible but unconfirmed by the probe.
Warnings
- —Probe returned 404 on HEAD and GET; endpoint is POST-only per OpenAPI spec but live 402 challenge was not captured
- —No response schema documented — the structure of the model list is unknown
- —All crawled documentation pages returned generic 'not found' errors; external docs at docs.mistral.ai and beta.paywithlocus.com were not crawled
- —Currency address 0x20c000000000000000000000b9537d11c60e8b50 assumed to be pathUSD (6 decimals) based on sibling endpoint descriptions
Citations
- —The /mistral/models endpoint charges 5000 base units via Tempo L2 charge intenthttps://mistral.mpp.paywithlocus.com
- —Sibling endpoints include chat completion ($0.005–$0.10), embeddings (8000 units), and moderation (8000 units)https://mistral.mpp.paywithlocus.com
- —Official API reference is at docs.mistral.ai; MPP-specific docs at beta.paywithlocus.com/mpp/mistral.mdhttps://mistral.mpp.paywithlocus.com