List available Groq LLM models via MPP micropayment on Tempo L2
What it does
This endpoint returns the catalog of models available through the Groq inference service, proxied via the Locus MPP (Micropayment Protocol) gateway. It is part of a broader Groq integration that also offers chat completions across models like Llama 3.3, DeepSeek R1, Gemma 2, Qwen, Whisper, and PlayAI TTS.
The `/groq/models` endpoint is a POST request that costs 5,000 base units of pathUSD (0x20c…b9537d11c60e8b50) on Tempo L2. Since pathUSD uses 6 decimals, this translates to $0.005 per call. The payment intent is "charge", meaning each request is a one-shot micropayment settled on Tempo. The endpoint returns a list of model IDs and metadata that can then be used with the companion `/groq/chat` chat-completion endpoint.
Note that the probe did not receive a 402 challenge when hitting this endpoint with HEAD or GET — the endpoint is POST-only, which is consistent with the OpenAPI spec declaring it under the POST method. The root domain returns 404 by design, directing callers to the skill file and llms.txt for routing information. Documentation is available at the Groq console docs and the Locus MPP skill file.
Capabilities
Use cases
- —Discovering which Groq-hosted models are available before making a chat completion call
- —Building model-selection UIs or agent logic that dynamically picks the best model
- —Validating model IDs programmatically before submitting inference requests
Fit
Best for
- —AI agents that need to enumerate available LLM models before inference
- —Developers integrating Groq via micropayment without API keys
- —Workflows that dynamically select models based on availability
Not for
- —Running actual LLM inference (use the /groq/chat endpoint instead)
- —Free or unauthenticated model discovery — each call costs $0.005
- —Non-Tempo payment rails — this endpoint requires Tempo L2 settlement
Quick start
curl -X POST https://groq.mpp.paywithlocus.com/groq/models \
-H "Content-Type: application/json" \
-H "Authorization: Bearer <TEMPO_PAYMENT_TOKEN>"Endpoint
Quality
The OpenAPI spec provides clear path, method, pricing, and payment metadata, but the probe did not capture a live 402 challenge (endpoint is POST-only and was probed with HEAD/GET). No response schema or example response is documented. Crawled pages all return 404 with no additional documentation content.
Warnings
- —Probe returned 404 on HEAD and GET; endpoint is POST-only per the OpenAPI spec — likely live but not confirmed with a POST probe
- —No response schema or example response is provided in the OpenAPI spec
- —No detailed documentation was retrievable from the crawled pages; external docs at console.groq.com/docs and paywithlocus.com/skill.md were not crawled
Citations
- —The /groq/models endpoint is a POST with amount 5000 in pathUSD on Tempo L2 with intent 'charge'https://groq.mpp.paywithlocus.com
- —pathUSD currency address is 0x20c000000000000000000000b9537d11c60e8b50https://groq.mpp.paywithlocus.com
- —Groq service supports Llama 3.3, DeepSeek R1, Gemma 2, Qwen, Whisper, and PlayAI TTShttps://groq.mpp.paywithlocus.com
- —API reference documentation is at https://console.groq.com/docshttps://groq.mpp.paywithlocus.com
- —Locus MPP documentation is at https://beta.paywithlocus.com/mpp/groq.mdhttps://groq.mpp.paywithlocus.com