Introduction

Telluvian is an OpenAI-compatible API with two products on one endpoint. Routing picks which model answers each request. Verification can score every token it returns for hallucination, when you turn it on. Use either, or both.

The API is OpenAI-compatible. If you can call OpenAI, you can call this. Change the base URL and the key.

https://api.telluvian.ai/v1

Routing

Model choice is usually made once and left alone, which means a frontier model answers your cheap requests and a small model answers your hard ones.

Gallery is our router, and you call it like a model. Send telluvian/gallery-1 and each request goes to the cheapest model that we expect clears the quality bar you set. The response reports which model ran. See Gallery.

Model Select is the engine behind it. It reads each prompt and predicts how well every candidate model will handle it. You can also call it directly with /v1/modelSelect to get the decision and make the model call yourself. See Model Select.

You control the quality bar and the allowed models. xLatency is currently accepted but ignored. Billing follows the chosen model's own rates, plus a $0.05 per 1M input-token Model Select fee.

Verification

When enabled, verification returns per-token scores indicating potentially unsupported text. These are not calibrated probabilities; readings can be missing. Not one number for the whole response: one score per generated token, so you can point at the specific claim that looks wrong.

Externally generated text is replayed through our probe model on our GPUs; locally served models can be scored from their own forward pass. The probe uses those hidden states to score tokens. Scores arrive per chunk when streaming, or as arrays on the completed response. Verification is off by default; enable it per request with include_scores: true. See Reading the scores.

Set up with a coding agent

Copy this prompt into your coding agent and it will make the integration in your project, following our agent guide.

Set up Telluvian routing in this project.

1. Read https://telluvian.ai/docs/agents/routing.md before changing anything.
2. Find where this project calls an LLM (OpenAI SDK or compatible).
3. Point it at https://api.telluvian.ai/v1 with model "telluvian/gallery-1".
4. Read the key from TELLUVIAN_API_KEY. Add it to .env.example; never hard-code it.
   If I don't have a key yet, tell me to create one at https://telluvian.ai/dashboard/keys.
5. Log the response's `model` field so I can see which model answered.
6. Make one test request and show me the result. Ask before changing production defaults.

Next steps