Models - Mirobody

Endpoint

GET /v1/models

Lists the capability tiers you can pass as model to the Answers API and the Agent API. OpenAI-compatible shape.

Public — the model catalog is a static capability list (no tenant data), so this endpoint needs no API key. An Authorization header, if sent (the OpenAI SDKs always attach one), is simply ignored. Every other /v1 endpoint requires Authorization: Bearer mb_live_*.

Tiers

`model`	Tier	Use case
`mirobody-flash`	Default — fast, low cost	Everyday health Q&A, high concurrency
`mirobody-expert`	Deeper reasoning	Complex report interpretation, multi-step analysis

Billing is metered per actual (provider-true) token usage — the console’s Usage page and each response’s usage.billed_tokens are the source of truth for consumption and cost. Self-hosting (SDK / open source) is free software; you pay only for your own infrastructure and LLM keys.

Per-tier metadata

Each entry carries a conservative capacity budget and the per-tier price:

Field	Meaning
`context_window`	Total tokens (input + output) a request may use. A conservative lower bound — budget against it and you’re always safe.
`max_output_tokens`	Upper bound on generated tokens per response. Also a conservative floor.
`pricing`	`{input_per_1m_tokens, output_per_1m_tokens, currency}` — price per 1M tokens, applied to `usage.billed_tokens`. Numbers only; the backing provider/model id is not exposed.

Example

# no API key needed
curl https://mirobody-api.thetahealth.ai/v1/models

from openai import OpenAI

# api_key is unused by /v1/models but the SDK requires the field to be set
client = OpenAI(api_key="unused", base_url="https://mirobody-api.thetahealth.ai/v1")
for m in client.models.list().data:
    print(m.id)

Response

An OpenAI-style { "object": "list", "data": [ … ] } — each tier extends the standard model object with context_window, max_output_tokens, and pricing:

{
  "object": "list",
  "data": [
    { "id": "mirobody-flash", "object": "model", "owned_by": "mirobody",
      "context_window": 65536, "max_output_tokens": 8192,
      "pricing": { "input_per_1m_tokens": 0.75, "output_per_1m_tokens": 4.50, "currency": "USD" } },
    { "id": "mirobody-expert", "object": "model", "owned_by": "mirobody",
      "context_window": 65536, "max_output_tokens": 8192,
      "pricing": { "input_per_1m_tokens": 5.0, "output_per_1m_tokens": 25.0, "currency": "USD" } }
  ]
}

The values above are from the global cluster (mirobody-api.thetahealth.ai). The China cluster (mirobody-api.thetahealth.cn) exposes the same fields, but its tiers are priced differently — always read pricing from the cluster you call rather than hard-coding numbers.

For your model value, always pass a stable tier — mirobody-flash (default) or mirobody-expert.

​Endpoint

​Tiers

​Per-tier metadata

​Example

​Response

Endpoint

Tiers

Per-tier metadata

Example

Response