Models

The live catalog of models. Always dynamic — we don't keep a static list in these docs because it drifts the moment we add a model.

Auth: Bearer token or x-api-key. Requires scope inference.models. Responses are cached for 5 minutes — safe to poll.

List models

GET /v1/models

Returns every model available to your key's plan. Add ?include_meta=true for Melious-specific capability metadata.

curl https://api.melious.ai/v1/models \
  -H "Authorization: Bearer sk-mel-<YOUR_API_KEY>"

{
  "object": "list",
  "data": [
    { "id": "glm-4.7", "object": "model", "created": 1699999999, "owned_by": "zai" },
    { "id": "deepseek-v3.2", "object": "model", "created": 1699999999, "owned_by": "deepseek" }
  ]
}

curl "https://api.melious.ai/v1/models?include_meta=true" \
  -H "Authorization: Bearer sk-mel-<YOUR_API_KEY>"

{
  "object": "list",
  "data": [
    {
      "id": "glm-4.7",
      "object": "model",
      "created": 1699999999,
      "owned_by": "zai",
      "_meta": {
        "type": "chat",
        "input_modalities": ["text"],
        "output_modalities": ["text"],
        "capabilities": {
          "streaming": true,
          "function_calling": true,
          "vision": false,
          "structured_output": true,
          "json_schema": true,
          "reasoning": false
        },
        "context_length": 131072
      }
    }
  ]
}

`_meta.type`

One of chat, embeddings, audio, image, rerank. Tells you which endpoint to hit.

Boolean flags you can branch on when picking a model programmatically. Common keys: streaming, function_calling, vision, structured_output, json_schema, audio_input, reasoning. Absence of a key means "not applicable" for that model type (e.g. embedding models don't have vision).

`_meta.context_length`

Max context tokens for chat and embedding models. Absent for image/audio models. Exceeding it returns INFERENCE_3207.

Retrieve one model

GET /v1/models/{id}

Returns a single model object in the same shape. include_meta=true works here too.

curl "https://api.melious.ai/v1/models/glm-4.7?include_meta=true" \
  -H "Authorization: Bearer sk-mel-<YOUR_API_KEY>"

Finding models programmatically

A common pattern: filter on capabilities before picking.

from openai import OpenAI

client = OpenAI(api_key="sk-mel-<YOUR_API_KEY>", base_url="https://api.melious.ai/v1")

# OpenAI SDK doesn't expose ?include_meta, so hit the raw endpoint
import httpx
models = httpx.get(
    "https://api.melious.ai/v1/models",
    params={"include_meta": "true"},
    headers={"Authorization": "Bearer sk-mel-<YOUR_API_KEY>"},
).json()

# Pick the largest-context chat model that supports tools
candidates = [
    m for m in models["data"]
    if m["_meta"]["type"] == "chat"
    and m["_meta"]["capabilities"].get("function_calling")
]
best = max(candidates, key=lambda m: m["_meta"]["context_length"])
print(best["id"], best["_meta"]["context_length"])

Plan benefits affect what shows up. If your key's plan doesn't include advanced models, they won't appear in the list — no need to filter them out on your side.

What's not here

Pricing isn't in this response. Rates live on melious.ai/pricing and the hub. Every inference response includes the exact cost in billing_cost — that's the authoritative per-request figure.

Errors

INFERENCE_3001 — unknown model ID on the single-retrieve endpoint.
AUTH_1015 — missing inference.models scope.

Human-readable catalog: melious.ai/hub • Model stance and families: Models concept • Routing by capability: Routing.