Choosing Models

Qubax provides access to 250+ models from leading providers through a single OpenAI-compatible API. This page explains how to discover available models, understand their IDs, and select the right one for your use case.

Listing Available Models

Every model you have access to can be fetched with a simple GET request to the /v1/models endpoint. The response is an OpenAI-compatible list of model objects.

curl https://api.qubax.ai/v1/models   -H "Authorization: Bearer $QUBAX_API_KEY"

The response is a JSON list where each entry includes the model id and its owning provider:

{
  "object": "list",
  "data": [
    {
      "id": "gpt-5.5",
      "object": "model",
      "created": 1719792000,
      "owned_by": "openai"
    },
    {
      "id": "claude-opus-4.8",
      "object": "model",
      "created": 1719792000,
      "owned_by": "anthropic"
    },
    {
      "id": "glm-5.2",
      "object": "model",
      "created": 1719792000,
      "owned_by": "zhipu"
    }
  ]
}

In Python, the same call works through the OpenAI SDK pointed at the Qubax base URL:

from openai import OpenAI

client = OpenAI(
    api_key=os.environ["QUBAX_API_KEY"],
    base_url="https://api.qubax.ai/v1",
)

models = client.models.list()
for m in models.data:
    print(m.id, "-", m.owned_by)

Model ID Format

Qubax uses human-readable slugs as model IDs rather than opaque version strings. Slugs follow a family-version pattern that makes them easy to recognize and remember:

• gpt-5.5 — OpenAI’s GPT family, version 5.5
• claude-opus-4.8 — Anthropic’s Claude Opus, version 4.8
• gemini-3.5-flash — Google’s Gemini 3.5 Flash
• glm-5.2 — Zhipu’s GLM, version 5.2
• kimi-k2.7 — Moonshot’s Kimi, version 2.7

How to Pick a Model

With 250+ models available, the best choice depends on what you are optimizing for. Consider these three dimensions:

By Provider

If your organization has a preferred provider or existing relationships, filter by owned_by. The major provider families are OpenAI (gpt-*), Anthropic (claude-*), Google (gemini-*), Zhipu (glm-*), and Moonshot (kimi-*).

By Price

For high-volume workloads, choose a smaller, lower-cost model. Flash and mini variants are optimized for throughput and cost per token. For example,gemini-3.5-flash is significantly cheaper than its Pro sibling while still handling most general tasks well.

By Capability

Match the model’s strengths to your task: frontier models likeclaude-opus-4.8 and gpt-5.5 excel at complex reasoning, coding, and long-context analysis, while specialized models may be better tuned for vision, tool use, or multilingual work.

Popular Models

The table below lists some of the most commonly used models and their IDs. This is a small sample — call /v1/models for the complete, up-to-date list.

Using a Model

Pass the model ID in the model field of any chat completion request. The same field works across streaming and non-streaming calls.

from openai import OpenAI

client = OpenAI(
    api_key=os.environ["QUBAX_API_KEY"],
    base_url="https://api.qubax.ai/v1",
)

response = client.chat.completions.create(
    model="claude-opus-4.8",
    messages=[
        {"role": "user", "content": "Explain transformers in one sentence."}
    ],
)

print(response.choices[0].message.content)

Switching models is as simple as changing the slug — no other code changes are required:

curl https://api.qubax.ai/v1/chat/completions   -H "Authorization: Bearer $QUBAX_API_KEY"   -H "Content-Type: application/json"   -d '{
    "model": "gpt-5.5",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'