AI Gateway

The AI Gateway proxies language-model requests through the qBraid API using OpenAI and Anthropic request formats. To use it with your existing SDK, change the base URL and API key.

https://api-v2.qbraid.com/api/v1/ai

Every request authenticates with your qBraid API key in the X-API-Key header. Create a key at account.qbraid.com/account/api-keys. The API Keys guide explains how to manage and rotate keys.

Endpoints

Anthropic routes include /v1 because Anthropic SDKs append /v1/messages to whatever base URL you give them. The gateway matches that shape, so the same base URL works for both wire formats.

Quickstart

The Anthropic SDK sends the x-api-key header on its own, so its api_key argument takes your qBraid key directly. The OpenAI SDK only sends a bearer header, so give it the key through default_headers instead.

curl https://api-v2.qbraid.com/api/v1/ai/chat/completions \
  -H "X-API-Key: $QBRAID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "messages": [{ "role": "user", "content": "Explain the GHZ state in two sentences." }]
  }'

import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api-v2.qbraid.com/api/v1/ai",
    api_key="unused",  # the gateway reads X-API-Key below
    default_headers={"X-API-Key": os.environ["QBRAID_API_KEY"]},
)

response = client.chat.completions.create(
    model="gpt-5.5",
    messages=[{"role": "user", "content": "Explain the GHZ state in two sentences."}],
)
print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api-v2.qbraid.com/api/v1/ai",
  apiKey: "unused", // the gateway reads X-API-Key below
  defaultHeaders: { "X-API-Key": process.env.QBRAID_API_KEY },
});

const response = await client.chat.completions.create({
  model: "gpt-5.5",
  messages: [
    { role: "user", content: "Explain the GHZ state in two sentences." },
  ],
});
console.log(response.choices[0].message.content);

import os

from anthropic import Anthropic

client = Anthropic(
    base_url="https://api-v2.qbraid.com/api/v1/ai",
    api_key=os.environ["QBRAID_API_KEY"],  # the SDK sends this as x-api-key
)

response = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Explain the GHZ state in two sentences."}],
)
print(response.content[0].text)

Use with Claude Code

Claude Code uses the Anthropic request format, so it can use your qBraid quota. Set the base URL and your key, then start it:

export ANTHROPIC_BASE_URL="https://api-v2.qbraid.com/api/v1/ai"
export ANTHROPIC_API_KEY="$QBRAID_API_KEY"
claude

ANTHROPIC_API_KEY reaches the gateway as the x-api-key header.

Available models

Query /models for the current model catalog:

curl https://api-v2.qbraid.com/api/v1/ai/models \
  -H "X-API-Key: $QBRAID_API_KEY"

The response uses the OpenAI model-list format. Each entry includes its canonical id and qBraid metadata under _qbraid:

• name, description, and provider describe the model.
• aliases lists accepted alternative IDs.
• capabilities describes image input, structured outputs, and parallel tool-call control.
• supportedEndpoints lists the generation endpoints that accept the model.
• pricing.inputCreditsPerMillionTokens and pricing.outputCreditsPerMillionTokens give the token rates in qBraid credits.

Check supportedEndpoints before selecting a model for Chat Completions, Responses, or Anthropic Messages. Catalog discovery omits models without a callable generation endpoint. A missing pricing block does not mean a model is free.

By default, the catalog reflects the caller’s model-access policy. ?includeLocked=1 also returns plan-locked models with _qbraid.requiredTier when restrictions apply. All current plan tiers allow the catalog, but still have different usage allowances.

See Models and pricing for a dated rate reference that includes the GPT-6 family, GPT-6.1 Sol, Claude Opus 5.5, Claude Sonnet 5, and Claude Fable 5.1. Query the catalog for current IDs and rates before integrating a model.

Costs draw from your plan’s AI allowance first. Spending beyond that allowance requires the effective Auto-switch to Credits policy and sufficient credits. The standard conversion is 100 credits = $1. See AI usage quotas.

Check your quota

curl https://api-v2.qbraid.com/api/v1/ai/quota \
  -H "X-API-Key: $QBRAID_API_KEY"

The response contains your LLM subscription state and remaining quota. Streaming responses also carry standard rate-limit headers.