Quickstart and API Authentication

Send compatible chat requests to:

https://tokenra.io/v1/chat/completions

Keep your API key on the server. Model availability and billing depend on the channels enabled for your account.

Use a Bearer token in the Authorization header.

curl https://tokenra.io/v1/chat/completions   -H "Authorization: Bearer YOUR_API_KEY"   -H "Content-Type: application/json"

curl -X POST https://tokenra.io/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-5-3-flash",
    "messages": [
      {"role": "user", "content": "Hello"}
    ],
    "temperature": 1,
    "top_p": 0.95,
    "max_tokens": 1024
  }'

Use the exact model identifier shown in the model directory. Preserve tool calls, reasoning content, and message history when continuing a multi-step workflow.

Video models may use asynchronous task endpoints. Confirm the enabled route and request schema in the relevant model guide before sending production traffic.

curl https://tokenra.io/v1/video/generations   -H "Authorization: Bearer YOUR_API_KEY"   -H "Content-Type: application/json"   -d '{"model":"YOUR_ENABLED_VIDEO_MODEL","prompt":"A cinematic scene"}'

• Use separate keys and budgets for each environment.
• Set timeouts, bounded retries, request tracing, and application limits.
• Validate model output and tool arguments before executing side effects.
• Monitor token usage, latency, error rates, and account quota.
• Review provider terms and data handling before sending sensitive information.