Chat completions

Generate responses from any model.

POST https://tokenroute.app/api/v1/chat/completions - fully compatible with the OpenAI Chat Completions API.

bash

curl https://tokenroute.app/api/v1/chat/completions \
  -H "Authorization: Bearer $TOKENROUTE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-4.6",
    "messages": [{ "role": "user", "content": "Hello!" }]
  }'

Response

The response includes the assistant message and a usage object with token counts and the cost charged to your balance.

json

{
  "id": "gen-...",
  "model": "anthropic/claude-sonnet-4.6",
  "choices": [{ "message": { "role": "assistant", "content": "Hi!" }, "finish_reason": "stop" }],
  "usage": { "prompt_tokens": 9, "completion_tokens": 3, "total_tokens": 12, "cost": 0.00004 }
}