Store the key safely
Use AIWAVE_API_KEY in the environment. Never paste it into browser code or source control.
One key. One verified request to begin.
Create a key, choose one verified model ID, send one representative request, and keep the response shape and charge evidence together.
The first request has four checks.
This launch set uses the OpenAI-compatible route and three verified text-model IDs.
Use the verified route
Set https://aiwave.live/v1 and send the request to /v1/chat/completions.
Pin the exact model ID
Choose deepseek-v4-pro, glm-5.1, or kimi-k3 and keep it in the acceptance note.
Save response and charge evidence
Record status, usage, request ID when available, effective group, and charge before scaling traffic.
The key is shared. The request contract is not.
Use the protocol that belongs to the selected family. This prevents a model ID from being sent to a path that returns a misleading 404 or an unreadable response envelope.
Route matrix checked 2026-09-10| Family | Route | Protocol | Boundary |
|---|---|---|---|
| GPT | /v1/chat/completions | OpenAI-compatible | Route facts recorded; public price pending |
| Chinese models | /v1/chat/completions | OpenAI-compatible | Public rate card available |
| Claude | /v1/messages | Anthropic native | Native route; compatible path is model-dependent |
| Gemini | /v1beta/models/{id}:generateContent | Gemini native | Native route; image IDs do not use /v1/images/generations |
| Image routes | /v1/images/generations or provider-native | Route-specific | Check the model-family contract before sending media |
See Models for exact IDs and Request Recovery when the route and model do not agree.
Copy a verified launch example.
Use one model first. The route matrix above is discovery context, not a substitute for a verified model and published rate.
DeepSeek V4 Pro
curl "https://aiwave.live/v1/chat/completions" \
+ -H "Authorization: Bearer $AIWAVE_API_KEY" \
+ -H "Content-Type: application/json" \
+ -d '{"model":"deepseek-v4-pro","messages":[{"role":"user","content":"Reply with one sentence."}]}'GLM 5.1
curl "https://aiwave.live/v1/chat/completions" \
+ -H "Authorization: Bearer $AIWAVE_API_KEY" \
+ -H "Content-Type: application/json" \
+ -d '{"model":"glm-5.1","messages":[{"role":"user","content":"Reply with one sentence."}]}'Kimi K3
curl "https://aiwave.live/v1/chat/completions" \
+ -H "Authorization: Bearer $AIWAVE_API_KEY" \
+ -H "Content-Type: application/json" \
+ -d '{"model":"kimi-k3","messages":[{"role":"user","content":"Reply with one sentence."}]}'Route boundary.
Claude, Gemini, image, audio, and video routes remain visible for discovery only. Do not turn a route fact into an agent configuration until its public verification and billing facts are complete.
Claude, Gemini, image, audio, and video routes remain visible for discovery only. Do not turn a route fact into an agent configuration until its public verification and billing facts are complete.
Bring your agent
Keep the agent. Change the model route.
OpenClaw, WorkBuddy, and a custom agent can use the same AIWave key and USD balance. Start with an OpenAI-compatible model and exact model ID, then use the native route when the model family requires it.