Agents
Use Voxvey as the model gateway for coding agents and editor assistants that accept Chat Completions, Responses, or Messages API endpoints.
Connection details
| Setting | Value |
|---|---|
| OpenAI-compatible base URL | https://api.voxvey.com/v1 |
| Messages base URL | https://api.voxvey.com |
| Chat completions endpoint | https://api.voxvey.com/v1/chat/completions |
| Responses endpoint | https://api.voxvey.com/v1/responses |
| Messages endpoint | https://api.voxvey.com/v1/messages |
| Auth | Bearer token |
| Token env var | VOXVEY_TOKEN |
Set your token before configuring a local agent:
export VOXVEY_TOKEN="<access-token>"
Recommended model IDs
Use the model ID that matches the API surface your client calls.
| Client surface | Model ID |
|---|---|
| Chat Completions | deepseek/deepseek-v4-flash |
| Responses | openai/gpt-5.5 |
| Messages | Use the model ID returned by /v1/models for the Messages API. |
Setup pages
| Client | Use when |
|---|---|
| Voxvey OpenClaw Plugin | You want OAuth sign-in, live model discovery, and the packaged Voxvey provider. |
| OpenClaw | You want a custom provider in OpenClaw config. |
| Hermes | You want Hermes to use Voxvey as the main model endpoint. |
| Claude Code | You want Claude Code to use Voxvey's Messages API route. |
| Codex | You want Codex to use Voxvey's Responses-compatible route. |
| VS Code | You want Copilot Chat BYOK Custom Endpoint setup. |
| Zed | You want Zed Agent or Inline Assistant through an OpenAI-compatible provider. |
Verify the gateway
Before debugging an editor or agent, verify the token and model directly.
curl https://api.voxvey.com/v1/chat/completions \
-H "Authorization: Bearer $VOXVEY_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek/deepseek-v4-flash",
"messages": [
{"role": "user", "content": "Reply with: ready"}
],
"stream": false
}'
Expected response shape:
{
"id": "chatcmpl_...",
"object": "chat.completion",
"choices": [
{
"message": {
"role": "assistant",
"content": "ready"
}
}
],
"usage": {
"prompt_tokens": 12,
"completion_tokens": 1,
"total_tokens": 13
}
}