API Reference
Chat Completions
Создает chat completion запрос к LLM-модели.
Совместим с OpenAI Chat Completions API — можно использовать любой OpenAI SDK,
указав base_url: "https://api.zveno.ai/v1".
Поддерживает:
- Обычный и streaming (
stream: true) режимы - Function calling / tool use
- Vision (изображения в сообщениях)
- Structured output (JSON schema, grammar)
- Reasoning (extended thinking)
- Мульти-модельный fallback (
models: [...]) - Настройки выбора провайдера (
provider)
Модель указывается в формате vendor/model (например, openai/gpt-4o, anthropic/claude-sonnet-4-20250514).
Аутентификация: Authorization: Bearer <api-key>.
Authorization
BearerAuth AuthorizationBearer <token>
In: header
Request Body
application/json
TypeScript Definitions
Use the request body type in TypeScript.
Response Body
application/json
application/json
application/json
application/json
application/json
application/json
application/json
application/json
curl -X POST "http://localhost:8080/v1/chat/completions" \ -H "Content-Type: application/json" \ -d '{}'{
"choices": [
{
"finish_reason": "string",
"native_finish_reason": "string",
"index": 0,
"logprobs": {
"content": [
{
"bytes": [
0
],
"logprob": 0.1,
"token": "string"
}
],
"refusal": [
{
"bytes": [
0
],
"logprob": 0.1,
"token": "string"
}
]
},
"message": {
"annotations": [
null
],
"content": [
{
"image_url": {
"detail": "string",
"url": "string"
},
"input_audio": {
"data": "string",
"format": "string"
},
"text": "string",
"type": "string"
}
],
"name": "string",
"reasoning": "string",
"reasoning_content": "string",
"reasoning_details": [
{
"data": "string",
"format": "string",
"id": "string",
"index": 0,
"signature": "string",
"summary": "string",
"text": "string",
"type": "string"
}
],
"refusal": "string",
"role": "string",
"tool_call_id": "string",
"tool_calls": [
{
"function": {
"arguments": "string",
"name": "string",
"thought_signature": "string"
},
"id": "string",
"index": 0,
"type": "string"
}
],
"images": [
{
"detail": "string",
"url": "string"
}
]
}
}
],
"created": 0,
"id": "string",
"model": "string",
"object": "string",
"system_fingerprint": "string",
"usage": {
"completion_tokens": 0,
"prompt_tokens": 0,
"total_tokens": 0
}
}{
"error": {
"code": 0,
"message": "string",
"metadata": {
"property1": null,
"property2": null
}
}
}{
"error": {
"code": 0,
"message": "string",
"metadata": {
"property1": null,
"property2": null
}
}
}{
"error": {
"code": 0,
"message": "string",
"metadata": {
"property1": null,
"property2": null
}
}
}{
"error": {
"code": 0,
"message": "string",
"metadata": {
"property1": null,
"property2": null
}
}
}{
"error": {
"code": 0,
"message": "string",
"metadata": {
"property1": null,
"property2": null
}
}
}{
"error": {
"code": 0,
"message": "string",
"metadata": {
"property1": null,
"property2": null
}
}
}{
"error": {
"code": 0,
"message": "string",
"metadata": {
"property1": null,
"property2": null
}
}
}{
"error": {
"code": 0,
"message": "string",
"metadata": {
"property1": null,
"property2": null
}
}
}