API reference

The gateway is an OpenAI-compatible HTTP API. Send requests to https://llms.party/v1 with an API key as a bearer token.

export LLMS_PARTY_KEY="sk-..."

Endpoints

Method	Path	Purpose
`GET`	`/v1/models`	List the model groups this key can call.
`GET`	`/v1/usage`	Budget, spend and model access for the calling key.
`POST`	`/v1/chat/completions`	Chat completions, with optional streaming and images.
`POST`	`/v1/videos`	Create a MiniMax H3 or BytePlus Seedance job.
`GET`	`/v1/videos/{id}`	Poll a video job.
`GET`	`/v1/videos/{id}/content`	Download the finished clip.
`GET`	`/health/liveness`	Process liveness probe.
`GET`	`/health/readiness`	Readiness probe, including database connectivity.

`GET /v1/models`

curl -sS "https://llms.party/v1/models" \
  -H "Authorization: Bearer $LLMS_PARTY_KEY"

const response = await fetch('https://llms.party/v1/models', {
  headers: { authorization: `Bearer ${process.env.LLMS_PARTY_KEY}` },
});
const { data } = await response.json();
console.log(data);

import os
import requests
 
response = requests.get(
    "https://llms.party/v1/models",
    headers={"Authorization": f"Bearer {os.environ['LLMS_PARTY_KEY']}"},
    timeout=30,
)
print(response.json()["data"])

{
  "data": [
    {
      "id": "deepseek-flash",
      "object": "model",
      "owned_by": "openai",
      "mode": "chat",
      "max_input_tokens": 1048576,
      "max_output_tokens": 393216
    }
  ]
}

The list depends on the key and deployment. A group missing from data is not available to that key. owned_by is LiteLLM's OpenAI-compatible placeholder; use id for routing and the models guide for the provider mapping.

`POST /v1/chat/completions`

curl -sS "https://llms.party/v1/chat/completions" \
  -H "Authorization: Bearer $LLMS_PARTY_KEY" \
  -H "content-type: application/json" \
  -d '{
    "model": "deepseek-flash",
    "messages": [
      { "role": "system", "content": "You are concise." },
      { "role": "user", "content": "What is an LLM gateway?" }
    ],
    "temperature": 0.7,
    "max_tokens": 1024
  }'

const response = await fetch('https://llms.party/v1/chat/completions', {
  method: 'POST',
  headers: {
    authorization: `Bearer ${process.env.LLMS_PARTY_KEY}`,
    'content-type': 'application/json',
  },
  body: JSON.stringify({
    model: 'deepseek-flash',
    messages: [
      { role: 'system', content: 'You are concise.' },
      { role: 'user', content: 'What is an LLM gateway?' },
    ],
    temperature: 0.7,
    max_tokens: 1024,
  }),
});
 
const completion = await response.json();
console.log(completion.choices[0]?.message.content);

import os
 
import requests
 
response = requests.post(
    "https://llms.party/v1/chat/completions",
    headers={"Authorization": f"Bearer {os.environ['LLMS_PARTY_KEY']}"},
    json={
        "model": "deepseek-flash",
        "messages": [
            {"role": "system", "content": "You are concise."},
            {"role": "user", "content": "What is an LLM gateway?"},
        ],
        "temperature": 0.7,
        "max_tokens": 1024,
    },
    timeout=300,
)
completion = response.json()
print(completion["choices"][0]["message"]["content"])

{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "model": "deepseek-flash",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "...",
        "reasoning_content": "..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 24,
    "completion_tokens": 61,
    "total_tokens": 85
  }
}

Set "stream": true to receive text/event-stream chunks ending in data: [DONE]. The model field echoes the group you requested. See Chat completions for streaming, vision and reasoning controls.

`POST /v1/videos`

curl -sS "https://llms.party/v1/videos" \
  -H "Authorization: Bearer $LLMS_PARTY_KEY" \
  -H "content-type: application/json" \
  -d '{
    "model": "minimax-h3",
    "prompt": "A glass city at sunset, slow aerial push-in.",
    "seconds": 4,
    "resolution": "768P",
    "ratio": "16:9"
  }'

const response = await fetch('https://llms.party/v1/videos', {
  method: 'POST',
  headers: {
    authorization: `Bearer ${process.env.LLMS_PARTY_KEY}`,
    'content-type': 'application/json',
  },
  body: JSON.stringify({
    model: 'minimax-h3',
    prompt: 'A glass city at sunset, slow aerial push-in.',
    seconds: 4,
    resolution: '768P',
    ratio: '16:9',
  }),
});
 
const job = await response.json();
console.log(job.id, job.status);

import os
 
import requests
 
response = requests.post(
    "https://llms.party/v1/videos",
    headers={"Authorization": f"Bearer {os.environ['LLMS_PARTY_KEY']}"},
    json={
        "model": "minimax-h3",
        "prompt": "A glass city at sunset, slow aerial push-in.",
        "seconds": 4,
        "resolution": "768P",
        "ratio": "16:9",
    },
    timeout=60,
)
job = response.json()
print(job["id"], job["status"])

{
  "id": "video_...",
  "object": "video",
  "model": "minimax-h3",
  "status": "queued",
  "progress": 0,
  "created_at": 1760000000
}

For Seedance, use "model": "seedance" with lowercase resolutions (480p, 720p, 1080p) and an optional input_reference image URL. See Video generation for the group-specific limits and pricing.

`GET /v1/videos/{id}`

curl -sS "https://llms.party/v1/videos/$VIDEO_ID" \
  -H "Authorization: Bearer $LLMS_PARTY_KEY"

const videoId = 'video_...';
 
const response = await fetch(`https://llms.party/v1/videos/${videoId}`, {
  headers: { authorization: `Bearer ${process.env.LLMS_PARTY_KEY}` },
});
console.log(await response.json());

import os
 
import requests
 
video_id = "video_..."
 
response = requests.get(
    f"https://llms.party/v1/videos/{video_id}",
    headers={"Authorization": f"Bearer {os.environ['LLMS_PARTY_KEY']}"},
    timeout=30,
)
print(response.json())

{
  "id": "video_...",
  "object": "video",
  "model": "minimax-h3",
  "status": "completed",
  "progress": 100,
  "created_at": 1760000000,
  "completed_at": 1760000060,
  "seconds": "4",
  "size": "1366x768"
}

Statuses are queued, in_progress, completed, failed and cancelled. Terminal states are completed, failed and cancelled.

`GET /v1/videos/{id}/content`

curl -sS "https://llms.party/v1/videos/$VIDEO_ID/content" \
  -H "Authorization: Bearer $LLMS_PARTY_KEY" \
  -o clip.mp4

import { writeFile } from 'node:fs/promises';
 
const videoId = 'video_...';
 
const response = await fetch(
  `https://llms.party/v1/videos/${videoId}/content`,
  { headers: { authorization: `Bearer ${process.env.LLMS_PARTY_KEY}` } },
);
const clip = Buffer.from(await response.arrayBuffer());
await writeFile('clip.mp4', clip);

import os
 
import requests
 
video_id = "video_..."
 
response = requests.get(
    f"https://llms.party/v1/videos/{video_id}/content",
    headers={"Authorization": f"Bearer {os.environ['LLMS_PARTY_KEY']}"},
    timeout=300,
)
with open("clip.mp4", "wb") as clip:
    clip.write(response.content)

The response is video/mp4. Range requests are supported; send a Range header to resume or slice a download. Task records are kept for 7 days.

Errors

Errors use the OpenAI error object:

{
  "error": {
    "message": "Invalid proxy server token passed.",
    "type": "auth_error",
    "code": "invalid_api_key"
  }
}

Status	Meaning
`401`	Missing, malformed or revoked key, or the key lacks this model group.
`422`	Validation failed, or the key is over budget.
`429`	Key or upstream rate limit.
`500`	Internal proxy error.
`502` / `503`	Upstream provider error or no healthy upstream.
`504`	Upstream timed out.

See Errors & limits for retries, budgets and fallback behaviour.