# LemonData API

> One API for All AI Models - Access 365+ AI models through a unified OpenAI-compatible API

## Agent Quick Reference

Common model IDs (use these exact strings in API calls):
- speech-2.5-turbo-preview-voice-clone
- grok-4-image
- qwen-image-plus
- qwen-image-lora
- speech-2.5-hd-preview
- higgsfield-standard
- flux-kontext-max
- grok-video-3-10s
- mistral-small
- qwen-image

Available endpoints:
- POST /v1/chat/completions — Text generation (OpenAI format)
- POST /v1/messages — Claude messages (Anthropic format)
- POST /v1/responses — Responses API (OpenAI format)
- POST /v1/embeddings — Text embeddings
- POST /v1/images/generations — Image generation
- POST /v1/audio/speech — Text-to-speech
- POST /v1/audio/transcriptions — Speech-to-text
- POST /v1/videos/generations — Video generation
- POST /v1/music/generations — Music generation
- POST /v1/3d/generations — 3D generation
- POST /v1/rerank — Reranking
- GET /v1/models — List all models (supports ?category= and ?provider= filters)

## Agent-First Error Handling

Error responses include structured hints so agents can self-correct:

| Field | Type | When |
|-------|------|------|
| did_you_mean | string | model_not_found — closest valid model ID |
| suggestions | array | model_not_found — top models in same category |
| hint | string | Always — human-readable recovery instruction |
| retry_after | number | rate_limit / model_unavailable — seconds to wait |
| retryable | boolean | Whether retrying the same request may succeed |
| balance_usd | number | insufficient_balance — current balance |
| estimated_cost_usd | number | insufficient_balance — estimated request cost |
| alternatives | array | model_unavailable — other models in same family |

### Recommended Agent Workflow

1. Try the request directly
2. On error, read the structured hints from the error response
3. If did_you_mean is present, retry with the corrected model
4. If retryable is true, wait retry_after seconds and retry
5. If suggestions/alternatives are present, try one of those

## Overview

LemonData is an AI API aggregation platform providing unified access to models from OpenAI, Anthropic, Google, xAI, DeepSeek, and more. Save 30% compared to official pricing.

## Base URL

```
https://api.lemondata.cc
```

## Authentication

All API requests require an API key in the Authorization header:

```
Authorization: Bearer YOUR_API_KEY
```

Get your API key at: https://lemondata.cc/dashboard/organizations

## Core Endpoints

### Chat Completions (OpenAI Format)
```
POST /v1/chat/completions
```
OpenAI-compatible chat completions with streaming support.

### Claude Messages (Anthropic Format)
```
POST /messages
```
Anthropic-native Messages API for Claude models.

### Responses API (OpenAI Format)
```
POST /v1/responses
```
OpenAI Responses API with built-in tool support.

### Embeddings
```
POST /v1/embeddings
```
Text embeddings for semantic search and RAG applications.

### Image Generation
```
POST /v1/images/generations
```
Generate images using DALL-E, Midjourney, Flux, and more.

### Video Generation
```
POST /v1/videos/generations
POST /v1/videos/generations/{id}
```
Generate videos using Sora, Kling, Veo, and more.

### Audio
```
POST /v1/audio/speech
POST /v1/audio/transcriptions
```
Text-to-speech and speech-to-text capabilities.

### Music Generation
```
POST /v1/music/generations
POST /v1/music/generations/{id}
```
Generate music with AI.

### 3D Generation
```
POST /v1/3d/generations
POST /v1/3d/generations/{id}
```
Generate 3D models with AI.

### Reranking
```
POST /v1/rerank
```
Rerank documents for improved search relevance.

## Supported Models

### Text Models (179 models)
- bce-reranker-base-v1
- claude-haiku-4-5
- claude-haiku-4-5-thinking
- claude-opus-4-5
- claude-opus-4-5-thinking
- claude-opus-4-6
- claude-opus-4-6-thinking
- claude-sonnet-4
- claude-sonnet-4-5
- claude-sonnet-4-5-thinking
- claude-sonnet-4-6
- claude-sonnet-4-6-thinking
- claude-sonnet-4-thinking
- deepseek-chat
- deepseek-ocr
- deepseek-r1
- deepseek-r1-distill-qwen-32b
- deepseek-r1-distill-qwen-7b
- deepseek-r1-searching
- deepseek-reasoner
- deepseek-v3-2
- deepseek-v3-2-exp
- deepseek-v3-2-exp-thinking
- deepseek-v3-2-fast
- deepseek-v3-2-thinking
- deepseek-v3-fast
- dolphin3.0-r1-mistral-24b
- doubao-1-5-vision-pro-32k
- doubao-1.5-lite-32k
- doubao-1.5-pro-32k
- doubao-1.5-thinking-pro
- doubao-1.5-thinking-vision-pro
- doubao-1.5-vision-pro
- doubao-embedding-vision
- doubao-seed-1-6
- doubao-seed-1-8-thinking
- doubao-seed-1.6
- doubao-seed-1.6-flash
- doubao-seed-1.6-lite
- doubao-seed-1.6-thinking
- doubao-seed-1.6-vision
- doubao-seed-1.8
- doubao-seed-code
- doubao-seed-translation
- flux-1-schnell
- gemini-2.5-flash
- gemini-2.5-flash-lite
- gemini-2.5-flash-lite-nothinking
- gemini-2.5-flash-lite-preview
- gemini-2.5-flash-lite-thinking
- gemini-2.5-flash-nothinking
- gemini-2.5-flash-preview
- gemini-2.5-flash-thinking
- gemini-2.5-pro
- gemini-2.5-pro-thinking
- gemini-3-flash-preview
- gemini-3-flash-preview-thinking
- gemini-3-pro-preview
- gemini-3-pro-preview-thinking
- gemini-3.1-pro-preview
- gemini-flash
- gemini-flash-lite
- glm-4.5-air
- glm-4.6
- glm-4.6-thinking
- glm-4.7
- glm-4.7-thinking
- glm-5
- gpt-3.5-turbo
- gpt-3.5-turbo-0125
- gpt-4.1
- gpt-4.1-mini
- gpt-4.1-nano
- gpt-4o
- gpt-4o-mini
- gpt-4o-realtime-preview
- gpt-5
- gpt-5-chat
- gpt-5-codex
- gpt-5-codex-mini
- gpt-5-mini
- gpt-5-nano
- gpt-5-pro
- gpt-5.1
- gpt-5.1-chat
- gpt-5.1-codex
- gpt-5.1-codex-max
- gpt-5.1-codex-mini
- gpt-5.2
- gpt-5.2-chat
- gpt-5.2-codex
- gpt-5.2-pro
- gpt-5.3-codex
- gpt-oss-120b
- gpt-oss-20b
- gpt-realtime
- grok-4
- grok-4-1-fast-non-reasoning
- grok-4-1-fast-reasoning
- grok-4-fast
- grok-4-fast-non-reasoning
- grok-4-fast-reasoning
- grok-4.1
- grok-4.1-fast
- grok-code-fast-1
- kimi-k2
- kimi-k2-instruct
- kimi-k2-preview
- kimi-k2-thinking
- kimi-k2.5
- kling-custom-elements
- kling-image-recognize
- llama-4-maverick
- llama-4-scout
- minimax-m2
- minimax-m2.1
- minimax-m2.5
- mistral-large
- mistral-small
- o3
- o3-mini
- o3-mini-high
- o3-pro
- o4-mini
- qwen-flash
- qwen-plus-character
- qwen-vl-max
- qwen2-vl-72b-instruct
- qwen2.5-32b-instruct
- qwen2.5-72b-instruct
- qwen2.5-7b-instruct
- qwen2.5-vl-32b-instruct
- qwen2.5-vl-72b-instruct
- qwen2.5-vl-7b-instruct
- qwen3-0.6b
- qwen3-1.7b
- qwen3-14b
- qwen3-235b-a22b
- qwen3-235b-a22b-instruct
- qwen3-235b-a22b-thinking
- qwen3-30b-a3b
- qwen3-30b-a3b-instruct
- qwen3-30b-a3b-thinking
- qwen3-32b
- qwen3-4b
- qwen3-8b
- qwen3-coder
- qwen3-coder-30b-a3b-instruct
- qwen3-coder-480b-a35b-instruct
- qwen3-coder-flash
- qwen3-coder-plus
- qwen3-max
- qwen3-max-preview-n
- qwen3-next-80b-a3b-instruct
- qwen3-next-80b-a3b-thinking
- qwen3-reranker-0.6b
- qwen3-vl-235b-a22b-instruct
- qwen3-vl-235b-a22b-thinking
- qwen3-vl-30b-a3b-instruct
- qwen3-vl-30b-a3b-thinking
- qwen3-vl-32b-instruct
- qwen3-vl-32b-thinking
- qwen3-vl-8b-instruct
- qwen3-vl-8b-thinking
- qwen3-vl-flash
- qwen3-vl-plus
- qwen3.5-397b-a17b
- qwen3.5-plus
- qwq-32b
- qwq-72b-preview
- qwq-plus
- seed-oss-36b-instruct
- seed3d-1.0
- seededit-3.0-i2i
- sparkdesk-v3.1
- sparkdesk-v3.5
- speech-2.6-hd
- whisper-large-v3
- whisper-large-v3-turbo

### Image Models (112 models)
- aigc-image-gem
- aigc-image-qwen
- animate-diff
- flux-1-dev
- flux-1-dev-image-to-image
- flux-1-dev-redux
- flux-1-schnell-redux
- flux-1.1-pro
- flux-1.1-pro-ultra
- flux-fill-dev
- flux-fill-pro
- flux-kontext-dev
- flux-kontext-max
- flux-kontext-max-multi
- flux-kontext-pro
- flux-kontext-pro-multi
- flux-lora
- flux-pro
- flux-pro-1.1-ultra
- flux-pro-max
- flux-schnell-lora
- gemini-2.5-flash-image
- gemini-2.5-flash-image-hd
- gemini-2.5-flash-image-preview
- gemini-3-pro-image-preview
- gemini-3.1-flash-image-preview
- gpt-4o-image-vip
- gpt-image-1
- gpt-image-1-mini
- gpt-image-1.5
- gpt-image-1.5-plus
- grok-2-image
- grok-3-image
- grok-4-image
- grok-imagine-0.9
- grok-imagine-image
- hailuo-2.3-fast
- hailuo-2.3-pro
- hailuo-2.3-standard
- higgsfield-lite
- higgsfield-standard
- higgsfield-turbo
- ideogram-describe
- ideogram-edit-v3
- ideogram-edit-v3-quality
- ideogram-edit-v3-turbo
- ideogram-generate-v3
- ideogram-generate-v3-quality
- ideogram-generate-v3-turbo
- ideogram-reframe-v3
- ideogram-reframe-v3-quality
- ideogram-reframe-v3-turbo
- ideogram-remix-v3
- ideogram-remix-v3-quality
- ideogram-remix-v3-turbo
- ideogram-replace-background-v3
- ideogram-replace-background-v3-quality
- ideogram-replace-background-v3-turbo
- ideogram-upscale
- image-background-remover
- image-upscaler
- image-watermark-remover
- image-zoom
- imagen-4
- imagen-4-fast
- imagen-4-ultra
- kling-image
- kling-image-o1
- kling-omni-image
- kling-v2.1-pro
- kling-v2.1-standard
- kling-v2.5-turbo-pro
- kling-v2.6-pro
- kling-v2.6-std
- kling-video-o1-pro
- kling-video-o1-std
- midjourney
- mj-blend
- mj-describe
- mj-high-variation
- mj-imagine
- mj-low-variation
- mj-modal
- mj-pan
- mj-reroll
- mj-upscale
- mj-variation
- mj-zoom
- nai-diffusion-4-5-curated
- nai-diffusion-4-5-full
- qwen-image
- qwen-image-edit
- qwen-image-lora
- qwen-image-max
- qwen-image-plus
- qwen-image-plus-lora
- recraft-v3
- recraft-v3-svg
- seedream-3.0-t2i
- seedream-4.0
- seedream-4.5
- seedream-5.0
- seedream-v4-edit
- seedream-v4-text-to-image
- sora-image
- tripo3d-v2.5
- viduq2
- viduq2-pro-fast
- wan-2.2-plus
- wan-2.5
- wan-2.6
- z-image-turbo

### Video Models (51 models)
- aigc-video-hailuo
- aigc-video-kling
- aigc-video-vidu
- grok-video-3
- grok-video-3-10s
- grok-video-3-15s
- hailuo-2.3
- kling-advanced-lip-sync
- kling-avatar-image2video
- kling-effects
- kling-motion-control
- kling-multi-elements
- kling-omni-video
- kling-v2.1-master
- kling-v2.5-turbo-std
- kling-video
- kling-video-extend
- luma-video-api
- luma-video-extend-api
- runwayml-gen4-turbo-10
- runwayml-gen4-turbo-5
- seedance-1.0-lite-i2v
- seedance-1.0-lite-t2v
- seedance-1.0-pro
- seedance-1.0-pro-fast
- seedance-1.5-pro
- seedance-2.0
- sora-2
- sora-2-characters
- sora-2-pro
- sora-2-vip
- vace-14b
- veo3
- veo3-fast
- veo3-pro
- veo3.1
- veo3.1-4k
- veo3.1-components
- veo3.1-components-4k
- veo3.1-fast
- veo3.1-fast-4k
- veo3.1-fast-components-4k
- veo3.1-pro
- veo3.1-pro-4k
- vidu2.0
- viduq2-pro
- viduq2-turbo
- viduq3-pro
- wan2.5-i2v-preview
- wan2.6-i2v
- wan2.6-i2v-flash

### Audio Models (19 models)
- audio1.0
- gemini-2.5-flash-preview-tts
- gemini-2.5-pro-preview-tts
- gpt-4o-mini-transcribe
- gpt-4o-mini-tts
- gpt-4o-transcribe
- kling-audio
- kling-custom-voices
- speech-2.5-hd-preview
- speech-2.5-hd-preview-voice-clone
- speech-2.5-turbo-preview
- speech-2.5-turbo-preview-voice-clone
- speech-2.6-turbo
- suno-lyrics
- suno-music
- tts-1
- tts-1-hd
- vidu-tts
- whisper-1

### Embedding Models (4 models)
- doubao-embedding-large
- gemini-embedding-001
- text-embedding-3-large
- text-embedding-3-small

## Quick Start

### Python
```python
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.lemondata.cc/v1"
)

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)
```

### cURL
```bash
curl https://api.lemondata.cc/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
```

## Pricing

Token-based pricing with significant discounts (~30% off official rates).
Full pricing: https://lemondata.cc/dashboard/models

## Features

- OpenAI-compatible API format
- Streaming support (SSE)
- Function calling / Tool use
- Vision (image input)
- Multiple output formats (JSON mode)
- Automatic failover between providers
- Real-time usage tracking

## Rate Limits

- Default: 60 requests/minute
- Premium: 300 requests/minute

## Error Codes

| Code | Description |
|------|-------------|
| 400 | Bad Request - Invalid parameters |
| 401 | Unauthorized - Invalid API key |
| 402 | Payment Required - Insufficient balance |
| 403 | Forbidden - Access denied |
| 429 | Too Many Requests - Rate limit exceeded |
| 500 | Internal Server Error |
| 503 | Service Unavailable - No available channels |
| 504 | Gateway Timeout - Request timed out |

## Integrations

LemonData works with any OpenAI-compatible client:
- LangChain
- LlamaIndex
- Dify
- LobeChat
- ChatGPT-Next-Web
- Open WebUI
- Continue (VS Code)
- Cursor
- And many more...

## Links

- Website: https://lemondata.cc
- Documentation: https://docs.lemondata.cc
- Dashboard: https://lemondata.cc/dashboard
- Status: https://lemondata.cc/status
- Support: support@lemondata.cc

## Company

LemonData - Making AI accessible to everyone.

---
Generated: 2026-02-28T05:56:53.501Z