Every model has a unique slug — a short identifier you pass in the model field of API requests.
{
"model": "gpt-5",
"messages": [...]
}
Model Categories
| Category | Count | API endpoint |
|---|
text | 12 | POST /api/v2/generate |
image | 12 | POST /api/v2/generate |
video | 9 | POST /api/v2/generate |
music | 3 | POST /api/v2/generate |
tts | 6 | POST /api/v2/generate |
stt | 3 | POST /api/v2/generate |
tool | 7 | POST /api/v2/generate/tools |
Text Models
| Slug | Name | Provider | Starter |
|---|
gpt-5-nano | GPT-5 Nano | OpenAI | ✅ |
claude-haiku-4.5 | Claude Haiku 4.5 | Anthropic | ✅ |
gemini-2.5-flash | Gemini 2.5 Flash | Google | ✅ |
deepseek-v3 | DeepSeek V3 Chat | DeepSeek | ✅ |
grok-4-fast | Grok 4 Fast | xAI | ✅ |
gpt-5 | GPT-5 | OpenAI | — |
gpt-5.2 | GPT-5.2 | OpenAI | — |
gpt-5.2-pro | GPT-5.2 Pro | OpenAI | — |
claude-sonnet-4.5 | Claude Sonnet 4.5 | Anthropic | — |
claude-opus-4.5 | Claude Opus 4.5 | Anthropic | — |
gemini-3-pro | Gemini 3 Pro | Google | — |
deepseek-r1 | DeepSeek R1 | DeepSeek | — |
Image Models
| Slug | Name | Provider | Starter |
|---|
photon-flash | Luma Photon Flash | Luma | ✅ |
dall-e-3 | DALL-E 3 | OpenAI | ✅ |
gpt-image-1.5 | GPT Image 1.5 | OpenAI | — |
flux-1.1-pro | Flux 1.1 Pro | Replicate | — |
flux-kontext-pro | Flux Kontext | Replicate | — |
sd-3.5-large | SD 3.5 Large | Replicate | — |
midjourney-v6 | Midjourney V6 | LegNext | — |
midjourney-turbo | Midjourney Turbo | LegNext | — |
recraft-v3 | Recraft V3 | Replicate | — |
photon-1 | Luma Photon | Luma | — |
nano-banana-pro | Nano Banana Pro | Replicate | — |
nano-banana-pro-2k | Nano Banana Pro 2K | Replicate | — |
Video Models
| Slug | Name | Provider | Starter |
|---|
luma-ray2-flash | Luma Flash2 720p | Luma | ✅ |
luma-ray2-flash | Luma Ray2 Flash | Luma | ✅ |
kling-v2.1 | Kling 2.1 Std | Replicate | — |
kling-v2.1-pro | Kling 2.1 Pro | Replicate | — |
minimax-video | MiniMax Video | Replicate | — |
luma-ray2 | Luma Ray2 720p | Luma | — |
luma-ray2-1080p | Luma Ray2 1080p | Luma | — |
mj-video-480p | MJ Video 480p | LegNext | — |
mj-video-720p | MJ Video 720p | LegNext | — |
Music & SFX Models
| Slug | Name | Provider | Starter |
|---|
musicgen | MusicGen | Replicate | ✅ |
elevenlabs-music | EL Music | ElevenLabs | — |
TTS Models
| Slug | Name | Provider | Starter |
|---|
minimax-tts | MiniMax TTS | MiniMax | — |
openai-tts | OpenAI TTS | OpenAI | — |
openai-tts-hd | OpenAI TTS HD | OpenAI | — |
gpt-4o-mini-tts | GPT-4o Mini TTS | OpenAI | — |
elevenlabs-flash | EL Flash | ElevenLabs | — |
elevenlabs-v2 | EL ML v2 | ElevenLabs | — |
STT Models
| Slug | Name | Provider | Starter |
|---|
whisper | Whisper STT | OpenAI | ✅ |
gpt-4o-transcribe | GPT-4o Transcribe | OpenAI | ✅ |
elevenlabs-scribe | EL Scribe | ElevenLabs | ✅ |
| Slug | Name |
|---|
upscale | Upscale ESRGAN |
face-swap | Face Swap |
remove-bg | Remove BG |
style-transfer | Style Transfer |
colorize | Colorize |
inpaint | InPaint Edit |
text-ocr | Text OCR |
Getting Models via API
GET /api/v2/models?category=image&available_for_plan=vip
Model Availability by Plan
| Plan | Available Models |
|---|
| Starter | 20 Starter-tier models |
| Basic+ | All 52 models |
Any paid plan (Basic and above) unlocks all 52 models. Plans differ only in token quantity and rate limits — not model access.
