Models
Every model, one key
67 models from 35 labs across text, image, video, speech and embeddings. Call any of them with the same key.
TextChat and reasoning, streamed token by token
AnthropicText
Claude Opus 5.5
/v1/chat/completions
AnthropicText
Claude Sonnet 5.5
/v1/chat/completions
AnthropicText
Claude Haiku 5.5
/v1/chat/completions
AnthropicText
Claude Fable 5.1
/v1/chat/completions
OpenAIText
GPT-6.1 Sol
/v1/chat/completions
OpenAIText
GPT-6 Luna
/v1/chat/completions
GoogleText
Gemini 3.8 Flash
/v1/chat/completions
DeepSeekText
DeepSeek V4.1 Flash
/v1/chat/completions
QwenText
Qwen3.8 Max
/v1/chat/completions
QwenText
Qwen3.8 Flash
/v1/chat/completions
Moonshot AIText
Kimi K3
/v1/chat/completions
Z.aiText
GLM 5.3
/v1/chat/completions
Z.aiText
GLM 5.3 Flash
/v1/chat/completions
MiniMaxText
MiniMax M3
/v1/chat/completions
xAIText
Grok 4.7
/v1/chat/completions
MistralText
Mistral Large 4
/v1/chat/completions
ByteDance SeedText
Seed 2.1 Turbo
/v1/chat/completions
XiaomiText
MiMo-V2.6-Pro
/v1/chat/completions
XiaomiText
MiMo-V2.6-Flash
/v1/chat/completions
StepFunText
Step 5
/v1/chat/completions
Tencent HunyuanText
Hy4
/v1/chat/completions
MetaText
Muse Spark 1.3
/v1/chat/completions
NVIDIAText
Nemotron 3 Ultra
/v1/chat/completions
CohereText
Command A+
/v1/chat/completions
AmazonText
Nova 2 Lite
/v1/chat/completions
ImageGenerate and edit through the same key
OpenAIImage
GPT Image 2.5
/v1/images/generations
GoogleImage
Nano Banana 2.1
/v1/images/generations
GoogleImage
Imagen 4
/v1/images/generations
ByteDance SeedImage
Seedream 5.0
/v1/images/generations
Black Forest LabsImage
FLUX.3 Image
/v1/images/generations
QwenImage
Qwen Image 3
/v1/images/generations
MicrosoftImage
MAI-Image-2.6
/v1/images/generations
xAIImage
Grok Imagine Image 2.0
/v1/images/generations
RecraftImage
Recraft V4.1
/v1/images/generations
Tencent HunyuanImage
Hy Image 3.5
/v1/images/generations
MetaImage
Muse Image
/v1/images/generations
KreaImage
Krea 2
/v1/images/generations
IdeogramImage
Ideogram V4.5
/v1/images/generations
VideoText and image to video, as async jobs
GoogleVideo
Veo 3.1
/v1/videos
OpenAIVideo
Sora 2
/v1/videos
KlingVideo
Kling Video v3.0
/v1/videos
ByteDance SeedVideo
Seedance 2.5
/v1/videos
AlibabaVideo
Wan 3.0
/v1/videos
HailuoVideo
Hailuo 2.3
/v1/videos
MiniMaxVideo
MiniMax H3
/v1/videos
RunwayVideo
Runway Gen-4.5
/v1/videos
RunwayVideo
Aleph 2.0
/v1/videos
xAIVideo
Grok Imagine Video 1.5
/v1/videos
Black Forest LabsVideo
FLUX.3 Video
/v1/videos
LumaVideo
Luma Ray 3.2
/v1/videos
ViduVideo
Vidu Q4
/v1/videos
PixVerseVideo
PixVerse V6
/v1/videos
SpeechVoices in, voices out
ElevenLabsText to speech
Eleven v4
/v1/audio/speech
ElevenLabsSpeech to text
Scribe v2
/v1/audio/transcriptions
GoogleText to speech
Gemini 3.8 Flash TTS
/v1/audio/speech
OpenAIRealtime voice
GPT Realtime 2
/v1/realtime
OpenAISpeech to text
Whisper Large V3
/v1/audio/transcriptions
MiniMaxText to speech
MiniMax Speech 2.8
/v1/audio/speech
Fish AudioText to speech
Fish Audio S2 Pro
/v1/audio/speech
DDeepgramText to speech
Aura-2
/v1/audio/speech
DDeepgramSpeech to text
Nova-3
/v1/audio/transcriptions
AssemblyAISpeech to text
Universal-3.5 Pro
/v1/audio/transcriptions
EmbeddingsVectors for search and retrieval
Voyage AIEmbeddings
voyage-4
/v1/embeddings
GoogleEmbeddings
Gemini Embedding 2
/v1/embeddings
QwenEmbeddings
Qwen3 Embedding 8B
/v1/embeddings
CohereEmbeddings
Cohere Embed v5.0
/v1/embeddings
OpenAIEmbeddings
Text Embedding 3 Large
/v1/embeddings
No model matches
Model names as listed on public API marketplaces (OpenRouter, fal, Replicate), October 2026. What a key can call depends on what is enabled for it.