AI Models, One API
Browse AI models, compare availability, pricing, and capabilities, and integrate fast.
Latest releases
The newest model families on SnapGen, freshest first.
Model catalog
Gemini Omni
VideoCreate short, sound-ready video clips from text prompts, source images, reference images, or extension inputs through an OpenAI-compatible video API.
Gemini Omni Flash 1.1
VideoGoogle's fast Gemini Omni Flash 1.1 video model creates 4–10 second clips with native audio from text, first and last frames, or up to seven reference images, and extends existing clips, at 360p to 4K through an OpenAI-compatible video API.
MiniMax H3
VideoMiniMax
MiniMax H3, also known as Hailuo 03, turns text prompts into cinematic video with native stereo audio, up to 2K output, six aspect ratios, and clips up to 15 seconds.
Seedance 2.0
VideoByteDance
ByteDance Seedance 2.0 turns text, up to 9 reference images, or up to 3 reference clips into 4–15 second cinematic video with native audio, at 480p, 720p, 1080p, or 4K. Billed per second.
Seedance 2 Fast
VideoByteDance
NewByteDance Seedance 2 Fast generates 4–15 second 480p or 720p video with optional native audio. Text, image, and reference routes are billed per second through POST /v1/videos.
Seedance 2 Mini
VideoByteDance
NewByteDance Seedance 2 Mini generates 4–15 second 480p or 720p video with optional native audio. Text, image, and reference routes are billed per second through POST /v1/videos.
Seedance 2.5
VideoByteDance
ByteDance Seedance 2.5 generates 4–30 second video with optional native audio. The 480p and 720p SKUs cover text, image, and video-edit jobs; the mode models add multi-reference generation and video extension up to 1080p. Billed per second.
Grok Imagine 1.5
VideoxAI
Generate 6–30 second cinematic video from a text prompt, with optional reference images (up to 7). Uses the non-preview Grok Imagine Video 1.5 Fast route.
Veo 3.1
VideoCreate fixed 8-second videos with synchronized native audio in 1080p or 4K. Seven Lite, Fast, reference, and Quality routes support text prompts plus optional start and end frames.
GPT Image 2.5 Ext
ImageOpenAI
NewGenerate and edit images with Flare or Sunburst, up to 4K output and 16 reference images.
GPT Image 2
ImageOpenAI
Generate thoughtful, production-ready images with a familiar OpenAI-compatible image endpoint.
Suno
AudioSuno
NewGenerate full songs with vocals from a description or your own lyrics with Suno V6, then extend, cover, remaster, split stems, add vocals and export MIDI, timed lyrics or a music video. 33 operations, one task API.
Flow Music
AudioGenerate songs with Google's Lyria 3 Pro and Lyria 3.5, then extend, replace a section, cover, split stems, download MP3 or WAV and render a music video. Nine operations, one task API.
ElevenLabs Text to Speech
AudioElevenLabs
NewTurn text into lifelike speech with Eleven v4, Eleven v3, Multilingual v2 and Flash v2.5, or voice a multi-speaker dialogue, with 21 ready-made voices. Billed per character.
Flux 3
VideoBlack Forest Labs
Coming soonAn upcoming Black Forest Labs multimodal foundation for image, video, audio, language, and action-oriented generation. SnapGen will add production access only when the public API details are confirmed.
ElevenLabs Scribe v2
AudioElevenLabs
NewTranscribe audio and video in 90+ languages with Scribe v2: speaker labels, word timestamps, audio events and SRT subtitles. Align a known script to audio word by word. Billed per second.
Eleven Music
AudioElevenLabs
NewCompose studio-quality music from a prompt with Eleven Music v2.5, with lyrics or as an instrumental, from 3 seconds to 5 minutes, returned directly as audio. Billed per second.
ElevenLabs Sound Effects
AudioElevenLabs
NewGenerate sound effects from a text description with ElevenLabs Sound Effects v2, up to 30 seconds and optionally as a seamless loop. Billed per second.
ElevenLabs Voice Changer
AudioElevenLabs
NewRe-voice a recording with any of 21 voices while keeping its timing and emotion, or isolate the voice from background noise. Billed per second of input.
ElevenLabs Dubbing
AudioElevenLabs
NewTranslate and re-voice video or audio into 32 languages with ElevenLabs Dubbing, keeping each speaker distinct. Runs as a task; billed per second of source.
GPT-5
TextOpenAI
Route live GPT-5.x chat and reasoning variants through one consistent chat-completions surface.
Claude
TextAnthropic
Coming soonUse the Claude models currently available through the SnapGen chat gateway.
Gemini
TextUse the Gemini text models currently available through the SnapGen chat gateway.
Grok
TextxAI
NewxAI Grok 4.6, 4.5 and 4.3 through the OpenAI-compatible Chat Completions and Responses APIs, with streaming, reasoning, and cached-input pricing at the xAI list rate.
DeepSeek
TextDeepSeek
NewUse the DeepSeek models currently available through the SnapGen chat gateway.
Qwen
TextQwen
Coming soonUse the Qwen models currently available through the SnapGen chat gateway.
All model rates
Live gateway prices
| Model | Input / 1M | Output / call | Endpoints |
|---|---|---|---|
| deepseek-flash | $0.23 | $0.90 | openai.chat_completions |
| deepseek-v4-flash | $0.48 | $1.42 | openai.chat_completions |
| deepseek-v4-pro | $1.42 | $4.26 | openai.chat_completions |
| eleven-dubbing-v1 | - | $0.75/ min | audio.dubbing |
| eleven-english-sts-v2 | - | $0.18/ min | audio.voice_changer |
| eleven-flash-v2.5 | - | $0.09/ 1K chars | openai.audio.speech |
| eleven-forced-alignment | - | $0.00744/ min | audio.alignment |
| eleven-multilingual-sts-v2 | - | $0.18/ min | audio.voice_changer |
| eleven-multilingual-v2 | - | $0.18/ 1K chars | openai.audio.speech |
| eleven-music-v2.5 | - | $0.42/ min | audio.music |
| eleven-sound-effects-v2 | - | $0.18/ min | audio.sound_effects |
| eleven-v3 | - | $0.18/ 1K chars | openai.audio.speech |
| eleven-v3-dialogue | - | $0.18/ 1K chars | audio.dialogue |
| eleven-v4 | - | $0.18/ 1K chars | openai.audio.speech |
| eleven-v4-dialogue | - | $0.18/ 1K chars | audio.dialogue |
| eleven-voice-isolator | - | $0.18/ min | audio.isolation |
| flow-music | - | $0.09 / call | music.generations |
| flow-music-cover | - | $0.09 / call | music.generations |
| flow-music-download | - | $0.03 / call | music.generations |
| flow-music-extend | - | $0.09 / call | music.generations |
| flow-music-lyrics | - | $0.03 / call | music.generations |
| flow-music-replace | - | $0.09 / call | music.generations |
| flow-music-stems | - | $0.09 / call | music.generations |
| flow-music-upload | - | $0.015 / call | music.generations |
| flow-music-video | - | $0.03 / call | music.generations |
| gemini-3.1-pro-preview | $1.20 | $7.20 | gemini.generate_contentgemini.stream_generate_contentopenai.chat_completions |
| gemini-3.5-flash | $0.90 | $5.40 | gemini.generate_contentgemini.stream_generate_contentopenai.chat_completions |
| gemini-3.6-flash | $0.90 | $4.50 | gemini.generate_contentgemini.stream_generate_contentopenai.chat_completions |
| gemini-3.8-flash | $0.90 | $4.50 | gemini.generate_contentgemini.stream_generate_contentopenai.chat_completions |
| gemini-omni-extend | - | $0.38 / call | openai.videos |
| gemini-omni-flash-1.1-extend | - | $1.20-$1.80 / call | openai.videos |
| gemini-omni-flash-1.1-i2v | - | 360p $0.09/ sec · 720p $0.09/ sec · 1080p $0.09/ sec · 4k $0.18/ sec | openai.videos |
| gemini-omni-flash-1.1-r2v | - | 360p $0.09/ sec · 720p $0.09/ sec · 1080p $0.09/ sec · 4k $0.18/ sec | openai.videos |
| gemini-omni-flash-1.1-t2v | - | 360p $0.09/ sec · 720p $0.09/ sec · 1080p $0.09/ sec · 4k $0.18/ sec | openai.videos |
| gemini-omni-i2v | - | $0.38 / call | openai.videos |
| gemini-omni-r2v | - | $0.38 / call | openai.videos |
| gemini-omni-t2v | - | $0.38 / call | openai.videos |
| gpt-5.4 | $3.00 | $18.00 | openai.chat_completionsopenai.responses |
| gpt-5.4-mini | $0.90 | $5.40 | openai.chat_completionsopenai.responses |
| gpt-5.4-nano | $0.24 | $1.50 | openai.chat_completionsopenai.responses |
| gpt-5.5 | $6.00 | $36.00 | openai.chat_completionsopenai.responses |
| gpt-5.6-luna | $0.24 | $1.44 | openai.chat_completionsopenai.responses |
| gpt-5.6-sol | $6.00 | $36.00 | openai.chat_completionsopenai.responses |
| gpt-5.6-terra | $2.40 | $14.40 | openai.chat_completionsopenai.responses |
| gpt-image-2 | - | $0.03-$0.26 / call | openai.images.generations |
| gpt-image-2.5-ext | - | $0.0085-$0.084 / call | openai.images.generations |
| gpt-image-2.5-ext-sunburst | - | $0.0085-$0.084 / call | openai.images.generations |
| grok-4.3 | $2.00 | $6.00 | openai.chat_completionsopenai.responses |
| grok-4.5 | $2.00 | $6.00 | openai.chat_completionsopenai.responses |
| grok-4.6 | $2.00 | $6.00 | openai.chat_completionsopenai.responses |
| grok-imagine-1.5-fast | - | $0.03/ sec | openai.videos |
| minimax-h3 | - | $0.105/ sec | openai.videos |
| minimax-h3-2k | - | $0.105/ sec | openai.videos |
| scribe-v2 | - | $0.00618/ min | openai.audio.transcriptions |
| seedance-2.0-fast-i2v | - | 480p $0.07/ sec · 720p $0.135/ sec | openai.videos |
| seedance-2.0-fast-r2v | - | 480p $0.07/ sec · 720p $0.135/ sec | openai.videos |
| seedance-2.0-fast-t2v | - | 480p $0.07/ sec · 720p $0.135/ sec | openai.videos |
| seedance-2.0-i2v | - | 480p $0.095/ sec · 720p $0.19/ sec · 1080p $0.48/ sec · 4k $1.10/ sec | openai.videos |
| seedance-2.0-mini-i2v | - | 480p $0.025/ sec · 720p $0.05/ sec | openai.videos |
| seedance-2.0-mini-r2v | - | 480p $0.025/ sec · 720p $0.05/ sec | openai.videos |
| seedance-2.0-mini-t2v | - | 480p $0.025/ sec · 720p $0.05/ sec | openai.videos |
| seedance-2.0-r2v | - | 480p $0.095/ sec · 720p $0.19/ sec · 1080p $0.48/ sec · 4k $1.10/ sec | openai.videos |
| seedance-2.0-t2v | - | 480p $0.095/ sec · 720p $0.19/ sec · 1080p $0.48/ sec · 4k $1.10/ sec | openai.videos |
| seedance-2.5-480p | - | $0.14/ sec | openai.videos |
| seedance-2.5-480p-v2v | - | $0.085/ sec | openai.videos |
| seedance-2.5-720p | - | $0.315/ sec | openai.videos |
| seedance-2.5-720p-v2v | - | $0.19/ sec | openai.videos |
| seedance-2.5-extend | - | 480p $0.15/ sec · 720p $0.335/ sec · 1080p $0.815/ sec | openai.videos |
| seedance-2.5-i2v | - | 480p $0.15/ sec · 720p $0.335/ sec | openai.videos |
| seedance-2.5-r2v | - | 480p $0.15/ sec · 720p $0.335/ sec | openai.videos |
| seedance-2.5-t2v | - | 480p $0.15/ sec · 720p $0.335/ sec | openai.videos |
| suno-add-instrumental | - | $0.075-$0.15 / call | music.generations |
| suno-add-stem | - | $0.075-$0.15 / call | music.generations |
| suno-add-vocals | - | $0.075-$0.15 / call | music.generations |
| suno-bpm | - | $0.0012 / call | music.generations |
| suno-concat | - | $0.006 / call | music.generations |
| suno-cover | - | $0.075-$0.15 / call | music.generations |
| suno-crop | - | $0.012 / call | music.generations |
| suno-custom-model | - | $1.44 / call | music.generations |
| suno-download | - | $0.0024 / call | music.generations |
| suno-extend | - | $0.075-$0.15 / call | music.generations |
| suno-fade-in | - | $0.012 / call | music.generations |
| suno-fade-out | - | $0.012 / call | music.generations |
| suno-inspo | - | $0.102-$0.204 / call | music.generations |
| suno-lyrics | - | $0.012 / call | music.generations |
| suno-mashup | - | $0.075-$0.15 / call | music.generations |
| suno-midi | - | $0.075 / call | music.generations |
| suno-mp4 | - | $0.006 / call | music.generations |
| suno-music | - | $0.075-$0.15 / call | music.generations |
| suno-persona | - | $0.006 / call | music.generations |
| suno-remaster | - | $0.075 / call | music.generations |
| suno-remove-section | - | $0.012 / call | music.generations |
| suno-replace-section | - | $0.075-$0.15 / call | music.generations |
| suno-sample | - | $0.075-$0.15 / call | music.generations |
| suno-sounds | - | $0.0144 / call | music.generations |
| suno-speed | - | $0.036 / call | music.generations |
| suno-stems | - | $0.15 / call | music.generations |
| suno-stems-all | - | $0.36 / call | music.generations |
| suno-style-boost | - | $0.006 / call | music.generations |
| suno-timed-lyrics | - | $0.0012 / call | music.generations |
| suno-upload | - | $0.006 / call | music.generations |
| suno-upload-cover | - | $0.075-$0.15 / call | music.generations |
| suno-upload-extend | - | $0.075-$0.15 / call | music.generations |
| suno-voice | - | $0.024 / call | music.generations |
| veo3-1-fast | - | $0.27 / call | openai.videos |
| veo3-1-fast-4k | - | $0.75 / call | openai.videos |
| veo3-1-fast-ref | - | $0.27 / call | openai.videos |
| veo3-1-lite | - | $0.12 / call | openai.videos |
| veo3-1-lite-4k | - | $0.60 / call | openai.videos |
| veo3-1-quality | - | $1.20 / call | openai.videos |
| veo3-1-quality-4k | - | $1.80 / call | openai.videos |
Explore more model APIs
Every model below works with the same SnapGen key and prepaid balance.
Video models
- Gemini Omni API
- Gemini Omni Flash 1.1 API
- MiniMax H3 API
- Seedance 2.0 API
- Seedance 2 Fast API
- Seedance 2 Mini API
- Seedance 2.5 API
- Grok Imagine 1.5 API
- Veo 3.1 API
- Flux 3 API
Image models
Audio models
Providers
- OpenAI models
- Google models
- ByteDance models
- MiniMax models
- ElevenLabs models
- Suno models
- xAI models
- DeepSeek models
- Anthropic models
- Qwen models
- Black Forest Labs models
Guides
- Gemini Omni Flash 1.1 API guide: modes, parameters, pricing and code
- GPT Image 2 with Node.js: generate, save and batch images through SnapGen
- GPT-5.6 Sol vs Terra vs Luna: pricing, positioning and routing
- How SnapGen bills reference videos: measured seconds, caps and examples
- How to use the SnapGen MCP server with Claude Code, Cursor and other agents
