Skip to main content
Chat Completions for GPT-5.6, GPT-6, Grok, Gemini, and DeepSeek; Responses for GPT-5.6, GPT-6, and Grok; Gemini native generateContent for Gemini. Each model page lists its protocols. SnapGen does not translate between protocols.
Not yet. Claude is listed as coming soon; when it launches it will be served on Anthropic Messages (POST /v1/messages).
When a GPT-5.6 or GPT-6 request’s prompt (input plus cached tokens) exceeds 272,000 tokens, the whole request bills at that model’s long-context rate, listed on the live GPT family model page.
Seedance 2.0 comes in standard (480p to 4K), Fast, and Mini lines (480p or 720p), each with t2v, i2v, and r2v models and 4 to 15 second output. Seedance 2.5 offers 480p and 720p SKUs (with -v2v edit SKUs) and t2v, i2v, r2v, and extend mode models with 4 to 30 second output.
Gemini Omni bills per fixed 10-second request at 720p or 1080p and uses a pixel size. Flash 1.1 bills per second, takes 4, 6, 8, or 10 seconds, offers 360p to 4K through resolution, uses aspect_ratio, and accepts up to seven reference images.
Model IDs without -4k produce 1080p. veo3-1-lite-4k, veo3-1-fast-4k, and veo3-1-quality-4k produce 4K. All Veo routes are fixed at 8 seconds. Lite, Fast, and Quality accept zero to two images; veo3-1-fast-ref requires one to three.
gpt-image-2 (quality low, medium, or high and a pixel size) and GPT Image 2.5 Ext (gpt-image-2.5-ext and gpt-image-2.5-ext-sunburst, with 1K, 2K, or 4K output, ratios, up to four images, and up to 16 references).
ElevenLabs speech (eleven-v4, eleven-v3, eleven-multilingual-v2, eleven-flash-v2.5) and dialogue, Scribe v2 speech to text, forced alignment, Eleven Music v2.5, sound effects, voice changer, voice isolator, and dubbing. Suno offers 33 models and Flow Music 9 for generating, editing, splitting, and exporting songs as tasks. See the Audio Series pages.
Dubbing (POST /v1/audio/dubbing) and every Suno and Flow Music model (POST /v1/music/generations) return a task to poll with GET /v1/tasks/{id}. The other audio endpoints return the audio file or JSON in the same response.
Yes. Suno and Flow Music edit models take one of your earlier tasks as source_task_id, with source_index to pick a track. The task must be yours and must have succeeded. See Reference earlier tasks.
Only to the file-based audio endpoints: speech to text, forced alignment, voice changer, and voice isolation accept a multipart/form-data upload of up to 50 MB. Everywhere else, image, video, and audio inputs must be public http or https URLs; private addresses and local files are rejected.
Call GET /v1/models at runtime and check the live models page for current prices.