Account & catalog

Models

Discover the active model catalog from the API instead of hard-coding media limits. Model entries use the standard model envelope and add Byta capability metadata such as credit prices, supported modes, reference limits, runtimes, and video options.

Catalog last synchronized: October 3, 2026 (UTC)

Public model and pricing catalog

Browse api.byta-ai.com/models without signing in. That live catalog is the final source of truth for model availability, capabilities, and API pricing.

Which model should I choose?

Start with the default model for each modality, then move when a concrete cost, latency, quality, or reference requirement calls for it.

Use case	Recommended model	Why
Text	`Byta-1.5`	Good for Daily Task
Text	`Byta-1.5-pro`	High reasoning, 2x usage
Text	`Byta-1.5-lite`	Ultra light model for general job, 0.2x usage
Images	`byta-image-1-5`	Our signature default model for reliable everyday image generation.
Images	`byta-image-1-5-pro`	Flagship high-resolution model with exceptional detail and precision.
Images	`byta-image-1-6-pro`	Premium image generation with a choice of quality-focused or accelerated inference.
Images	`byta-image-1-5-turbo`	Fast text-to-image model for reliable everyday results.
Video	`byta-video-1-5`	Our signature default model for reliable everyday video generation. Safety check is applied.
Video	`bytis-video-1-4`	Fast and stable video generation model, no content moderation.
Video	`bytis-video-1-5`	Fast video generation model with strong prompt understanding and cinematic output. No content moderation.
Video	`bytis-video-1-5b`	Powerful video model fine-tuned for high-resolution output. No moderation.
Video	`seedance-2-0-mini`	Fast, economical video generation with native audio and optional first-to-last-frame animation. Safety check is applied.
Video	`minimax-h3`	Open-weights video generation with native stereo audio and optional first-to-last-frame animation. Safety check is applied.
Video	`minimax-h3-spicy`	MiniMax H3 text-to-video with Spicy image-to-video and optional first-to-last-frame animation. The image route has no upstream safety check; the text route is standard H3.
Video	`minimax-h3-turbo`	Turbo MiniMax H3 generation optimized for faster inference with optional first-to-last-frame animation. Safety check is applied.

Text models

Both text models support Responses, Chat Completions, SSE streaming, reasoning aliases, and web search.

Model	Best for	Context	Input / 1M	Output / 1M
`Byta-1.5`	Good for Daily Task	500,000	$0.3520	$1.4080
`Byta-1.5-pro`	High reasoning, 2x usage	1,050,000	$0.40	$2.16
`Byta-1.5-lite`	Ultra light model for general job, 0.2x usage	1,000,000	$0.0608	$0.32

Context and output limits

Model	Maximum input	Maximum output	Safety margin
`Byta-1.5`	400,000 tokens	32,000 tokens	4,096 tokens
`Byta-1.5-pro`	800,000 tokens	32,000 tokens	4,096 tokens
`Byta-1.5-lite`	800,000 tokens	32,000 tokens	4,096 tokens

Image models

All active image models support text-to-image. Reference support and USD prices are model-specific and shown per completed image.

Model	Best for	T2I	Reference	Max refs	Runtime
`byta-image-1-5`	Our signature default model for reliable everyday image generation.	$0.0256	Default: $0.0256	Up to 5	~30s / ~45s
`byta-image-1-5-pro`	Flagship high-resolution model with exceptional detail and precision.	$0.04	Default: $0.0480	Up to 5	~80s / ~100s
`byta-image-1-6-pro`	Premium image generation with a choice of quality-focused or accelerated inference.	$0.0960	Default: $0.0960	Up to 5	~150s / ~180s
`byta-image-1-5-turbo`	Fast text-to-image model for reliable everyday results.	$0.0192	Not supported	None	~18s

Video models

Video price depends on the exact duration and resolution pair. See the video guide or pricing page for the full matrix.

Model	Best for	Durations	Resolutions	References	Runtime
`byta-video-1-5`	Our signature default model for reliable everyday video generation. Safety check is applied.	6s, 10s, 15s	480p, 720p, 1080p	Up to 7	~45s
`bytis-video-1-4`	Fast and stable video generation model, no content moderation.	5s, 10s	480p, 720p	Up to 1	~20s
`bytis-video-1-5`	Fast video generation model with strong prompt understanding and cinematic output. No content moderation.	5s, 8s, 12s	480p, 720p	Up to 1	~150s
`bytis-video-1-5b`	Powerful video model fine-tuned for high-resolution output. No moderation.	5s, 8s, 12s	480p, 720p, 1080p	Up to 1	~120s
`seedance-2-0-mini`	Fast, economical video generation with native audio and optional first-to-last-frame animation. Safety check is applied.	6s, 10s, 15s	480p, 720p	Up to 2	~90s
`minimax-h3`	Open-weights video generation with native stereo audio and optional first-to-last-frame animation. Safety check is applied.	6s, 10s, 15s	480p, 768p	Up to 2	~150s
`minimax-h3-spicy`	MiniMax H3 text-to-video with Spicy image-to-video and optional first-to-last-frame animation. The image route has no upstream safety check; the text route is standard H3.	6s, 10s, 15s	480p, 768p	Up to 2	~150s
`minimax-h3-turbo`	Turbo MiniMax H3 generation optimized for faster inference with optional first-to-last-frame animation. Safety check is applied.	6s, 10s, 15s	480p, 768p	Up to 2	~90s

List active models

Authenticate with the same API key used for generation. The catalog returns only public, currently enabled models.

GET/v1/models

Bearer authentication required

cURL · model catalog

curl https://api.byta-ai.com/v1/models \
  -H "Authorization: Bearer $BYTA_API_KEY" \
  -H "Accept: application/json"

200 OK · shortened

{
  "object": "list",
  "data": [
    {
      "id": "Byta-1.5",
      "object": "model",
      "owned_by": "byta-ai",
      "capabilities": [
        "chat.completions",
        "responses"
      ],
      "contextWindowTokens": 500000,
      "pricing": {
        "currency": "USD",
        "usdMicros": {
          "inputPerMillionTokens": 352000,
          "outputPerMillionTokens": 1408000
        }
      }
    },
    {
      "id": "byta-video-1-5",
      "object": "model",
      "owned_by": "byta-ai",
      "capabilities": [
        "videos"
      ],
      "videoOptions": [
        {
          "creditsPerVideo": 45,
          "originalCreditsPerVideo": 50,
          "durationSeconds": 6,
          "i2vEnabled": true,
          "referenceSupport": "inherit",
          "resolution": "480p",
          "t2vEnabled": true
        },
        {
          "creditsPerVideo": 90,
          "originalCreditsPerVideo": 100,
          "durationSeconds": 6,
          "i2vEnabled": true,
          "referenceSupport": "inherit",
          "resolution": "720p",
          "t2vEnabled": true
        },
        {
          "creditsPerVideo": 68,
          "originalCreditsPerVideo": 75,
          "durationSeconds": 10,
          "i2vEnabled": true,
          "referenceSupport": "inherit",
          "resolution": "480p",
          "t2vEnabled": true
        },
        {
          "creditsPerVideo": 135,
          "originalCreditsPerVideo": 150,
          "durationSeconds": 10,
          "i2vEnabled": true,
          "referenceSupport": "inherit",
          "resolution": "720p",
          "t2vEnabled": true
        },
        {
          "creditsPerVideo": 113,
          "originalCreditsPerVideo": 125,
          "durationSeconds": 15,
          "i2vEnabled": false,
          "referenceSupport": "inherit",
          "resolution": "480p",
          "t2vEnabled": true
        },
        {
          "creditsPerVideo": 225,
          "originalCreditsPerVideo": 250,
          "durationSeconds": 15,
          "i2vEnabled": false,
          "referenceSupport": "inherit",
          "resolution": "720p",
          "t2vEnabled": true
        },
        {
          "creditsPerVideo": 113,
          "originalCreditsPerVideo": 125,
          "durationSeconds": 15,
          "i2vEnabled": true,
          "referenceSupport": "single",
          "resolution": "480p",
          "t2vEnabled": false
        },
        {
          "creditsPerVideo": 225,
          "originalCreditsPerVideo": 250,
          "durationSeconds": 15,
          "i2vEnabled": true,
          "referenceSupport": "single",
          "resolution": "720p",
          "t2vEnabled": false
        },
        {
          "creditsPerVideo": 180,
          "originalCreditsPerVideo": 200,
          "durationSeconds": 6,
          "i2vEnabled": true,
          "referenceSupport": "single",
          "resolution": "1080p",
          "t2vEnabled": true
        },
        {
          "creditsPerVideo": 270,
          "originalCreditsPerVideo": 300,
          "durationSeconds": 10,
          "i2vEnabled": true,
          "referenceSupport": "single",
          "resolution": "1080p",
          "t2vEnabled": true
        },
        {
          "creditsPerVideo": 450,
          "originalCreditsPerVideo": 500,
          "durationSeconds": 15,
          "i2vEnabled": true,
          "referenceSupport": "single",
          "resolution": "1080p",
          "t2vEnabled": true
        }
      ],
      "pricing": {
        "currency": "USD",
        "usdMicros": {
          "video:6:480p": 72000,
          "video:6:720p": 144000,
          "video:10:480p": 108800,
          "video:10:720p": 216000,
          "video:15:480p": 180800,
          "video:15:720p": 360000,
          "video:6:1080p": 288000,
          "video:10:1080p": 432000,
          "video:15:1080p": 720000
        }
      }
    }
  ]
}

Speech and music models

Audio catalog entries expose their current fixed USD prices.

Model	Capability	Price	Estimated generation
`Byta-Audio-1.1`	Speech	$0.0240 / 1,000 characters	Synchronous
`Byta-Audio-1.1-Pro`	Speech	$0.0320 / 1,000 characters	Synchronous
`Byta-Music-1.1`	Music	$0.2880 / request (2 song variants)	~200s
`Byta-Music-1.2`	Music	$0.40 / request (2 song variants)	~150s

Capability identifiers

Use capabilities to route each model to a compatible request interface.

responsesPOST /v1/responses

Unified text generation.

chat.completionsPOST /v1/chat/completions

Messages and choices text interface.

images.generationsPOST /v1/images/generations

Asynchronous image jobs.

videosPOST /v1/videos/generations

Asynchronous video jobs.

speech.generationsPOST /v1/speech/generations

Synchronous speech generation.

music.generationsPOST /v1/music/generations

Asynchronous music tasks.

Build dynamic clients

Treat the catalog as runtime configuration

Admins can change active media models and their options without a client release. Refresh the catalog periodically and validate the selected duration, resolution, aspect ratio, reference count, and credit price before submission.