Models & Pricing

Kolbo provides …+ AI models that are dynamically available. New models are added regularly and immediately accessible via the API.

List Models

GET /api/v1/models

Query Parameters

Example

# All image generation models
curl "https://api.kolbo.ai/api/v1/models?type=text_to_img" \
  -H "X-API-Key: kolbo_live_..."

# All text-to-video models from a specific provider
curl "https://api.kolbo.ai/api/v1/models?type=text_to_video&provider=fal" \
  -H "X-API-Key: kolbo_live_..."

Response

{
  "success": true,
  "models": [
    {
      "identifier": "nano-banana-2",
      "name": "Nano Banana 2 1K",
      "provider": "fal",
      "types": ["text_to_img"],
      "credit": 8,
      "supported_aspect_ratios": ["1:1", "16:9", "9:16", "4:3", "3:4"],
      "supported_aspect_ratios_by_type": null,
      "default_aspect_ratio": "1:1",
      "supported_resolutions": ["1K", "2K", "4K"],
      "resolution_multipliers": { "1K": 1.0, "2K": 1.5, "4K": 2.0 },
      "supported_durations": null,
      "max_reference_images": 8,
      "max_visual_dna": 8,
      "supports_visual_dna": true,
      "supports_first_last_frame": false,
      "requires_prompt": true,
      "min_prompt_length": null,
      "max_prompt_length": 2000,
      "max_file_size": null,
      "recommended": true,
      "new_model": false,
      "avatar": "https://..."
    }
  ],
  "count": 42
}

Model Fields — full reference

The response is a flat object; fields not applicable to a model family are null / [] / 0. Read the constraint envelope before submitting a generation — out-of-envelope values are rejected with 400, not silently substituted.

Identity & cost

Output constraints

Input constraints

Sound generation (video output)

Cost formula

final_cost = credit
           × (resolution_multipliers[resolution] || 1)
           × (sound_enabled ? sound_credit_multiplier : 1)
           × (duration_seconds  ?? 1)    // video tools
           × (num_images        ?? 1)    // image tools

For exact charged numbers, read credits_used from the generation response — that's the authoritative server-side total, multiplier-adjusted.

Available Image Models

Available Image Editing Models

Available Text-to-Video Models

Available Image-to-Video Models

Available Draw-to-Video Models

Available Video-to-Video Models

Available Elements Models

Available First & Last Frame Models

Available Lipsync Models (Image Source)

Available Lipsync Models (Video Source)

Available Music Models

Available Speech Models

Available Sound Models

Available Chat Models

Available 3D Models

Available Transcription Models

Credit Costs

Credits are the universal currency for all generations. 1 credit = $0.01.

Pricing by Type

Exact costs are shown in the live tables above. The credit field on each model is always up to date.

Credit Multipliers

The base credit price shown on each model is the base cost at the default tier. Two optional selections on some models — resolution and audio — multiply the base cost.

Resolution Multipliers (resolutionMultipliers)

When you pass a resolution parameter (or when a model has a tier selector in the UI), the final cost is base × resolutionMultiplier[tier].

Examples from production models:

The exact multiplier map is on each model document. Call GET /api/v1/models and read resolutionMultipliers to know the cost at every tier before you submit. Omitting resolution uses the model default tier (multiplier 1.0 in most cases).

Audio Multipliers (soundCreditMultiplier)

Some video models generate native audio when enabled. When the underlying session or controller sets soundEnabled: true (Creative Director video scenes, Veo 3.1, Pixverse V6, etc.), the final cost is base × soundCreditMultiplier.

Examples:

Both multipliers compound when a model has both:

final = base × resolutionMultiplier[tier] × (soundEnabled ? soundCreditMultiplier : 1.0) × durationSeconds

The per-second base (credit), the tier map (resolutionMultipliers), and soundCreditMultiplier are all fields on the model document — they stay authoritative there, not in this doc.

Auto-Selection

If you omit the model parameter, Kolbo's Smart Select automatically chooses the best model for your prompt. This is recommended for most use cases.