December 5, 2025 (April 24, 2026)

Table of contents

  1. Video Models
    1. Endpoint Compatibility
      1. Extend, upscale, modify, lipsync
      2. v5 family (legacy)
    2. Quality, Duration, Aspect Ratio
    3. Audio
    4. Native PixVerse — extra flags
    5. Video-Reference (Fusion) Notation
  2. Image Models
    1. Unlimited Image Generation (Relax Mode)
  3. Quality Tier Requirements

Video Models

Endpoint Compatibility

Model create create-frames create-fusion
v6 (default) ✓ ✓ —
v5.6 ✓ ✓ ✓
pixverse-c1 ✓ ✓ ✓
seedance-2.0 ✓ ✓ ✓
seedance-2.0-fast ✓ ✓ ✓
kling-o3 ✓ ✓ ✓
kling-v3 ✓ ✓ —
grok-imagine ✓ — —
veo-3.1-lite ✓ ✓ —
veo-3.1-standard ✓ ✓ —
veo-3.1-fast ✓ ✓ —
sora-2 ✓ — —
sora-2-pro ✓ — —

Fusion notation: v5 uses @pic1/@pic2/@pic3; all other fusion-capable models use @image1…@imageN (mapped positionally to frame_1_path…frame_N_path).

Extend, upscale, modify, lipsync

Only native PixVerse models support these endpoints.

Endpoint v6 v5 v5.5 v5.6
extend ✓ ✓ ✓ —
upscale ✓ ✓ ✓ ✓
modify — — ✓ —
lipsync — ✓ — —

v5 family (legacy)

v5 carries legacy-only modes — multi-frame create-transition, lipsync, and fusion with the original @pic1/@pic2/@pic3 notation.

Endpoint v5 v5.5 v5.6 v5-fast
create ✓ ✓ ✓ ✓
create-frames ✓ ✓ ✓ —
create-transition (2-frame) ✓ ✓ ✓ —
create-transition (3+ frame) ✓ — — —
create-fusion ✓ — ✓ —
extend ✓ ✓ — —
modify — ✓ — —
lipsync ✓ — — —
upscale ✓ ✓ ✓ ✓

v5 accepts both @image1…@imageN (unified) and the legacy @pic1/@pic2/@pic3 synonyms for backward compatibility.

Quality, Duration, Aspect Ratio

Model Qualities Durations Aspect Ratios Max ref imgs (fusion)
v6 360p, 540p, 720p (default), 1080p 1-15s 16:9, 9:16, 1:1, 4:3, 3:4 —
v5.6 360p, 540p (default), 720p, 1080p 1-10s (1080p max 8) 16:9, 9:16, 1:1, 4:3, 3:4 7
v5.5 360p, 540p (default), 720p, 1080p 1-10s (1080p max 8) 16:9, 9:16, 1:1, 4:3, 3:4 —
v5 360p, 540p (default), 720p, 1080p 1-10s (1080p max 8) 16:9, 9:16, 1:1, 4:3, 3:4 3
v5-fast 360p, 540p (default), 720p, 1080p 1-10s (1080p max 8) 16:9, 9:16, 1:1, 4:3, 3:4 —
pixverse-c1 360p, 540p, 720p, 1080p 1-15s 16:9, 4:3, 1:1, 3:4, 9:16, 3:2, 2:3 7
seedance-2.0 480p, 720p, 1080p 4-15s 16:9, 4:3, 1:1, 3:4, 9:16, 21:9 9
seedance-2.0-fast 480p, 720p 4-15s 16:9, 4:3, 1:1, 3:4, 9:16, 21:9 9
kling-o3 720p (Std), 1080p (Pro) 3-15s 16:9, 1:1, 9:16 7
kling-v3 720p (Std), 1080p (Pro) 3-15s 16:9, 1:1, 9:16 —
grok-imagine 480p, 720p 1-15s 16:9, 4:3, 1:1, 3:4, 9:16, 3:2, 2:3 —
veo-3.1-lite 720p, 1080p 4, 6, 8 16:9, 9:16 —
veo-3.1-standard 720p, 1080p, 4K 4, 6, 8 16:9, 9:16 —
veo-3.1-fast 720p, 1080p, 4K 4, 6, 8 16:9, 9:16 —
sora-2 720p 4, 8, 12 16:9, 9:16 —
sora-2-pro 720p, 1080p 4, 8, 12 16:9, 9:16 —
  • aspect_ratio is required for t2v and fusion, not accepted for i2v or transition (derived from image).
  • For kling-o3 / kling-v3: quality: 720p routes to Std, quality: 1080p routes to Pro.
  • For veo-3.1-standard / veo-3.1-fast: quality: 1080p requires duration: 8.

Audio

Model audio
v6 toggle
v5.6 toggle
v5.5 toggle
v5 — (use lip_sync_tts_prompt + sound_effect_prompt)
v5-fast —
pixverse-c1 toggle
seedance-2.0 toggle
seedance-2.0-fast toggle
kling-o3 toggle
kling-v3 toggle
grok-imagine rejected
veo-3.1-lite rejected
veo-3.1-standard always on
veo-3.1-fast always on
sora-2 rejected
sora-2-pro rejected
  • toggle — accept audio: true / false.
  • always on — audio generated automatically; audio: false is rejected.
  • rejected — audio parameter is not accepted (content has no audio track or audio is handled internally).

Native PixVerse — extra flags

multi_shot, preview_mode, off_peak_mode, and seed are supported only on native PixVerse models. Third-party models reject them.

Model multi_shot preview_mode off_peak_mode seed
v6 ✓ ✓ ✓ ✓
v5.6 — ✓ ✓ ✓
v5.5 — ✓ ✓ ✓
v5 — ✓ ✓ ✓
v5-fast — ✓ ✓ ✓
pixverse-c1 — ✓ ✓ ✓

Video-Reference (Fusion) Notation

All fusion-capable models use @image1, @image2, … @imageN in the prompt. Each token maps positionally to frame_1_path…frame_N_path.

v5 additionally accepts the legacy @pic1/@pic2/@pic3 synonyms for backward compatibility.

Image Models

All image models share the same endpoints: create, list, get, delete.

Model Qualities Max Refs Est. Time
qwen-image (default) 720p, 1080p 3 ~3s
nano-banana 1080p 3 ~10s
seedream-4.0 1080p, 1440p, 2160p 6 ~10s
seedream-4.5 1440p, 2160p 6 ~15s
nano-banana-2 512p, 1080p, 1440p, 2160p 9 ~30s
seedream-5.0-lite 1440p, 1800p 6 ~30s
nano-banana-pro 1080p, 1440p, 2160p 9 ~60s
kling-3.0 1080p, 1440p 1 ~15s
kling-o3 1080p, 1440p, 2160p 1 ~20s
gpt-image-2.0 1080p, 1440p, 2160p 9 ~30s
  • Aspect ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 5:4, 4:5, 3:2, 2:3, 21:9. Also auto (default) except for qwen-image, kling-3.0, kling-o3, gpt-image-2.0 (the first three default to 1:1; gpt-image-2.0 uses a per-quality whitelist — see below).
  • create_count: 1-4 (default 1).
  • detail_level (gpt-image-2.0 only, required): low, medium, high. Rejected for all other models. Affects credit cost (low = 0.5×, medium = 1×, high = 2× of the per-quality base).

  • gpt-image-2.0 aspect ratios (no auto):

    Quality Allowed aspect_ratio
    1080p 1:1, 3:2, 2:3
    1440p 1:1, 16:9, 9:16
    2160p 16:9, 9:16

Unlimited Image Generation (Relax Mode)

Pro+ subscription plans include unlimited image generation in Relax Mode:

Plan Price Unlimited Models
Pro $30/m qwen-image
Premium $60/m qwen-image + selectively others
Ultra $199/m ALL models

Quality Tier Requirements

  • 360p / 480p / 540p: All subscription tiers
  • 720p: Standard or higher
  • 1080p: Pro / Premium
  • 4K (Veo 3.1 Standard / Fast only): Premium / Ultra