CQTAI

Model Marketplace

Browse every AI model on the platform — chat, image, video, audio and media processing. Filter by provider / modality / tag.

OpenAIText

gpt-5.4

In 300.00Out 1500.00Rate 1x
View docs
OpenAIText

gpt-5.4-mini

In 100.00Out 500.00Rate 1x
View docs
OpenAIText

gpt-5.5

In 500.00Out 3000.00Rate 1x
View docs
OpenAIText

gpt-5.6-luna

In 100.00Out 600.00Rate 2x
View docs
OpenAIText

gpt-5.6-sol

In 500.00Out 3000.00Rate 2x
View docs
OpenAIText

gpt-5.6-terra

In 250.00Out 1500.00Rate 2x
View docs
AnthropicText

claude-fable-5

In 1000.00Out 5000.00Rate 2x
View docs
AnthropicText

claude-haiku-4-5

In 100.00Out 500.00Rate 2x
View docs
AnthropicText

claude-opus-4-5

In 500.00Out 2500.00Rate 2x
View docs
AnthropicText

claude-opus-4-6

In 500.00Out 2500.00Rate 2x
View docs
AnthropicText

claude-opus-4-7

In 500.00Out 2500.00Rate 2x
View docs
AnthropicText

claude-opus-4-8

In 500.00Out 2500.00Rate 2x
View docs
AnthropicText

claude-sonnet-4-5

In 300.00Out 1500.00Rate 2x
View docs
AnthropicText

claude-sonnet-4-6

In 500.00Out 2500.00Rate 2x
View docs
DeepSeekText

deepseek-r1

In 400.00Out 1600.00Rate 1x
View docs
DeepSeekText

deepseek-r1-0528

In 400.00Out 1600.00Rate 1x
View docs
DeepSeekText

deepseek-v3

In 200.00Out 800.00Rate 1x
View docs
DeepSeekText

deepseek-v3.1

In 400.00Out 1200.00Rate 1x
View docs
DeepSeekText

deepseek-v3.2

In 200.00Out 300.00Rate 1x
View docs
DeepSeekText

deepseek-v3.2-exp

In 200.00Out 300.00Rate 1x
View docs
DeepSeekText

deepseek-v4-flash

In 100.00Out 200.00Rate 1x
View docs
DeepSeekText

deepseek-v4-pro

In 1200.00Out 2400.00Rate 1x
View docs
GLMText

glm-5

In 600.00Out 2200.00Rate 1x
View docs
GLMText

glm-5.1

In 800.00Out 2800.00Rate 1x
View docs
GLMText

glm-5.2

In 800.00Out 2800.00Rate 1x
View docs
SunoAudio

V6 Pro Song Generation/Extension/Cover

taskType: create_v6, extend_v6, upload_extend_v6, upload_cover_v6, cover_v6

30 credits
View docs
SunoAudio

V6-mini Song Generation/Extension/Cover

taskType: create_v6-mini, extend_v6-mini, upload_extend_v6-mini, upload_cover_v6-mini, cover_v6-mini

30 credits
View docs
SunoAudio

V6-wild Song Generation/Extension/Cover

taskType: create_v6-wild, extend_v6-wild, upload_extend_v6-wild, upload_cover_v6-wild, cover_v6-wild

30 credits
View docs
SunoAudio

Other Generation Tasks

taskType: replace_section, add_instrumental, add_vocals, sample, inspiration, mashup, use_styles_lyrics

30 credits
View docs
SunoAudio

Sound Effect Generation

taskType: sound

10 credits
View docs
SunoAudio

Vocal Separation

taskType: gen_stem_two

60 credits
View docs
SunoAudio

Instrument Separation

taskType: gen_stem_all

150 credits
View docs
SunoAudio

Merge Replaced Audio

taskType: replace_merge (concat)

4 credits
View docs
SunoAudio

Replace & Auto-merge

taskType: replace_auto (replace + auto-merge, directly yields 2 full songs)

4 credits
View docs
SunoAudio

Audio Upload

taskType: upload

4 credits
View docs
SunoAudio

Persona Generation

taskType: persona

5 credits
View docs
SunoAudio

Audio/Video Processing (MP4/WAV/Timeline/Downbeats)

taskType: mp4, wav, timeline, downbeats

2 credits
View docs
SunoAudio

Lyrics Generation / Upsample Tags

taskType: lyrics, upsample_tags

1 credits
View docs
SunoAudio

Remaster

taskType: remaster

40 credits
View docs
SunoAudio

Image Generation · Basic

taskType: imageGenerate · basic

2 credits
View docs
SunoAudio

Image Generation · Advanced

taskType: imageGenerate · advanced

80 credits
View docs
SunoAudio

Standalone Video Generation

taskType: videoStandaloneGenerate

80 points × duration
View docs
SunoAudio

Custom Model

taskType: customModel

400 credits
View docs
SunoAudio

Voice Persona

taskType: voicePersona_complete (voicePersona_init is free)

5 credits
View docs
SunoAudio

Mashup Lyrics

taskType: mashupLyrics

2 credits
View docs
SunoAudio

Audio Editing (Speed/Crop/Fade/MDI)

taskType: adjustSpeed, audioCrop, audioFade, mdi

2 credits
View docs
SunoAudio

Song Download

Standalone sync endpoint POST /api/cqt/v2/suno/download; charged on every call (including cache hits). One call downloads one song — both songs of a task means two calls

2 credits
View docs
MiniMaxAudio

MiniMax Music 3.0

model: minimax-music-3.0 (full song 2-3.5 min)

100 credits/call
View docs
MiniMaxAudio

MiniMax Music 2.6

model: minimax-music-2.6 (full song 2-3.5 min)

100 credits/call
View docs
MiniMaxAudio

MiniMax Music 2.5

model: minimax-music-2.5 (full song 2-3.5 min)

100 credits/call
View docs
MiniMaxAudio

MiniMax Music 2.0

model: minimax-music-2.0 (full song 2-3.5 min)

25 credits/call
View docs
GoogleAudio

Lyria 3.0 Clip

model: lyria-3.0-clip (~30 s clip)

30 credits/call
View docs
GoogleAudio

Lyria 3.0 Pro

model: lyria-3.0-pro (~3 min full song)

60 credits/call
View docs
MurekaAudio

Mureka Song 9

model: mureka-song-9 (full song ~2:50, lyrics required)

33 credits/call
View docs
MurekaAudio

Mureka Song 8

model: mureka-song-8 (full song ~2:50, lyrics required)

33 credits/call
View docs
ElevenLabsAudio

ElevenLabs Sound v2

model: elevenlabs-sound-v2 (sound effect, 1~30s)

1.5 credits/sec × duration (sec)
View docs
GoogleVideo

Veo3.1, text-to-video, Fast

model: veo31-fast

5 credits × duration
View docs
GoogleVideo

Veo3.1, text-to-video, Lite (fixed 8s)

model: veo31-lite

2.5 credits × duration (fixed 8s)
View docs
GoogleVideo

Veo3.1, image-to-video

model: veo31-ingredients

10 credits × duration
View docs
GoogleVideo

Veo3.1, text-to-video, Quality

model: veo31

10 credits × duration
View docs
GoogleVideo

Veo3.1, 1080p/HD extra

hd=true or resolution=1080p

20 credits
View docs
SoraVideo

Sora 2

model: sora-2

10 credits × duration
View docs
SeedanceVideo

Seedance 2

model: seedance2 (text/image-to-video, 4-15s)

5 credits × seconds
View docs
SeedanceVideo

Seedance 1.0 Pro

model: seedance-1.0-pro (text / image/first-last frame, 3~10s)

480P=14.6 / 720P=30.8 / 1080P=73.4 / 2K=110.1 / 4K=165.2 credits/sec × duration (sec)
View docs
SeedanceVideo

Seedance 1.0 Pro Fast

model: seedance-1.0-pro-fast (text / image/first-last frame, 3~10s)

480P=4 / 720P=8.6 / 1080P=20.6 / 2K=30.9 / 4K=46.4 credits/sec × duration (sec)
View docs
MiniMaxVideo

MiniMax H3

Standard workflow_id: text-to-video / multi-reference (images<=9 + reference videos<=3 + audio<=3) / multi-reference-4 / mj (MJ-style reference) / lh-multi-reference (images<=4, 480P/768P only) / fl2v (first frame required, last frame optional); 8 aspect ratios, 480P/768P/1080P, 4-15s (first-last & flexible multi-ref 4-10s)

480P=5 / 768P=12 / 1080P=18 credits/sec × duration (sec)
View docs
MiniMaxVideo

MiniMax H3 · CF Super-res

CF super-res workflow_id: cf-multi-reference / cf-mj / cf-fl2v (4-10s); super-resolves to 2K/4K at the chosen ratio for higher quality, other inputs match the matching standard workflow. API-only (/v1/videos), not offered in the creation studio

2K=30 / 4K=60 credits/sec × duration (sec)
View docs
KuaishouVideo

Kling 3.0 Turbo

model: kling-3.0-turbo (text / image/first-last frame / reference, 3~15s)

720P=80 / 1080P=100 / 2K=120 / 4K=144 credits/sec × duration (sec)
View docs
KuaishouVideo

Kling 3.0 Omni

model: kling-3.0-omni (text / image/first-last frame / reference, 3~15s)

720P=60 / 1080P=80 / 2K=100 / 4K=300; with audio: 720P=80 / 1080P=100 / 2K=120 / 4K=300; reference + ref video: 720P=90 / 1080P=120 / 2K=150 / 4K=300 credits/sec × duration (sec)
View docs
KuaishouVideo

Kling 3.0

model: kling-3.0 (text / image/first-last frame / reference, 3~15s)

720P=60 / 1080P=80 / 2K=100 / 4K=300; with audio: 720P=90 / 1080P=120 / 2K=150 / 4K=300 credits/sec × duration (sec)
View docs
KuaishouVideo

Kling O1

model: kling-o1 (text / image/first-last frame / reference, 5 / 10s)

720P=60 / 1080P=80 / 2K=120 / 4K=180; reference + ref video: 720P=90 / 1080P=120 / 2K=180 / 4K=270 credits/sec × duration (sec)
View docs
KuaishouVideo

Kling 2.6

model: kling-2.6 (text / image/first-last frame / reference, 5 / 10s)

720P=30 / 1080P=50 / 2K=75 / 4K=112; with audio: 1080P=100 / 2K=150 / 4K=225 credits/sec × duration (sec)
View docs
KuaishouVideo

Kling 2.5 Turbo

model: kling-2.5-turbo (text / image/first-last frame / reference, 3~15s)

720P=30 / 1080P=50 / 2K=75 / 4K=112 credits/sec × duration (sec)
View docs
KuaishouVideo

Kling 2.1

model: kling-2.1 (text / image/first-last frame / reference, 3~15s)

720P=40 / 1080P=70 / 2K=100 / 4K=150 credits/sec × duration (sec)
View docs
KuaishouVideo

Kling 2.0

model: kling-2.0 (text / image/first-last frame / reference, 3~15s)

720P=40 / 1080P=70 / 2K=100 / 4K=150 credits/sec × duration (sec)
View docs
KuaishouVideo

Kling 1.6

model: kling-1.6 (text / image/first-last frame / reference, 3~15s)

720P=40 / 1080P=70 / 2K=100 / 4K=150 credits/sec × duration (sec)
View docs
ViduVideo

Vidu Q4 Preview

model: vidu-q4-preview (image/first-last frame / reference, 3~16s)

540P=28.13 / 720P=59.38 / 1080P=75 / 2K=118.75 / 4K=243.75 credits/sec × duration (sec)
View docs
ViduVideo

Vidu Q3

model: vidu-q3 (reference, 1~10s)

540P=31.3 / 720P=62.5 / 1080P=78.2 / 2K=93.9 / 4K=112.7 credits/sec × duration (sec)
View docs
ViduVideo

Vidu Q3 Pro

model: vidu-q3-pro (text / image/first-last frame, 1~10s)

540P=31.3 / 720P=78.2 / 1080P=93.8 / 2K=112.6 / 4K=135.1 credits/sec × duration (sec)
View docs
ViduVideo

Vidu Q3 Turbo

model: vidu-q3-turbo (text / image/first-last frame / reference, 1~10s)

text/image/first-last frame: 540P=25 / 720P=37.5 / 1080P=43.8 / 2K=52.6 / 4K=63.1; reference: 540P=12.5 / 720P=31.3 / 1080P=40.6 / 2K=48.7 / 4K=58.5 credits/sec × duration (sec)
View docs
ViduVideo

Vidu Q3 Mix

model: vidu-q3-mix (reference, 1~10s)

720P=78.2 / 1080P=93.8 / 2K=112.6 / 4K=135.2 credits/sec × duration (sec)
View docs
ViduVideo

Vidu Q3 AD

model: vidu-q3-ad (reference, 1~10s)

720P=78.2 / 1080P=93.8 / 2K=112.6 / 4K=135.2 credits/sec × duration (sec)
View docs
ViduVideo

Vidu Q3 Drama

model: vidu-q3-drama (reference, 1~10s)

1080P=87.5 / 2K=105 / 4K=126 credits/sec × duration (sec)
View docs
ViduVideo

Vidu Q2

model: vidu-q2 (text / reference, 1~10s)

text: 720P=32 / 1080P=47 / 2K=70 / 4K=105; reference: 540P=24 / 720P=32 / 1080P=82 / 2K=123 / 4K=184.5 credits/sec × duration (sec)
View docs
ViduVideo

Vidu Q2 Pro

model: vidu-q2-pro (image/first-last frame / reference, 1~10s)

image/first-last frame: 720P=35 / 1080P=70 / 2K=100 / 4K=150; reference: 540P=27 / 720P=35 / 1080P=90 / 2K=135 / 4K=202.5 credits/sec × duration (sec)
View docs
ViduVideo

Vidu Q2 Turbo

model: vidu-q2-turbo (image/first-last frame, 1~10s)

720P=25 / 1080P=47 / 2K=70 / 4K=105 credits/sec × duration (sec)
View docs
TencentVideo

HunyuanVideo 1.5

model: hunyuan-video-1.5 (text / image/first-last frame, 5s)

720P=30 / 1080P=50 / 2K=75 / 4K=112 credits/sec × duration (sec)
View docs
AIsphereVideo

PixVerse v5.6

model: pixverse-v5.6 (text / image/first-last frame, 5 / 8 / 10s)

540P=24.5 / 720P=31.5 / 1080P=52.5 / 2K=73.5 / 4K=102.9 credits/sec × duration (sec)
View docs
AIsphereVideo

PixVerse v6

model: pixverse-v6 (text / image/first-last frame, 5 / 8 / 10s)

540P=20.5 / 720P=26.4 / 1080P=52.8 / 2K=63.4 / 4K=76; with audio: 540P=26.4 / 720P=35.2 / 1080P=67.5 / 2K=81 / 4K=97.1 credits/sec × duration (sec)
View docs
AIsphereVideo

PixVerse C1

model: pixverse-c1 (text / image/first-last frame, 5 / 8 / 10s)

540P=23.5 / 720P=29.3 / 1080P=55.7 / 2K=66.9 / 4K=80.3; with audio: 540P=29.3 / 720P=38.1 / 1080P=70.4 / 2K=84.5 / 4K=101.4 credits/sec × duration (sec)
View docs
TencentVideo

Mingmou 1.0

model: mingmou-1.0 (text / image/first-last frame, 5s)

720P=30 / 1080P=50 / 2K=75 / 4K=112 credits/sec × duration (sec)
View docs
VProVideo

MiniMax H3 V

model: minimax-h3-v (text / image/first-last frame / reference, 4~15s)

480P=29.7 / 720P=37.5 / 1080P=50 / 2K=62.5 / 4K=75 credits/sec × duration (sec); +15 per reference image after the first 5
View docs
VProVideo

Seedance 2.0

model: seedance-2.0 (text / image/first-last frame / reference, 4~15s)

720P=79.5 / 1080P=173 / 2K=430 / 4K=490 credits/sec × duration (sec)
View docs
VProVideo

Seedance 2.0 Fast

model: seedance-2.0-fast (text / image/first-last frame / reference, 4~15s)

720P=64.5 / 1080P=140 / 2K=154 / 4K=169.4 credits/sec × duration (sec)
View docs
VProVideo

Seedance 2.5

model: seedance-2.5 (text / image/first-last frame / reference, 4~30s)

720P=118.8 / 1080P=258.7 / 2K=637 / 4K=700.7 credits/sec × duration (sec)
View docs
TencentVideo

Viral Clone · Advanced

model: viral-clone-flash (script / motion clone, 2~15s)

720P=136 / 1080P=323.5 credits/sec × duration (sec)
View docs
TencentVideo

Viral Clone · Pro

model: viral-clone-pro (script / motion clone, 4~30s)

720P=210 / 1080P=500 credits/sec × duration (sec)
View docs
OpenAIImage

gpt-image-1

model: gpt-image-1

4 credits
View docs
OpenAIImage

gpt-image-1.5

model: gpt-image-1.5

4 credits
View docs
OpenAIImage

gpt-image-2

model: gpt-image-2

6 credits
View docs
OpenAIImage

gpt-image-2.5-flare

model: gpt-image-2.5-flare

6 credits
View docs
OpenAIImage

gpt-image-2.5-sunburst

model: gpt-image-2.5-sunburst

6 credits
View docs
GoogleImage

Nano Banana

model: nano-banana

10 credits
View docs
GoogleImage

Nano Banana Pro

model: nano-banana-pro

20 credits
View docs
GoogleImage

Nano Banana 2

model: nano-banana-2

20 credits
View docs
GoogleImage

Nano Banana 2.1

model: nano-banana-2.1

20 credits
View docs
AlibabaImage

Qwen-Image 2.0

model: qwen-image-2.0

20 credits
View docs
AlibabaImage

Qwen-Image 2.0 Pro

model: qwen-image-2.0-pro

50 credits
View docs
AlibabaImage

Qwen-Image Max

model: qwen-image-max

50 credits
View docs
AlibabaImage

Qwen-Image Plus

model: qwen-image-plus-2026-01-09

20 credits
View docs
AlibabaImage

Qwen-Image Edit

model: qwen-image-edit-plus

20 credits
View docs
AlibabaImage

Wan2.7 Image

model: wan2.7-image

20 credits
View docs
AlibabaImage

Wan2.7 Image Pro (4K)

model: wan2.7-image-pro

50 credits
View docs
AlibabaImage

Wan2.5 Text-to-Image (preview)

model: wan2.5-t2i-preview

20 credits
View docs
AlibabaImage

Wan2.5 Image Edit / Multi-image Fusion (preview)

model: wan2.5-i2i-preview

20 credits
View docs
KuaishouImage

Kling Image 3.0

model: kling-image-3.0 (text / reference, ≤1 refs)

1K=20 / 2K=20 credits/image × images (1-9)
View docs
KuaishouImage

Kling Image 3.0 Omni

model: kling-image-3.0-omni (text / reference, ≤10 refs)

1K=20 / 2K=20 / 4K=40 credits/image × images (1-9)
View docs
KuaishouImage

Kling Image O1

model: kling-image-o1 (text / reference, ≤10 refs)

1K=20 / 2K=20 / 4K=40 credits/image × images (1-9)
View docs
KuaishouImage

Kling Image 2.1

model: kling-image-2.1 (text / reference / multi-reference, ≤4 refs)

text: 1K=10 / 2K=10; reference: 1K=20 / 2K=20; multi-reference(≥2): 1K=40 / 2K=48 credits/image × images (1-9)
View docs
ViduImage

Vidu Image Q2

model: vidu-image-q2 (text / reference / multi-reference, ≤7 refs)

text: 1K=18.8 / 2K=25 / 4K=31.3; reference: 1K=25 / 2K=37.5 / 4K=50; multi-reference(≥4): 1K=31.3 / 2K=62.5 / 4K=93.8 credits/image
View docs
TencentImage

Hunyuan Image 3.5 Preview

model: hunyuan-image-3.5-preview (text / reference, ≤3 refs, default output)

2K=15 credits/image
View docs
TencentImage

Hunyuan Image 3.0

model: hunyuan-image-3.0 (text / reference, ≤3 refs, default output)

1K=20 credits/image
View docs
TencentImage

Hunyuan World Panorama 2.1

model: hunyuan-world-panorama-2.1 (text)

500 credits/call
View docs
TencentImage

Mingmou Image 1.0

model: mingmou-image-1.0 (text, default output)

1K=30 credits/image
View docs
MidjourneyImage

Midjourney v8.2

model: mj-v8.2 (text)

30 credits/call (4 images)
View docs
MidjourneyImage

Midjourney v8.1

model: mj-v8.1 (text)

30 credits/call (4 images)
View docs
MidjourneyImage

Midjourney v7

model: mj-v7 (text)

30 credits/call (4 images)
View docs
MidjourneyImage

Midjourney niji 7

model: mj-niji7 (text)

30 credits/call (4 images)
View docs
ByteDanceImage

Seedream 5.0 Pro

model: seedream-5.0-pro (text / reference, ≤4 refs)

2K=60 / 4K=72 credits/image; +2 per reference image after the first 1
View docs
ByteDanceImage

Seedream 5.0 Lite

model: seedream-5.0-lite (text / reference, ≤4 refs)

2K=22 credits/image
View docs
ByteDanceImage

Seedream 4.5

model: seedream-4.5 (text / reference, ≤4 refs)

2K=25 / 4K=25 credits/image
View docs
ByteDanceImage

Seedream 4.0

model: seedream-4.0 (text / reference, ≤4 refs)

2K=20 / 4K=20 credits/image
View docs
AlibabaVideo

Wan2.7 Video · 720P

model: wan2.7-t2v / i2v / r2v · 720P

60 credits × duration
View docs
AlibabaVideo

Wan2.7 Video · 1080P

model: wan2.7-t2v / i2v / r2v · 1080P

100 credits × duration
View docs
AlibabaVideo

Wan2.5 Video · 480P (preview)

model: wan2.5-t2v-preview / i2v-preview (with audio) · 480P

30 credits × duration
View docs
AlibabaVideo

Wan2.5 Video · 720P (preview)

model: wan2.5-t2v-preview / i2v-preview (with audio) · 720P

60 credits × duration
View docs
AlibabaVideo

Wan2.5 Video · 1080P (preview)

model: wan2.5-t2v-preview / i2v-preview (with audio) · 1080P

100 credits × duration
View docs
AlibabaVideo

HappyHorse Video · 720P

model: happyhorse-1.0/1.1-t2v / i2v / r2v · 720P (duration 3-15)

90 credits × duration
View docs
AlibabaVideo

HappyHorse 1.0 Video · 1080P

model: happyhorse-1.0-t2v / i2v / r2v · 1080P (duration 3-15)

160 credits × duration
View docs
AlibabaVideo

HappyHorse 1.1 Video · 1080P

model: happyhorse-1.1-t2v / i2v / r2v · 1080P (duration 3-15)

120 credits × duration
View docs
AlibabaVideo

Wan3.0 All-in-One Video · 480P

model: wan3.0-video · 480P · all-in-one (text/image/reference-to-video; pass a reference image for image-to-video) · duration 2-30

30 credits × duration
View docs
AlibabaVideo

Wan3.0 All-in-One Video · 720P

model: wan3.0-video · 720P · all-in-one (text/image/reference-to-video; pass a reference image for image-to-video) · duration 2-30

60 credits × duration
View docs
AlibabaVideo

Wan3.0 All-in-One Video · 1080P

model: wan3.0-video · 1080P (default) · all-in-one (text/image/reference-to-video; pass a reference image for image-to-video) · duration 2-30

120 credits × duration
View docs
AlibabaVideo

Wan3.0 All-in-One Video · High-Speed · 480P

model: wan3.0-video-prime · 480P · high-speed variant (same capability, faster, ~1.5x price) · duration 2-30

45 credits × duration
View docs
AlibabaVideo

Wan3.0 All-in-One Video · High-Speed · 720P

model: wan3.0-video-prime · 720P · high-speed variant (same capability, faster, ~1.5x price) · duration 2-30

90 credits × duration
View docs
AlibabaVideo

Wan3.0 All-in-One Video · High-Speed · 1080P

model: wan3.0-video-prime · 1080P (default) · high-speed variant (same capability, faster, ~1.5x price) · duration 2-30

180 credits × duration
View docs
AlibabaVideo

Wan2.7 Video Edit (post-paid)

model: wan2.7-videoedit · 720P=60 / 1080P=100 credits/sec · Post-paid: no charge at submit; on success billed by real usage (~2x output seconds); nothing charged/refunded on failure

60 (720P) / 100 (1080P) credits × real usage (sec)
View docs
AlibabaVideo

HappyHorse 1.0 Video Edit (post-paid)

model: happyhorse-1.0-video-edit · 720P=90 / 1080P=160 credits/sec · Post-paid: no charge at submit; on success billed by real usage (~2x output seconds); nothing charged/refunded on failure

90 (720P) / 160 (1080P) credits × real usage (sec)
View docs
xAIVideo

grok-imagine-video

model: grok-imagine-video · custom duration (>=1, default 6) · multi reference · 480P/720P only

480P=6 / 720P=7 credits/sec × duration (sec)
View docs
xAIVideo

grok-imagine-video-1.5-preview

model: grok-imagine-video-1.5-preview · custom duration (>=1, default 6) · single reference only · 480P/720P only

480P=6 / 720P=7 credits/sec × duration (sec)
View docs
xAIVideo

grok-video-1.5-pro

model: grok-video-1.5-pro · custom duration (>=1, default 6) · 480P/540P/720P/1080P

480P/540P=5 / 720P=6 / 1080P=7 credits/sec × duration (sec)
View docs
xAIVideo

grok-video-1.5-max

model: grok-video-1.5-max · custom duration (>=1, default 6) · 480P/540P/720P/1080P

480P/540P=5 / 720P=6 / 1080P=7 credits/sec × duration (sec)
View docs
xAIVideo

grok-video-3-pro

model: grok-video-3-pro · fixed 10s · 480P/540P/720P/1080P

480P/540P=5 / 720P=6 / 1080P=7 credits/sec × 10s
View docs
xAIVideo

grok-video-3-max

model: grok-video-3-max · fixed 15s · 480P/540P/720P/1080P

480P/540P=4 / 720P=5 / 1080P=6 credits/sec × 15s
View docs
FFmpegMedia

Upload file upload

operation: upload · multipart file <=200MB, sync upload returns a CDN URL

Flat 1 credit/call (not charged on failure)
View docs
FFmpegMedia

Media probe probe

operation: probe · extract duration/resolution/bitrate/codec, instant

Flat 1 credit
View docs
FFmpegMedia

Thumbnail thumbnail

operation: thumbnail · single frame image, instant

Flat 1 credit
View docs
FFmpegMedia

Extract single frame extract_frame

operation: extract_frame · position grabs the last frame or a given second, png/jpg

Flat 1 credit
View docs
FFmpegMedia

Trim clip trim

operation: trim · cut by start/end time, stream-copy preferred

Factor 0.3 · 1 min 720P ~ 1 credit (by output length)
View docs
FFmpegMedia

Deep QC qc

operation: qc · inputUrl only; decodes the whole file twice and returns a JSON report of black/freeze/silence segments plus EBU R128 loudness

Factor 0.3 · 6 min 1080P ~ 10 credits (by source video length)
View docs
FFmpegMedia

Extract audio extract_audio

operation: extract_audio · mp3/aac/wav, resolution-independent

Factor 0.4 · 1 min 720P ~ 2 credits
View docs
FFmpegMedia

Mux audio mux

operation: mux · replace / add audio track

Factor 0.4 · 1 min 720P ~ 2 credits (by video length)
View docs
FFmpegMedia

Timeline audio mux mux_timeline

operation: mux_timeline · audioUrls multiple tracks + offsets timeline placement, replace/add

Factor 0.4 · 1 min 720P ~ 2 credits (by video length)
View docs
FFmpegMedia

Scale scale

operation: scale · 480p/720p/1080p

Factor 0.8 · 1 min 720P ~ 3 credits
View docs
FFmpegMedia

Compress compress

operation: compress · crf or targetBitrate to reduce size

Factor 1.0 · 1 min 720P ~ 3 credits
View docs
FFmpegMedia

Transcode transcode

operation: transcode · format/vcodec/acodec, baseline op

Factor 1.0 · 1 min 720P ~ 3 credits
View docs
FFmpegMedia

Concat videos concat

operation: concat · inputUrls 2-200 clips, mismatched codec/resolution auto re-encoded

Factor 1.0 · 1 min 720P ~ 3 credits (by total length)
View docs
FFmpegMedia

Concat with transitions concat_transition

operation: concat_transition · inputUrls multiple clips + transitions per-cut (crossfade/dip/none) + head/tail fade

Factor 1.0 · 1 min 720P ~ 3 credits (by total length)
View docs
FFmpegMedia

Character nameplate overlay_text

operation: overlay_text · overlays 1-4 lower-third nameplates (name + subtitle + time window + slot)

Factor 1.0 · 1 min 720P ~ 3 credits (by video length; nameplate count does not change the price)
View docs
FFmpegMedia

Video to GIF to_gif

operation: to_gif · fps/width/start/duration

Factor 1.2 · 1 min 720P ~ 4 credits (by output length)
View docs
FFmpegMedia

Extract frames frames

operation: frames · interval or fps, zipped, <=1000 frames

Factor 1.2 · 1 min 720P ~ 4 credits (by input length)
View docs
FFmpegMedia

Watermark watermark

operation: watermark · position/opacity/margin

Factor 1.3 · 1 min 720P ~ 4 credits
View docs
FFmpegMedia

Burn Subtitle burn_subtitle

operation: burn_subtitle · mode soft track / hard burn-in

Factor 1.3 · 1 min 720P ~ 4 credits
View docs
TencentMedia

Hunyuan 3D 3.1

model: hunyuan-3d-3.1 (full 3D asset, prompt or 1 reference image)

200 credits/call
View docs
TencentMedia

Hunyuan 3D 3.1 Geometry

model: hunyuan-3d-3.1-geometry (geometry only, prompt or 1 reference image)

100 credits/call
View docs
AlibabaAudio

File Transcription fun-asr

model: fun-asr · Chinese file transcription (with timestamps)

0.022 credits/sec (by audio length, ~1.32 credits/min)
View docs
AlibabaAudio

File Transcription (Multilingual) fun-asr-mtl

model: fun-asr-mtl · multilingual file transcription

0.022 credits/sec (by audio length, ~1.32 credits/min)
View docs
AlibabaAudio

File Transcription qwen3-asr-flash-filetrans

model: qwen3-asr-flash-filetrans · file transcription

0.022 credits/sec (by audio length, ~1.32 credits/min)
View docs
AlibabaAudio

Fast Recognition qwen3-asr-flash

model: qwen3-asr-flash · returns recognized text directly

0.022 credits/sec (by audio length, ~1.32 credits/min)
View docs
TTSMedia

Text to Speech /v1/tts

text→mp3 / mp3-high / webm · 32 curated CN/EN voices (322 in full catalog) · adjustable rate/pitch/volume · per-sentence control · optional SRT subtitles · synchronous

0.1 credits/sec (by synthesized audio length, 10s ~ 1 credit, 60s ~ 6 credits) · min 1 credit · subtitles free
View docs
TTSMedia

Qwen TTS qwen-audio-3.1-tts-flash

model: qwen-audio-3.1-tts-flash · multilingual & dialect voices · instruction and emotion tags · mp3 / wav · synchronous

Input 150 / output 1200 credits per 1M tokens (actual usage; a ~25-char sentence ≈ 0.08 credits)
View docs
TTSMedia

Qwen TTS qwen-audio-3.0-tts-flash

model: qwen-audio-3.0-tts-flash · instruction and emotion tags · mp3 / wav · synchronous

100 credits / 10k characters (actual usage)
View docs
TTSMedia

Qwen TTS qwen-audio-3.0-tts-plus

model: qwen-audio-3.0-tts-plus · instruction and emotion tags · mp3 / wav · synchronous

140 credits / 10k characters (actual usage)
View docs
TTSMedia

Qwen TTS qwen3-tts-flash

model: qwen3-tts-flash · 49 multilingual / dialect voices · wav · synchronous

80 credits / 10k characters (actual usage)
View docs

Prices are in platform credits (token models are credits/M); actual billing follows the final result. Provider / modality / tag are auto-classified for filtering only.

CQTAI

Copyright © 2025 CQTAI API Generator All rights reserved

Email: support@cqtai.com