Skip to main content
QwenCloud home page
Docs
Getting Started

Model pricing

Full per-model unit-price reference: text, image, video, audio, embeddings, and reranking.

Unit prices for real-time inference on QwenCloud models, in USD. Prices follow the console: Models shows live unit prices, discounts, and free tiers per model; the API pricing page lists flagship-model pricing. This page is a lookup table for full-coverage search and side-by-side comparison. Billing rules are in Pricing. Model IDs containing / are third-party direct models — enable the provider's service in the console before calling.

Text generation

ModelModeInput tokens per requestInput (USD/1M tokens)Output (USD/1M tokens)Implicit cache (USD/1M tokens)Explicit cache creation (USD/1M tokens)Explicit cache read (USD/1M tokens)
qwen-flashFlatInput ≤ 256K0.050.40.010.0630.005
qwen-flashFlat256K < Input ≤ 1M0.2520.050.3130.025
qwen-flash-2025-07-28FlatInput ≤ 256K0.050.4---
qwen-flash-2025-07-28Flat256K < Input ≤ 1M0.252---
qwen-flash-characterFlatFlat0.050.40.01--
qwen-maxFlatFlat1.66.40.32--
qwen-mt-flashFlatFlat0.160.49---
qwen-mt-liteFlatFlat0.120.36---
qwen-mt-plusFlatFlat2.467.37---
qwen-plusStandardInput ≤ 256K0.41.20.080.50.04
qwen-plusThinkingInput ≤ 256K0.440.080.50.04
qwen-plusStandard256K < Input ≤ 1M1.23.60.241.50.12
qwen-plusThinking256K < Input ≤ 1M1.2120.241.50.12
qwen-plus-2025-01-25FlatFlat0.41.2---
qwen-plus-2025-04-28StandardFlat0.41.2---
qwen-plus-2025-04-28ThinkingFlat0.44---
qwen-plus-2025-07-14StandardFlat0.41.2---
qwen-plus-2025-07-14ThinkingFlat0.44---
qwen-plus-2025-12-01StandardInput ≤ 256K0.41.2---
qwen-plus-2025-12-01ThinkingInput ≤ 256K0.44---
qwen-plus-2025-12-01Standard256K < Input ≤ 1M1.23.6---
qwen-plus-2025-12-01Thinking256K < Input ≤ 1M1.212---
qwen-plus-characterFlatFlat0.51.40.1--
qwen-plus-character-jaFlatFlat0.51.40.1--
qwen-plus-latestStandardInput ≤ 256K0.41.2---
qwen-plus-latestThinkingInput ≤ 256K0.44---
qwen-plus-latestStandard256K < Input ≤ 1M1.23.6---
qwen-plus-latestThinking256K < Input ≤ 1M1.212---
qwen-vl-ocrFlatFlat0.070.16---
qwen-vl-ocr-2025-11-20FlatFlat0.070.16---
qwen3-coder-flashFlatInput ≤ 32K0.31.50.060.3750.03
qwen3-coder-flashFlat32K < Input ≤ 128K0.52.50.10.6250.05
qwen3-coder-flashFlat128K < Input ≤ 256K0.840.1610.08
qwen3-coder-flashFlat256K < Input ≤ 1M1.69.60.3220.16
qwen3-coder-flash-2025-07-28FlatInput ≤ 32K0.31.5---
qwen3-coder-flash-2025-07-28Flat32K < Input ≤ 128K0.52.5---
qwen3-coder-flash-2025-07-28Flat128K < Input ≤ 256K0.84---
qwen3-coder-flash-2025-07-28Flat256K < Input ≤ 1M1.69.6---
qwen3-vl-plusFlatInput ≤ 32K0.21.60.040.250.02
qwen3-vl-plusFlat32K < Input ≤ 128K0.32.40.060.3750.03
qwen3-vl-plusFlat128K < Input ≤ 256K0.64.80.120.750.06
qwen3.5-122b-a10bFlatFlat0.43.2---
qwen3.5-27bFlatFlat0.32.4---
qwen3.5-35b-a3bFlatFlat0.252---
qwen3.5-397b-a17bFlatFlat0.63.6---
qwen3.5-flashFlatFlat0.10.4-0.1250.01
qwen3.5-flash-2026-02-23FlatFlat0.10.4---
qwen3.5-plusFlatInput ≤ 256K0.42.4-0.50.04
qwen3.5-plusFlat256K < Input ≤ 1M0.53-0.6250.05
qwen3.5-plus-2026-02-15FlatInput ≤ 256K0.42.4---
qwen3.5-plus-2026-02-15Flat256K < Input ≤ 1M0.53---
qwen3.5-plus-2026-04-20FlatInput ≤ 256K0.42.4-0.50.04
qwen3.5-plus-2026-04-20Flat256K < Input ≤ 1M0.53-0.6250.05
qwen3.6-27bFlatFlat0.63.6---
qwen3.6-35b-a3bFlatFlat0.3752.25---
qwen3.6-flashFlatInput ≤ 256K0.251.5-0.31250.025
qwen3.6-flashFlat256K < Input ≤ 1M14-1.250.1
qwen3.6-flash-2026-04-16FlatInput ≤ 256K0.251.5---
qwen3.6-flash-2026-04-16Flat256K < Input ≤ 1M14---
qwen3.6-plusFlatInput ≤ 256K0.53-0.6250.05
qwen3.6-plusFlat256K < Input ≤ 1M26-2.50.2
qwen3.6-plus-2026-04-02FlatInput ≤ 256K0.53---
qwen3.6-plus-2026-04-02Flat256K < Input ≤ 1M26---
qwen3.7-flashFlatInput ≤ 32K0.030.130.0060.0380.003
qwen3.7-flashFlat32K < Input ≤ 256K0.10.40.020.1250.01
qwen3.7-flashFlat256K < Input ≤ 1M0.20.80.040.250.02
qwen3.7-flash-2026-07-15FlatInput ≤ 32K0.030.130.0060.0380.003
qwen3.7-flash-2026-07-15Flat32K < Input ≤ 256K0.10.40.020.1250.01
qwen3.7-flash-2026-07-15Flat256K < Input ≤ 1M0.20.80.040.250.02
qwen3.7-maxFlatFlat2.57.50.53.1250.25
qwen3.7-max-2026-05-17FlatFlat2.57.5---
qwen3.7-max-2026-05-20FlatFlat2.57.5-3.1250.25
qwen3.7-max-2026-06-08FlatFlat2.57.50.53.1250.25
qwen3.7-max-previewFlatFlat2.57.5---
qwen3.7-plus(limited-time 20% off)FlatInput ≤ 256K0.32 (list 0.4)1.28 (list 1.6)0.064 (list 0.08)0.4 (list 0.5)0.032 (list 0.04)
qwen3.7-plus(limited-time 20% off)Flat256K < Input ≤ 1M0.96 (list 1.2)3.84 (list 4.8)0.192 (list 0.24)1.2 (list 1.5)0.096 (list 0.12)
qwen3.7-plus-2026-05-26FlatInput ≤ 256K0.41.60.080.50.04
qwen3.7-plus-2026-05-26Flat256K < Input ≤ 1M1.24.80.241.50.12
qwen3.8-2.4t-a95bFlatFlat260.252.50.17
qwen3.8-27bFlatFlat0.530.10.6250.05
qwen3.8-flashFlatFlat0.150.470.0160.20.016
qwen3.8-maxFlatFlat260.252.50.17
qwen3.8-max-0902FlatFlat260.252.50.17
deepseek-v4-flash-0731PeakFlat0.441.320.044--
deepseek-v4-flash-0731Off-peakFlat0.220.660.022--
deepseek-v4-proFlatFlat2.44.80.2--
deepseek-v4-pro-0813PeakFlat1.323.960.132--
deepseek-v4-pro-0813Off-peakFlat0.661.980.066--
deepseek-v4.1-flashPeakFlat0.31.20.03--
deepseek-v4.1-flashOff-peakFlat0.150.60.015--
glm-5.1FlatFlat1.44.40.26--
glm-5.2FlatFlat1.44.40.28--
glm-5.2-fast-previewFlatFlat2.88.80.56--
glm-5.3FlatFlat1.44.40.28--
glm-5.3-primeFlatFlat2.88.80.56--
kimi-k2.7-codeFlatFlat0.9540.19--
kimi-k3FlatFlat3150.3--
kimi/kimi-k3FlatFlat3150.3--
ZHIPU/GLM-5.2FlatFlat1.44.40.26--
ZHIPU/GLM-5.3FlatFlat1.44.40.26--
ModelBilling dimensionUnit price (USD/sec)
wan2.2-kf2v-flashVideo Generation(480P)0.015
wan2.2-kf2v-flashVideo Generation(720P)0.036
wan2.2-kf2v-flashVideo Generation(1080P)0.07

Free-trial models

ModelNotes
decision-model-previewFree during preview

Image generation

ModelTierImage input (USD/image)Image generation (USD/image)
qwen-image-2.0Flat-0.035
qwen-image-2.0-2026-03-03Flat-0.035
qwen-image-2.0-proFlat-0.075
qwen-image-2.0-pro-2026-03-03Flat-0.075
qwen-image-2.0-pro-2026-04-22Flat-0.075
qwen-image-2.0-pro-2026-06-22Flat-0.075
qwen-image-2.1-proFlat-0.04
qwen-image-2.1-turboFlat-0.016
qwen-image-3.0Output 1K0.0030.03
qwen-image-3.0Output 2K0.0030.03
qwen-image-3.0-proOutput 1K0.0030.04
qwen-image-3.0-proOutput 2K0.0030.075
qwen-mt-image-2.0Flat-0.0006
wan2.1-t2i-plusFlat-0.05
wan2.1-t2i-turboFlat-0.025
wan2.2-t2i-flashFlat-0.025
wan2.2-t2i-plusFlat-0.05
wan2.5-i2i-previewFlat-0.03
wan2.5-t2i-previewFlat-0.03
wan2.6-imageFlat-0.03
wan2.6-t2iFlat-0.03
wan2.7-imageFlat-0.03
wan2.7-image-proFlat-0.075
z-image-turboPrompt rewrite off-0.015
z-image-turboPrompt rewrite on-0.03
vidu/vidu-image_reference2imageOutput 1K-0.1
vidu/vidu-image_reference2imageOutput 2K-0.16
vidu/vidu-image_reference2imageOutput 4K-0.24

Video generation

Output video only

ModelOutput tierOutput video unit price (USD/sec)
wan2.1-i2v-plus(std)0.1
wan2.1-i2v-turbo(std)0.036
wan2.1-kf2v-plus(std)0.1
wan2.1-t2v-plus(720P)0.1
wan2.1-t2v-turbo(480P)0.036
wan2.1-t2v-turbo(720P)0.036
wan2.1-vace-plus(std)0.1
wan2.2-animate-mix(std)0.18
wan2.2-animate-mix(pro)0.26
wan2.2-animate-move(std)0.12
wan2.2-animate-move(pro)0.18
wan2.2-i2v-flash(480P)0.015
wan2.2-i2v-flash(720P)0.036
wan2.2-i2v-plus(480P)0.02
wan2.2-i2v-plus(1080P)0.1
wan2.2-t2v-plus(480P)0.02
wan2.2-t2v-plus(1080P)0.1
wan2.5-i2v-preview(480P)0.05
wan2.5-i2v-preview(720P)0.1
wan2.5-i2v-preview(1080P)0.15
wan2.5-t2v-preview(480P)0.05
wan2.5-t2v-preview(720P)0.1
wan2.5-t2v-preview(1080P)0.15
wan2.6-i2v-flash(720P)0.05
wan2.6-i2v-flash(1080P)0.075
wan2.6-i2v-flash(720P no audio)0.025
wan2.6-i2v-flash(1080P no audio)0.0375
wan2.7-i2v(720P)0.1
wan2.7-i2v(1080P)0.15
wan2.7-i2v-2026-04-25(720P)0.1
wan2.7-i2v-2026-04-25(1080P)0.15
wan2.7-t2v(720P)0.1
wan2.7-t2v(1080P)0.15
wan2.7-t2v-2026-04-25(720P)0.1
wan2.7-t2v-2026-04-25(1080P)0.15
wan2.7-t2v-2026-06-12(720P)0.1
wan2.7-t2v-2026-06-12(1080P)0.15
happyhorse-1.0-i2v(720P)0.14
happyhorse-1.0-i2v(1080P)0.24
happyhorse-1.0-r2v(720P)0.14
happyhorse-1.0-r2v(1080P)0.24
happyhorse-1.0-t2v(720P)0.14
happyhorse-1.0-t2v(1080P)0.24
happyhorse-1.1-i2v(480P)0.07
happyhorse-1.1-i2v(720P)0.14
happyhorse-1.1-i2v(1080P)0.18
happyhorse-1.1-r2v(480P)0.07
happyhorse-1.1-r2v(720P)0.14
happyhorse-1.1-r2v(1080P)0.18
happyhorse-1.1-t2v(480P)0.07
happyhorse-1.1-t2v(720P)0.14
happyhorse-1.1-t2v(1080P)0.18
vidu/viduq2-pro-fast_img2video(720P)0.016
vidu/viduq2-pro-fast_img2video(1080P)0.032
vidu/viduq3-ad_reference2video(720P)0.125
vidu/viduq3-ad_reference2video(1080P)0.15
vidu/viduq3-drama_reference2video(720P)0.14
vidu/viduq3-drama_reference2video(1080P)0.14
vidu/viduq3-mix_reference2video(720P)0.12
vidu/viduq3-mix_reference2video(1080P)0.145

Both input and output video billed

ModelOutput tierInput & output video unit price (USD/sec)Billed input video seconds
wan2.6-r2v(720P)0.1Up to 5 sec, split across reference materials
wan2.6-r2v(1080P)0.15Up to 5 sec, split across reference materials
wan2.6-r2v-flash(720P)0.05Up to 5 sec, split across reference materials
wan2.6-r2v-flash(1080P)0.075Up to 5 sec, split across reference materials
wan2.6-r2v-flash(720P no audio)0.025Up to 5 sec, split across reference materials
wan2.6-r2v-flash(1080P no audio)0.0375Up to 5 sec, split across reference materials
wan2.7-r2v(720P)0.1Up to 5 sec, split across reference materials
wan2.7-r2v(1080P)0.15Up to 5 sec, split across reference materials
wan2.7-r2v-2026-06-12(720P)0.1Up to 5 sec, split across reference materials
wan2.7-r2v-2026-06-12(1080P)0.15Up to 5 sec, split across reference materials
wan2.7-videoedit(720P)0.1All
wan2.7-videoedit(1080P)0.15All
wan3.0-video(limited-time 30% off)(480P)0.035 (list 0.05)All
wan3.0-video(limited-time 30% off)(720P)0.07 (list 0.1)All
wan3.0-video(limited-time 30% off)(1080P)0.14 (list 0.2)All
wan3.0-video-prime(480P)0.068All
wan3.0-video-prime(720P)0.14All
wan3.0-video-prime(1080P)0.28All
happyhorse-1.0-video-edit(720P)0.14All
happyhorse-1.0-video-edit(1080P)0.24All

Free-trial models

ModelNotes
wan2.6-i2vFree trial only; unavailable after free quota is exhausted
wan2.6-t2vFree trial only; unavailable after free quota is exhausted

Text-to-speech

ModelInput text (USD/10K chars)
qwen-audio-3.0-tts-flash0.15
qwen-audio-3.0-tts-plus0.2
qwen3-tts-flash0.1
qwen3-tts-flash-realtime0.13
cosyvoice-v3-flash0.13
cosyvoice-v3-plus0.26
ModelVoice enrollment (USD/voice)
qwen-voice-enrollment0.01
ModelInput (USD/1M tokens)Output (USD/1M tokens)
qwen-audio-3.1-tts-flash0.231.87

Speech-to-text

ModelInput audio duration (USD/sec)
qwen-audio-3.0-asr-flash0.000035
qwen-audio-3.0-asr-flash-filetrans0.000035
qwen-audio-3.0-asr-flash-streaming0.00009
qwen3-asr-flash0.000035
qwen3-asr-flash-filetrans0.000035
qwen3-asr-flash-realtime0.00009
fun-asr0.000035
fun-asr-flash-2026-06-150.000035
ModelInput (USD/1M tokens)Output (USD/1M tokens)
qwen-audio-3.1-asr-flash0.150.47
qwen-audio-3.1-asr-flash-filetrans0.150.47
qwen-audio-3.1-asr-flash-message0.930.7
qwen-audio-3.1-asr-flash-streaming0.930.7

Free-trial models

ModelNotes
fun-asr-realtimeFree trial only; unavailable after free quota is exhausted

Voice chat

ModelBilling dimensionUnit price (USD/1M tokens)
qwen-audio-3.0-realtime-flashInput: Audio0.93
qwen-audio-3.0-realtime-flashInput: Text0.23
qwen-audio-3.0-realtime-flashOutput: Text0.7
qwen-audio-3.0-realtime-flashOutput: Audio1.87
qwen-audio-3.0-realtime-plusInput: Audio6.4
qwen-audio-3.0-realtime-plusInput: Text0.8
qwen-audio-3.0-realtime-plusOutput: Text6.4
qwen-audio-3.0-realtime-plusOutput: Audio24
qwen-audio-3.1-realtime-plusInput: Audio6.4
qwen-audio-3.1-realtime-plusInput: Text0.8
qwen-audio-3.1-realtime-plusOutput: Text6.4
qwen-audio-3.1-realtime-plusOutput: Audio24
qwen3-omni-flashInput: Text0.43
qwen3-omni-flashInput: Audio3.81
qwen3-omni-flashInput: Vision0.78
qwen3-omni-flashOutput: Text (When input contains only text)1.66
qwen3-omni-flashOutput: Text (When input contains images/audio/video)3.06
qwen3-omni-flashOutput: Audio15.11
qwen3-omni-flashInput: Text(Thinking)0.43
qwen3-omni-flashInput: Audio(Thinking)3.81
qwen3-omni-flashInput: Vision(Thinking)0.78
qwen3-omni-flashOutput: Text (in thinking mode, when input contains only text)1.66
qwen3-omni-flashOutput: Text (in thinking mode, when the input contains images/audio/video)3.06
qwen3-omni-flash-realtime-2025-09-15Input: Text0.52
qwen3-omni-flash-realtime-2025-09-15Input: Audio4.57
qwen3-omni-flash-realtime-2025-09-15Input: Vision0.94
qwen3-omni-flash-realtime-2025-09-15Output: Text (When input contains only text)1.99
qwen3-omni-flash-realtime-2025-09-15Output: Text (When input contains images/audio/video)3.67
qwen3-omni-flash-realtime-2025-09-15Output: Audio18.13
qwen3.5-omni-flashInput: Audio3
qwen3.5-omni-flashOutput: Audio11.9
qwen3.5-omni-flashInput: Text/Image/Video0.4
qwen3.5-omni-flashOutput: Text2.2
qwen3.5-omni-flash-2026-03-15Input: Audio3
qwen3.5-omni-flash-2026-03-15Output: Audio11.9
qwen3.5-omni-flash-2026-03-15Input: Text/Image/Video0.4
qwen3.5-omni-flash-2026-03-15Output: Text2.2
qwen3.5-omni-flash-realtimeInput: Audio4.5
qwen3.5-omni-flash-realtimeOutput: Audio17.7
qwen3.5-omni-flash-realtimeInput: Text/Image/Video0.55
qwen3.5-omni-flash-realtimeOutput: Text3.3
qwen3.5-omni-flash-realtime-2026-03-15Input: Audio4.5
qwen3.5-omni-flash-realtime-2026-03-15Output: Audio17.7
qwen3.5-omni-flash-realtime-2026-03-15Input: Text/Image/Video0.55
qwen3.5-omni-flash-realtime-2026-03-15Output: Text3.3
qwen3.5-omni-plusInput: Audio11
qwen3.5-omni-plusOutput: Audio44
qwen3.5-omni-plusInput: Text/Image/Video1.4
qwen3.5-omni-plusOutput: Text8.3
qwen3.5-omni-plus-2026-03-15Input: Audio11
qwen3.5-omni-plus-2026-03-15Output: Audio44
qwen3.5-omni-plus-2026-03-15Input: Text/Image/Video1.4
qwen3.5-omni-plus-2026-03-15Output: Text8.3
qwen3.5-omni-plus-realtimeInput: Audio16.5
qwen3.5-omni-plus-realtimeOutput: Audio62
qwen3.5-omni-plus-realtimeInput: Text/Image/Video2.1
qwen3.5-omni-plus-realtimeOutput: Text12.4
qwen3.5-omni-plus-realtime-2026-03-15Input: Audio16.5
qwen3.5-omni-plus-realtime-2026-03-15Output: Audio62
qwen3.5-omni-plus-realtime-2026-03-15Input: Text/Image/Video2.1
qwen3.5-omni-plus-realtime-2026-03-15Output: Text12.4
qwen3.8-omni-flashInput0.15
qwen3.8-omni-flashOutput0.47
qwen3.8-omni-flashInput(Implicit Cache)0.016
qwen3.8-omni-flash-realtimeInput: Audio0.93
qwen3.8-omni-flash-realtimeOutput: Text0.7
qwen3.8-omni-flash-realtimeOutput: Audio1.87
qwen3.8-omni-flash-realtimeInput: Text/Image/Video0.23

Embeddings & reranking

ModelText input (USD/1M tokens)Image/video input (USD/1M tokens)
qwen3-rerank0.1-
qwen3.7-text-embedding0.07-
tongyi-embedding-vision-flash0.090.03
tongyi-embedding-vision-plus0.090.09
text-embedding-v30.07-
text-embedding-v40.07-

Realtime translation

ModelInput · Audio (USD/1M tokens)Input · Image (USD/1M tokens)Output · Text (USD/1M tokens)Output · Audio (USD/1M tokens)
qwen3.5-livetranslate-flash-realtime7.50.552030
qwen3.5-livetranslate-flash-realtime-2026-05-197.50.552030
qwen3.8-livetranslate-flash-realtime7.50.552030

Free-trial models

ModelNotes
qwen3-livetranslate-flashFree trial only; unavailable after free quota is exhausted
qwen3-livetranslate-flash-2025-12-01Free trial only; unavailable after free quota is exhausted

World models

ModelBilling dimensionUnit price (USD/sec)
happyoyster-1.0-adventureWorld Experience (480P)0.0308
happyoyster-1.0-directingWorld Experience (480P)0.0539
happyoyster-1.0-directingWorld Experience (720P)0.0858
ModelBilling dimensionUnit price (USD/voice)
happyoyster-1.0-adventureWorld Creation0.0077
happyoyster-1.0-directingWorld Creation (No Reference Image)0.3113
happyoyster-1.0-directingWorld Creation (With Reference Image)0.0077
happyoyster-1.0-directingPrompt Injection0.0154

Learn more

Model pricing - QwenCloud