Skip to main content
Qwen Cloud home page
Docs
Getting Started

Pricing

Pay-as-you-go pricing for API usage

Billing varies by model type: text models charge per token, image generation per image, video generation per second, and speech models per character or per second of audio.

Text generation

Billed per million tokens. Models with long-context support use tiered pricing — longer prompts cost more per token.
ModelContext tierInputOutput
qwen3.6-plus≤ 256K$0.50$3.00
256K – 1M$2.00$6.00
qwen3.5-plus≤ 256K$0.40$2.40
256K – 1M$0.50$3.00
qwen3.5-flash≤ 1M$0.10$0.40
qwen3-max≤ 32K$1.20$6.00
32K – 128K$2.40$12.00
128K – 252K$3.00$15.00
For complete text model pricing, see Model Marketplace.

Images & videos

Understanding

Vision understanding is billed per token. Qwen text generation models (qwen3.6-plus, etc.) support vision input at the same token price listed above. Dedicated vision models have separate pricing:
ModelContext tierInputOutput
qwen3-vl-plus≤ 32K$0.20$1.60
32K – 128K$0.30$2.40
128K – 256K$0.60$4.80
qwen3-vl-flash≤ 32K$0.05$0.40
32K – 128K$0.075$0.60
128K – 256K$0.12$0.96
Image and video inputs are automatically converted to tokens. The conversion varies by model:
Model familyImage conversionExample (1024×1024)
Qwen (qwen3.6-plus, etc.)1 token per 32×32 pixels≈ 256 tokens
Qwen-VL (qwen3-vl, etc.)1 token per 32×32 pixels≈ 256 tokens
Qwen3-Omni-Flash1 token per 32×32 pixels≈ 256 tokens
Video tokens = sampled frames × tokens per frame. See Token counting → for details.

Generation

Image generation is billed per image (resolution-independent). Video generation is billed per second of output video. Image generation
ModelPrice per image
qwen-image-2.0-pro$0.075
qwen-image-2.0$0.035
qwen-image-edit$0.045
wan2.6-t2i$0.03
wan2.6-image$0.03
z-image-turbo$0.015 (prompt rewrite off) / $0.03 (on)
Video generation
ModelPrice per second
wan2.6-t2v$0.10
wan2.6-i2v$0.10
wan2.6-i2v-flash$0.05
For all image and video model pricing, see Model Marketplace.

Audio & speech

Text to speech

Billed per 10,000 characters of input text.
ModelPrice per 10K chars
cosyvoice-v3-plus$0.22
cosyvoice-v3-flash$0.116
qwen3-tts-flash$0.10

Speech to text

Billed per second of audio input.
ModelPrice per second
fun-asr$0.000035
fun-asr-realtime$0.00009
qwen3-asr-flash$0.000035

Speech to speech

Qwen-Omni is a multimodal model that handles text, audio, and image/video in a single call. All modality prices are listed in the table below.
Billed per million tokens, with different rates per modality. Token conversion
Input typeConversion rate
TextStandard tokenizer
Audio≈ 12.5 tokens/sec (Qwen3-Omni-Flash) or 25 tokens/sec (Qwen-Omni-Turbo)
Image/VideoSee Understanding section above
qwen3-omni-flash pricing
ModalityPrice per 1M tokens
Text input (pure text)$0.43
Text input (multimodal context)$1.66
Audio input$3.81
Image/Video input$0.78
Text output$3.06
Text + Audio output$15.11
For all speech model pricing, see Model Marketplace.

Embedding & reranking

Billed per million input tokens (output is not charged). Multimodal embedding models may charge different rates for image vs text input. Image/video token conversion for embedding models is handled internally — check the usage field in the API response for actual token counts.
ModelModalityPrice per 1M tokens
text-embedding-v4Text$0.07
tongyi-embedding-vision-plusAll$0.09
tongyi-embedding-vision-flashImage/Video$0.03
Text$0.09
qwen3-rerankText$0.10
For all embedding and reranking model pricing, see Model Marketplace.

Built-in tools

Some built-in tools incur per-call fees in addition to model token costs.
ToolFeeNotes
Web Search$10 / 1K calls
Web ExtractorFREELimited time
Code InterpreterFREELimited time
Image Search$8 / 1K callsText-to-image and image-to-image
Function calling and MCP have no tool fees — tool descriptions count as input tokens.

Free quota

New users get 1 million free tokens per model for 90 days. Applies to real-time API calls only. Learn more →

Save on costs

Batch and cache discounts cannot be combined on the same request.
For worked examples and advanced strategies, see Cost optimization →.

Learn more