How do I call the Qwen API through ATP Token?

Create a project API key, enable the Qwen (Alibaba) model ids you need on that project's model allowlist, point an OpenAI-compatible SDK at https://api.atptoken.ai/v1 and set model to the API id (for example qwen-3-7-flash).

How much does the Qwen API cost on ATP Token?

Prices for the 10 Qwen (Alibaba) models on ATP Token: input $0.03–$2.50 and output $0.13–$7.71 per 1M tokens; $0.0248–$0.0688 per image. Usage is billed in credits (USD 1 = 100 credits), debited from the project balance per completed request; failed requests are not billed. No monthly fee, USD 5 minimum top-up.

Which Qwen (Alibaba) model is cheapest on ATP Token?

By price (compared within each modality): Text: Qwen 3.7 Flash (qwen-3-7-flash) at $0.03 input / $0.13 output per 1M tokens; Image: Qwen Image 3.0 (qwen-image-3.0) from $0.0248 per image.

What are the newest Qwen (Alibaba) models on ATP Token?

The most recent Qwen (Alibaba) release we list is Qwen Image 3.0 (qwen-image-3.0), released by Qwen (Alibaba) on Aug 4, 2026. GET /v1/models lists the full set.

Do Qwen (Alibaba) models support tool calling and vision?

Per the capability flags in the ATP model catalog: of 8 text models, 8 support tool calling, 0 accept image (vision) input and 3 support extended thinking. Each model's flags are in the table above.

How do teams control who can use Qwen (Alibaba) models, and how much they spend?

Each project has its own API keys and model allowlist — a Qwen (Alibaba) model that isn't on the list can't be called with that project's key. Credits flow from organization to workspace to project with budget caps, every request is logged with project, key, model and credits debited, and all providers share one wallet and one bill.

Provider

Qwen API: models & pricing

Qwen 3.6–3.8 Flash, Plus and Max text models and Qwen Image 3.0. Call every one with a single ATP project key through an OpenAI-compatible gateway.

Get started free Read the docs

Models

Qwen (Alibaba)

Modalities

Text · Image

From

$0.13

per 1M output tokens

qwen-3-7-flash

Latest release

Qwen Image 3.0

Aug 4, 2026

qwen-image-3.0

Models

All Qwen (Alibaba) models on ATP

Prices in USD. Credits are deducted only when a request succeeds. Open a model for full pricing and an estimate.

Prices

USD · USD 1 = 100 credits

All Qwen (Alibaba) models on ATP
Model	Modality	Input / 1M	Output / rate	Capabilities
Qwen 3.6 Max `qwen-3-6-max` Positioning: Flagship. Price level 3 of 4 among text models.	Text	$1.29	$7.71in $1.29	Tools
Qwen 3.7 MaxNew `qwen-3-7-max` Positioning: Flagship. Price level 3 of 4 among text models.	Text	$2.50	$7.50in $2.50	Tools
Qwen 3.8 MaxNew `qwen-3-8-max` Positioning: Flagship. Price level 3 of 4 among text models.	Text	$2.00	$6.00in $2.00	Tools
Qwen 3.6 PlusNew `qwen-3-6-plus` Positioning: Balanced. Price level 2 of 4 among text models.	Text	$0.276	$1.651in $0.276tiered	ThinkingTools
Qwen 3.7 PlusNew `qwen-3-7-plus` Positioning: Balanced. Price level 2 of 4 among text models.	Text	$0.40	$1.60in $0.40tiered	Tools
Qwen 3.6 FlashNew `qwen-3-6-flash` Positioning: Economy. Price level 1 of 4 among text models.	Text	$0.165	$0.99in $0.165tiered	ThinkingTools
Qwen Plus CharacterNew `qwen-plus-character` Positioning: Economy. Price level 1 of 4 among text models.	Text	$0.115	$0.287in $0.115	Tools
Qwen 3.7 FlashNew `qwen-3-7-flash` Positioning: Economy. Price level 1 of 4 among text models.	Text	$0.03	$0.13in $0.03tiered	ThinkingTools
Qwen Image 3.0 ProNew `qwen-image-3.0-pro` Positioning: Flagship. Price level 2 of 4 among image models.	Image	—	$0.0344–$0.0688/ image	Vision
Qwen Image 3.0New `qwen-image-3.0` Positioning: Balanced. Price level 1 of 4 among image models.	Image	—	$0.0248/ image	Vision

On ATP

How teams use Qwen (Alibaba) on ATP

The same Qwen (Alibaba) models, with the controls a company needs around them: who can call which model, from which project, within what budget, and a record of every request.

Project API keys
Every key belongs to one project and inherits its models and balance. Revoke one at any time without touching the rest.
Model allowlist per project
Enable only the Qwen (Alibaba) models a project needs. Anything off the list can't be called with that project's keys.
Budgets
Credits flow from organization to workspace to project. The allocation is the cap, so one team can't spend another team's budget.
Per-request logs
Each call is recorded with its project, key, model, usage and credits debited, so spend is attributable down to a single request.
One wallet, one bill
Qwen (Alibaba) and the other 10 providers on ATP draw from the same prepaid credits. No separate vendor contracts or invoices.

quickstart.py · OpenAI SDK

from openai import OpenAI

client = OpenAI(
  base_url="https://api.atptoken.ai/v1",
  api_key="atp-•••",
)

r = client.chat.completions.create(
  model="qwen-3-7-flash",
  messages=[{"role": "user", "content": "hi"}],
)
print(r.choices[0].message.content)

Point an existing SDK or HTTP client at ATP and set the model id. Confirm what your key can call with GET /v1/models. Full guide in the docs

Governance treeSample

Organization  Northwind Labs · 9,842 credits
├─ Workspace  Product
│  ├─ Project  support-bot   budget ■■■■■■□□□□  62%
│  │           models: qwen-3-7-flash, gpt-5.5
│  └─ Project  web-app       budget ■■■■□□□□□□  38%
│              models: gpt-5.5, deepseek-v4-flash
└─ Workspace  Media lab
   └─ Project  video-lab     budget ■■■■■■■■■■ 100%
               limit reached · models: seedance-2-0, kling-v3-pro

Organization  Northwind Labs · 9,842 credits
├─ Workspace  Product
│  ├─ ■■■■■■□□□□  62%  support-bot
│  │  models: qwen-3-7-flash,
│  │          gpt-5.5
│  └─ ■■■■□□□□□□  38%  web-app
│     models: gpt-5.5,
│             deepseek-v4-flash
└─ Workspace  Media lab
   └─ ■■■■■■■■■■ 100%  video-lab
      limit reached
      models: seedance-2-0,
              kling-v3-pro

FAQ

Qwen API on ATP: FAQ

FAQ

How do I call the Qwen API through ATP Token?: Create a project API key, enable the Qwen (Alibaba) model ids you need on that project's model allowlist, point an OpenAI-compatible SDK at https://api.atptoken.ai/v1 and set model to the API id (for example qwen-3-7-flash).
How much does the Qwen API cost on ATP Token?: Prices for the 10 Qwen (Alibaba) models on ATP Token: input $0.03–$2.50 and output $0.13–$7.71 per 1M tokens; $0.0248–$0.0688 per image. Usage is billed in credits (USD 1 = 100 credits), debited from the project balance per completed request; failed requests are not billed. No monthly fee, USD 5 minimum top-up.
Which Qwen (Alibaba) model is cheapest on ATP Token?: By price (compared within each modality): Text: Qwen 3.7 Flash (qwen-3-7-flash) at $0.03 input / $0.13 output per 1M tokens; Image: Qwen Image 3.0 (qwen-image-3.0) from $0.0248 per image.
What are the newest Qwen (Alibaba) models on ATP Token?: The most recent Qwen (Alibaba) release we list is Qwen Image 3.0 (qwen-image-3.0), released by Qwen (Alibaba) on Aug 4, 2026. GET /v1/models lists the full set.
Do Qwen (Alibaba) models support tool calling and vision?: Per the capability flags in the ATP model catalog: of 8 text models, 8 support tool calling, 0 accept image (vision) input and 3 support extended thinking. Each model's flags are in the table above.
How do teams control who can use Qwen (Alibaba) models, and how much they spend?: Each project has its own API keys and model allowlist — a Qwen (Alibaba) model that isn't on the list can't be called with that project's key. Credits flow from organization to workspace to project with budget caps, every request is logged with project, key, model and credits debited, and all providers share one wallet and one bill.

More providers

All providers Compare every price in the table Browse the full model catalog

Get started

One key for Qwen (Alibaba) and every other model.

Get started free Talk to enterprise

Qwen API: models & pricing

All Qwen (Alibaba) models on ATP

How teams use Qwen (Alibaba) on ATP

Project API keys

Model allowlist per project

Budgets

Per-request logs

One wallet, one bill

Qwen API on ATP: FAQ

Other providers on the same key

One key for Qwen (Alibaba) and every other model.