TokenLX — One API for 235+ AI Models

Text-to-image model. Generates original images from natural-language prompts.

Key strengths

Prompt-driven generation
Multiple resolutions
Seed control
Negative prompts

Use cases

Marketing assets
Blog illustrations
Product concepts
Storyboards

Alibaba's alibaba/wanx2.1-turbo is a high-fidelity video generation model. It supports text-to-video and image-to-video workflows with configurable duration, aspect ratio, and resolution, plus first-frame and last-frame control for guided scene composition.

Generates cinematic clips with consistent motion, camera control, and optional native audio. Billed per second of generated content.

alibaba/wanx2.1-turbo is fully OpenAI-compatible — drop in your existing OpenAI Python or Node SDK and switch `baseURL` to `https://api.tokenlx.ai`. TokenLX transparently routes your requests to the optimal provider endpoint while preserving streaming, function-calling, and structured-output semantics.

Performance

Compare different providers across TokenLX · All locations.

Throughput

tok/s

Latency

143

E2E Latency

200

Tool Call Errors

0.07

Output Errors

0.36

Time to First Token

103

Effective Pricing

Pricing is shown by the model billing method, using per-call or per-second prices and resolution tiers.

Per second

$0.04

Per duration

Resolution pricing · with audio

480P

$0.04

720P

$0.04

Recent activity

Total usage per day on TokenLX (last 30 days).

Prompt

27.25M

Completion

64.04M

30d ago15d agotoday

Sample code & API

TokenLX normalizes requests and responses across providers. Use any OpenAI SDK or our native SDK.

# ─── 文生视频示例 ───
import requests, time

headers = {"Authorization": "Bearer sk-tokenlx-...", "Content-Type": "application/json"}

resp = requests.post(
    "https://api.tokenlx.ai/v1/aigc/video/tasks",
    headers=headers,
    json={
        "model": "wanx2.1-turbo",
        "prompt": "都市街头延时摄影，车流如织",
        "duration": 5,
        "size": "1280*720",
    },
)
task = resp.json()
task_id = task.get("taskId") or task.get("task_id") or task.get("id")

# 轮询结果
while True:
    result = requests.get(
        f"https://api.tokenlx.ai/v1/aigc/video/tasks/{'{'}task_id{'}'}?model=wanx2.1-turbo",
        headers=headers,
    ).json()
    print("status:", result.get("status"))
    if result.get("status") in ("completed", "succeeded", "done"):
        print(result)
        break
    time.sleep(10)

# ─── 图生视频（首帧驱动）───
i2v_resp = requests.post(
    "https://api.tokenlx.ai/v1/aigc/video/tasks",
    headers=headers,
    json={
        "model": "wanx2.1-turbo",
        "prompt": "画面中的人物缓缓转头微笑",
        "referenceImageUrls": ["https://example.com/first-frame.jpg"],
        "videoInputMode": "first_frame",
        "duration": 5,
        "size": "1280*720",
    },
)
print("taskId:", i2v_resp.json())
# 轮询方式同上

Replace sk-aihubrouter-… with your key from the dashboard.

Parameter Reference

Async Workflow

Create task

POST /v1/aigc/video/tasks

Poll result

GET /v1/aigc/video/tasks/{taskId}?model=wanx2.1-turbo

Recommended poll interval: 5–15sTask ID validity: 24h

Response is raw upstream JSON passthrough — fields vary by channel.

Parameter	Type	Required	Description
model	string	Yes	Model name
prompt	string	Yes	Video description prompt
duration	int	No	Duration in seconds (≤10s)
size	string	No	Video size in WH format (e.g. 19201080)
seed	int	No	Random seed — fixed value produces reproducible results
referenceImageUrls	array	Image-to-video	Reference image URLs. Formats: JPEG/JPG/PNG/BMP/WEBP; Resolution: [240,8000]px; Aspect ratio: 1:8~8:1; Size: ≤20MB (wan2.7) / ≤10MB (older models)
videoInputMode	string	No	Input mode. Auto-inferred if omitted: 1 image → first_frame, 2 → first_last_frame, ≥3 → reference `first_framefirst_last_framereference`

modelstringYes

Model name

promptstringYes

Video description prompt

durationintNo

Duration in seconds (≤10s)

sizestringNo

Video size in W*H format (e.g. 1920*1080)

seedintNo

Random seed — fixed value produces reproducible results

referenceImageUrlsarrayImage-to-video

Reference image URLs. Formats: JPEG/JPG/PNG/BMP/WEBP; Resolution: [240,8000]px; Aspect ratio: 1:8~8:1; Size: ≤20MB (wan2.7) / ≤10MB (older models)

videoInputModestringNo

Input mode. Auto-inferred if omitted: 1 image → first_frame, 2 → first_last_frame, ≥3 → reference

first_framefirst_last_framereference

Image-to-video Capabilities

✓First frame

✕First + last frame

✕Reference image

Sample code & API

TokenLX normalizes requests and responses across providers. Use any OpenAI SDK or our native SDK.

# ─── 文生视频示例 ───
import requests, time

headers = {"Authorization": "Bearer sk-tokenlx-...", "Content-Type": "application/json"}

resp = requests.post(
    "https://api.tokenlx.ai/v1/aigc/video/tasks",
    headers=headers,
    json={
        "model": "wanx2.1-turbo",
        "prompt": "都市街头延时摄影，车流如织",
        "duration": 5,
        "size": "1280*720",
    },
)
task = resp.json()
task_id = task.get("taskId") or task.get("task_id") or task.get("id")

# 轮询结果
while True:
    result = requests.get(
        f"https://api.tokenlx.ai/v1/aigc/video/tasks/{'{'}task_id{'}'}?model=wanx2.1-turbo",
        headers=headers,
    ).json()
    print("status:", result.get("status"))
    if result.get("status") in ("completed", "succeeded", "done"):
        print(result)
        break
    time.sleep(10)

# ─── 图生视频（首帧驱动）───
i2v_resp = requests.post(
    "https://api.tokenlx.ai/v1/aigc/video/tasks",
    headers=headers,
    json={
        "model": "wanx2.1-turbo",
        "prompt": "画面中的人物缓缓转头微笑",
        "referenceImageUrls": ["https://example.com/first-frame.jpg"],
        "videoInputMode": "first_frame",
        "duration": 5,
        "size": "1280*720",
    },
)
print("taskId:", i2v_resp.json())
# 轮询方式同上

Replace sk-aihubrouter-… with your key from the dashboard.

Parameter Reference

Async Workflow

Create task

POST /v1/aigc/video/tasks

Poll result

GET /v1/aigc/video/tasks/{taskId}?model=wanx2.1-turbo

Recommended poll interval: 5–15sTask ID validity: 24h

Response is raw upstream JSON passthrough — fields vary by channel.

Parameter	Type	Required	Description
model	string	Yes	Model name
prompt	string	Yes	Video description prompt
duration	int	No	Duration in seconds (≤10s)
size	string	No	Video size in WH format (e.g. 19201080)
seed	int	No	Random seed — fixed value produces reproducible results
referenceImageUrls	array	Image-to-video	Reference image URLs. Formats: JPEG/JPG/PNG/BMP/WEBP; Resolution: [240,8000]px; Aspect ratio: 1:8~8:1; Size: ≤20MB (wan2.7) / ≤10MB (older models)
videoInputMode	string	No	Input mode. Auto-inferred if omitted: 1 image → first_frame, 2 → first_last_frame, ≥3 → reference `first_framefirst_last_framereference`

modelstringYes

Model name

promptstringYes

Video description prompt

durationintNo

Duration in seconds (≤10s)

sizestringNo

Video size in W*H format (e.g. 1920*1080)

seedintNo

Random seed — fixed value produces reproducible results

referenceImageUrlsarrayImage-to-video

Reference image URLs. Formats: JPEG/JPG/PNG/BMP/WEBP; Resolution: [240,8000]px; Aspect ratio: 1:8~8:1; Size: ≤20MB (wan2.7) / ≤10MB (older models)

videoInputModestringNo

Input mode. Auto-inferred if omitted: 1 image → first_frame, 2 → first_last_frame, ≥3 → reference

first_framefirst_last_framereference

Image-to-video Capabilities

✓First frame

✕First + last frame

✕Reference image

alibaba/wanx2.1-turbo

Key strengths

Use cases

Performance

Effective Pricing

Recent activity

Sample code & API

Parameter Reference

More models from Alibaba

alibaba/wanx2.1-turbo

Key strengths

Use cases

Performance

Effective Pricing

Recent activity

Sample code & API

Parameter Reference

More models from Alibaba