Wan 2.2 I2V Fast API guide
The short answer · Wan 2.2 I2V Fast uses wan-video/wan-2.2-i2v-fast in MaxAPI's video-generation API. Submit a task, save its identifier, and poll for the final result. Acceptance is not completion. Supported media, duration and resolution depend on this model entry and the selected route.
Integration review ·
Checked against MaxAPI's public catalogue, gateway implementation and local regression cases. Shared gateway checks are not separate end-to-end tests of every listed model. This is an integration reference, not a live upstream availability or performance report.
Before you integrate
Parameters describe MaxAPI's published configuration. A selected route may impose additional input or access requirements.
- Request model ID
wan-video/wan-2.2-i2v-fast- Output type
- Video
- Base URL
https://api.maxapi.dev- Generation workflow
- Asynchronous task + polling
- Quality values
480p / 720p- Resolution & dimensions
- 480p / 720p · follows the input image's aspect ratio
- Video duration
- 81–121 frames at 5–30 fps (default 81 frames at 16 fps ≈ 5 s)
Image-to-video only: send one first-frame image (image_url) and optionally a last frame (last_frame_url) as public https URLs or data:image/ URIs. Text-to-video, reference videos, audio, aspect_ratio and duration are not accepted; length is num_frames / frames_per_second. A submitted task is not a completed video.
Model strengths & selection
Fast image-to-video drafts
Wan 2.2 I2V Fast is a PrunaAI-optimized version of Wan 2.2 A14B image-to-video, served through Replicate. MaxAPI exposes image-to-video with an optional last frame at 480p or 720p, 81–121 frames and no audio. The Official route is priced per video: 0.05 credits at 480p and 0.11 at 720p (0.065 / 0.145 with 30 fps interpolation).
Source review ·
Model-specific sources: Replicate · Wan 2.2 I2V Fast API schema
When to compare this model
Compare it for quick motion drafts from an existing still, simple camera moves and transitions between two frames. Draft at 480p, then render the chosen prompt at 720p.
Know the limits
There is no text-to-video, audio, reference video or aspect-ratio control; the output follows the input image. Clips are short (about 5 s by default, 7.5 s at 121 frames). Our last-frame test held the first scene for most of the clip and changed late, so check transitions frame by frame.
Provider capabilities describe the model, not the complete MaxAPI feature set. Use the parameters, input types and routes documented for this MaxAPI entry. Vendor speed or quality descriptions are not service-level guarantees.
How MaxAPI handles this request
Which route wins?
Routing priority is: the API key's configured route_modes list → an explicitly requested route → the model's default route. A non-empty key list takes precedence over route_mode in the request. To test a specific route, check the key configuration first; changing the request alone may not change the route used.
RPM is shared at account level
An account's positive RPM limit covers its API keys together. A key can impose a stricter limit, but a higher key limit does not override the user limit. For example, a user limit of 200 RPM is not 200 RPM for each key. Service-level RPM and concurrency controls also apply; adding keys is not a way to bypass them.
Routes & pricing
Published routes: official. Specify route_mode in an image/video JSON request; Gemini-native requests use X-MaxAPI-Route-Mode. A route is an access and billing choice, not a different public model ID.
| Route | Published base price | Billing unit |
|---|---|---|
official | $0.05 | 480p · per video |
official | $0.11 | 720p · per video |
official | $0.065 | 480p + 30 fps interpolation · per video |
official | $0.145 | 720p + 30 fps interpolation · per video |
1 credit = US$1. These are catalogue base rates, not a live account quote. Account multipliers and the active billing configuration determine the final charge. Token rates are not a fixed price per image.
Check current pricingYour first request
Create a MaxAPI API key and set MAXAPI_KEY in your server environment; never put it in browser code. A configured key route list takes priority, even if the request specifies a route. Only when that list is empty does the request route apply; otherwise the model default is used. API calls may incur charges.
POST /v1/videos/generationsGET /v1/videos/generations/{task_id}
# The create call returns {"id":"task_...","poll_url":"/v1/videos/generations/task_..."}. Poll that URL.
curl -X POST "https://api.maxapi.dev/v1/videos/generations" \
-H "Authorization: Bearer $MAXAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "wan-video/wan-2.2-i2v-fast",
"prompt": "slow camera push-in, soft light moving across the scene",
"route_mode": "official",
"image_url": "https://your-cdn.com/first-frame.png",
"resolution": "480p",
"num_frames": 81,
"frames_per_second": 16
}'Check your first result
Request-contract review ·
Checked against the public catalogue and gateway code. Examples are structural illustrations, not paid model tests, latency measurements or a guarantee that every route is currently available.
Send the right fields
model / image_url- Send wan-video/wan-2.2-i2v-fast with prompt and a first-frame image_url (public https URL or data:image/ URI). Add last_frame_url only for a two-frame transition. There is no mode, text-to-video or reference-video field.
resolution / num_frames / frames_per_second- The example requests 480p, 81 frames and 16 fps (about 5 seconds). Do not send aspect_ratio or duration: the output follows the input image and length is num_frames / frames_per_second. The price depends on resolution and interpolate_output only.
HTTP 202 / id / poll_url- A successful submission returns a task receipt, not a video. Save id and poll_url before closing the client; the JSON identifier is id, not task_id.
Read the actual result
status / video- Poll with authentication from the same account. queued/running are not final; on succeeded, read the top-level video URL. On failed/canceled, inspect message instead of assuming a usable file.
estimated_charge_credits- The receipt carries an estimate, not a final invoice. Check final usage and billing records; downloading the returned file is a separate step from task completion.
{
"id": "example-task-id",
"object": "video.generation.task",
"status": "queued",
"model": "wan-video/wan-2.2-i2v-fast",
"poll_url": "/v1/videos/generations/example-task-id"
}# Set TASK_ID to the saved response.id; this queries, it does not create a task.
curl --fail-with-body "https://api.maxapi.dev/v1/videos/generations/${TASK_ID:?Set TASK_ID from response.id}" \
-H "Authorization: Bearer $MAXAPI_KEY"Troubleshoot by symptom, not just HTTP status
429rate_limit_exceeded / capacity_exhausted
- What it tells you
- 429 can represent account/key RPM, service-wide capacity or generation capacity. Use Retry-After and available X-RateLimit-* / X-Global-* headers to distinguish them; one status code does not identify one unique cause.
- What to do next
- Respect Retry-After when present, reduce request rate or active concurrency as appropriate, and use bounded backoff. Do not treat the site's total capacity as your account's personal quota.
What you can build
The use cases and prompts below are our suggested evaluation briefs, not provider benchmarks or tested output samples.
AI-created concept illustrations · not outputs or benchmarks from this model. Prompts below are starting points, not recipes that reproduce these images.
Creative practice · shared production advice
Make a shot list, not a list of effects
For Wan 2.2 I2V Fast, describe a single subject, a scene and a camera intention before adding motion. A product reveal might start on a material detail and pull back to show the object; a lifestyle shot might keep the camera still while the subject moves. Avoid asking one short clip to contain several unrelated locations, perspectives and actions. A clear shot brief is easier to evaluate and edit into a larger sequence.
The still illustration shows a possible visual direction, not a video result. Turn a chosen direction into a timing brief: what is visible at the start, what changes, and what the last frame should communicate. Review motion continuity, object shape and framing across the whole clip, not just its thumbnail. Use only the reference modes and media fields documented for the selected model.
Prompt examples worth adapting
A good prompt is a small creative brief. Replace the subject and constraints with your actual requirements; keep size, route and quality in the API parameters rather than relying on prose alone.
01 / A slow push-in on a product
Slow camera push-in toward the perfume bottle, soft light moving across the satin behind it. Keep the bottle's shape and label unchanged and the camera steady, with no cuts.What to review · Check that the bottle keeps its shape across frames and that the motion has no sudden jumps.
From a storyboard to a usable clip
Define the acceptance criteria
Choose representative inputs and describe what makes the output usable. Include difficult cases, not only ideal examples. Fix the request parameters while comparing results.
Keep execution separate from presentation
Store request identifiers and preserve the response before transforming it for your interface. Validate errors and incomplete results explicitly. A user-interface timeout should not silently trigger duplicate work.
Measure usable output, not just successful calls
Log the model, route, input characteristics, actual usage and review outcome. Include manual correction and repeated attempts when estimating the cost of delivering a usable result.
From a test to production
Test the route you will actually use
Keep model, route and parameters fixed during your first comparison. Test your own typical inputs as well as large or unusual files. Published model capabilities do not guarantee that every upstream channel accepts every edge case.
Separate limits from generation errors
On 429, reduce request rate or concurrency and back off before retrying. On invalid-input errors, fix the input first. Preserve request and task IDs for troubleshooting; do not log API keys or sensitive reference files in public logs.
Track usable results and actual spend
Use your account's usage and billing records to verify the final result and charge. A successful HTTP response can be a task receipt rather than the final output. For published work, check generated text, visual details and rights to supplied reference material.
Verified integration cases
Checked against MaxAPI's public catalogue, gateway implementation and local regression cases. Shared gateway checks are not separate end-to-end tests of every listed model. This is an integration reference, not a live upstream availability or performance report.
Multiple keys share the user limit
Local regression · passed- Test setup
- Use two keys owned by the same account against an in-memory limiter with a small user quota.
- Observed result
- Requests across the keys consume the same user quota; subsequent requests are limited. A larger key quota does not override the user quota, and a smaller key quota remains effective.
Frequently asked questions
When should I choose this model?
Compare it for quick motion drafts from an existing still, simple camera moves and transitions between two frames. Draft at 480p, then render the chosen prompt at 720p.
What limitations are specific to this entry?
There is no text-to-video, audio, reference video or aspect-ratio control; the output follows the input image. Clips are short (about 5 s by default, 7.5 s at 121 frames). Our last-frame test held the first scene for most of the clip and changed late, so check transitions frame by frame.
Why does changing route_mode not change my route?
Routing priority is: the API key's configured route_modes list → an explicitly requested route → the model's default route. A non-empty key list takes precedence over route_mode in the request. To test a specific route, check the key configuration first; changing the request alone may not change the route used.
Does each API key get the user's full RPM limit?
An account's positive RPM limit covers its API keys together. A key can impose a stricter limit, but a higher key limit does not override the user limit. For example, a user limit of 200 RPM is not 200 RPM for each key. Service-level RPM and concurrency controls also apply; adding keys is not a way to bypass them.
Do these local regression cases prove live model performance?
Local tests use simulated requests, responses and test storage; they do not call paid model channels. They verify request handling, not model image quality, live success rates, latency or end-to-end support for the maximum reference count. The concept illustrations elsewhere on this page are not these test outputs.
Which model ID should I send for Wan 2.2 I2V Fast?
Use wan-video/wan-2.2-i2v-fast. Use the exact endpoint format in the example; the Gemini-native URL uses the short model name.
Does a listed price apply to every account and route?
1 credit = US$1. These are catalogue base rates, not a live account quote. Account multipliers and the active billing configuration determine the final charge. Token rates are not a fixed price per image.
Are failed requests charged?
MaxAPI's published rule is that failed requests are not charged. A request may temporarily reserve balance while it runs; check the final task outcome and billing records rather than treating a temporary balance change as the final charge.
Why is a route unavailable for my API key?
Route availability depends on the model, account permission and the API key's allowed routes. A published price is not an access grant. Check the account and key configuration before changing route_mode.
What should I check before processing the result?
Image-to-video only: send one first-frame image (image_url) and optionally a last frame (last_frame_url) as public https URLs or data:image/ URIs. Text-to-video, reference videos, audio, aspect_ratio and duration are not accepted; length is num_frames / frames_per_second. A submitted task is not a completed video.
Should I immediately retry a failed or timed-out request?
First identify whether the response is a rate limit, invalid input or a still-running task. If you already have a task ID, query its status before submitting another generation. Apply bounded retries with backoff only to retryable errors.