Overview
gpt-image-2-all is a GPT image generation reverse-engineered model available on the API易 platform. With extremely competitive pricing at $0.03/image per call, it generates images in about 30 seconds and supports text-to-image / single-image editing / multi-image fusion / natural-language editing — with high text-rendering fidelity, fewer content restrictions, and native support for Chinese prompts.🎨 Highlights: Reliable reverse-engineered channel with a flat $0.03/image rate. No need to worry about size/quality/n parameters — just describe size and style in the prompt. Perfect for out-of-the-box image generation use cases.
Text-to-Image API
Generate images from text prompts. Includes an interactive playground for online testing.
Image Editing API
Upload reference images + edit/fusion instructions (multipart/form-data).
Core Features
Highly Competitive Pricing
Flat per-call pricing of $0.03/image, no resolution tiers, predictable costs
High Text Rendering
Stable rendering of Chinese/English text, signs, and poster text — ideal for infographics and marketing assets
Chinese Prompt Friendly
Native understanding of Chinese descriptions without translation
Multi-Image Fusion
Supports multiple reference images; prompts can reference them as “image1/image2/image3”
Fewer Content Restrictions
More permissive for creative content than some official models, higher success rate
R2 CDN Accelerated
Default returns R2 CDN URLs for global low-latency downloads. Can switch to b64_json.
Natural-Language Editing
Edit via conversational descriptions, no masks required, supports multi-turn iteration
Triple Endpoint Support
Compatible with
/images/generations, /images/edits, and /chat/completionsPricing
| Model | Billing | Price | Output |
|---|---|---|---|
gpt-image-2-all | Per-call | $0.03 / image | 1 image per call |
Billing notes:
- Flat pricing; no tiers by resolution, quality, or prompt length
- Failed requests are not charged (auth failures, parameter validation errors)
- For N images, call the API N times in parallel
Technical Specs
| Attribute | Value |
|---|---|
| Model name | gpt-image-2-all |
| Channel type | Official reverse-engineered |
| Pricing | $0.03 / image, per-call |
| Generation time | ~30 seconds |
| Output resolution | No explicit size parameter; adaptive (describe in prompt) |
| Default response format | url (R2 CDN accelerated link) |
| Alternative format | b64_json (already prefixed with data:image/png;base64,) |
| Chinese prompts | ✅ Natively supported |
| Capabilities | Text-to-image, single-image editing, multi-image fusion, natural-language editing |
Endpoints
| Endpoint | Purpose | Content-Type |
|---|---|---|
POST /v1/images/generations | Text-to-image | application/json |
POST /v1/images/edits | Image editing (single/multi) | multipart/form-data |
POST /v1/chat/completions | Chat-based (multi-turn + reference images) | application/json |
Size and Aspect Ratio Control
This model has nosize parameter — size is described in the prompt. Proven-stable phrasings:
| Need | Suggested Phrasing |
|---|---|
| Square | 1024×1024 square / 1:1 square composition |
| Landscape | Landscape 16:9 / Widescreen 16:9 cinematic |
| Portrait | Portrait 9:16 / Phone poster 9:16 |
| Ultra-wide | Banner 21:9 ultra-widescreen |
| Classic print | 4:3 standard / 3:2 classic |
Best Practices
Put size at the start of the prompt
Ratio, resolution, and composition words at the front yield better adherence.
Use text elements confidently
Text rendering fidelity is a key selling point — signs, posters, infographics with Chinese/English text all work well.
Annotate multi-image order
image[] order is meaningful. Reference explicitly as “image1/image2/image3” in the prompt.Choose response format by need
Use
b64_json for direct web rendering; url for server-side storage/forwarding.Use ≥120s timeout
Typical generation is ~30s, but set timeouts to at least 120s to absorb tail latency.
Error Codes and Retries
| Status | Meaning | Suggestion |
|---|---|---|
401 | Invalid token | Check Bearer Token |
429 | Rate limit / quota exhausted | Exponential backoff retry |
5xx | Transient gateway/backend error | Retry 1–2 times |
| Timeout | Occasional during peak hours | Use ≥120s client timeout |
Client recommendations:
- Request timeout starting at 120 seconds (typical ~30s, leaves 4× buffer for tails)
- Use exponential backoff for 5xx and timeouts (2–3 retries recommended)
- Log the
request-idresponse header for debugging
FAQ
Can I generate multiple images at once?
Can I generate multiple images at once?
No. This model returns 1 image per call. For N images, call the API N times in parallel. Each call is billed independently at $0.03.
Do I need to add data:image/png;base64, prefix to b64_json?
Do I need to add data:image/png;base64, prefix to b64_json?
No. The
b64_json field already includes the prefix. You can use it directly as <img src> or write it to a file. If your code follows the old “prepend prefix” pattern, you’ll produce a broken data URL — add a startsWith('data:') check first.Why am I getting a different size even though the prompt says 1024x1024?
Why am I getting a different size even though the prompt says 1024x1024?
Adaptive models treat size descriptions as “guidance” rather than “forced”. To improve adherence: put size/composition words at the very start of the prompt, and combine with style descriptors (e.g.,
cinematic, phone poster, square composition).What's the max reference image size and supported formats?
What's the max reference image size and supported formats?
Recommended ≤ 10MB per image, formats
png / jpg / webp. Overly large images may hit gateway limits. Each image in multi-image fusion must meet this limit.Does it support streaming?
Does it support streaming?
No. This model returns the image in one shot; streaming is not supported. If latency matters, show a “generating…” progress indicator on the client side and configure a 120s timeout.
Can I use the official OpenAI SDK?
Can I use the official OpenAI SDK?
Yes. Point
base_url to https://api.apiyi.com/v1 and set api_key to your API易 token. However, client.images.generate() sends size/n by default — we recommend:- Use
client.chat.completions.create()instead; or - Make raw HTTP calls with
requests/fetch.
Are Chinese and English prompts meaningfully different?
Are Chinese and English prompts meaningfully different?
This model natively supports Chinese, and results are comparable. For Chinese-specific scenarios (calligraphy, traditional festival elements), Chinese phrasing feels more natural.
Related Documentation
- Text-to-Image Playground - Interactive online testing
- Image Editing Playground - Multi-image fusion and editing
- GPT-Image Series Overview - Official GPT-Image comparison
- API Manual - General calling conventions
gpt-image-2-all is a reverse-engineered channel. Behavior is aligned but pricing/capabilities may not fully match the official version. For the official direct version, see GPT-Image-1.5.