Skip to main content

​
📅 July 2026

​
🎨 gpt-image-2-vip Size and Quality Parameters Restored

July 9, 2026
gpt-image-2-vip parameter capability restored
  • Latest channel verification confirms that default-group gpt-image-2-vip has restored size and quality support
  • size can now be used for common 1K / 2K / 4K outputs; 1024x1024, 2048x2048, and 3840x2160 were verified to return the requested dimensions
  • quality currently supports low, medium, and high; higher quality usually increases wait time and output token usage
  • Do not mix token types: default-group gpt-image-2-vip uses a per-call token; Sora2Official / GPTImage2 Enterprise use usage-billed tokens, and the request body still uses model="gpt-image-2"
  • The response remains Images API-compatible and returns data[0].b64_json by default
  • The gpt-image-2-vip model name and $0.03/call per-request billing remain unchanged
  • The June 23, 2026 notice that size was unavailable again is superseded by this announcement
  • 📝 Developer documentation:
When you need per-call billing plus 1K / 2K / 4K size control, create a default-group per-call token and use model="gpt-image-2-vip". When you need usage-based billing by official input / output tokens, pure official-key routing, or stricter official parameter compatibility, create a Sora2Official or GPTImage2 Enterprise usage-billed token and use model="gpt-image-2".

​
🍌 Nano Banana 2 Lite is live with $0.025/call per-request billing

July 1, 2026
Nano Banana 2 Lite is now available on LaoZhang API
  • 🆕 New model: gemini-3.1-flash-lite-image (Nano Banana 2 Lite / Gemini 3.1 Flash Lite Image)
  • ⚡ Positioning: Google’s lightweight image model released on June 30, built for about 4-second generation, faster throughput than Nano Banana 2, and low-cost 1K image workflows
  • 📐 Capability scope: Supports 1K output and 14 common aspect ratios, suitable for drafts, batch assets, quick previews, and low-cost iteration
  • 💵 Billing: LaoZhang API currently offers per-request billing only at $0.025/call; actual charges are shown in console call logs
  • 📣 Launch price: The initial price is temporary. Any later change will be announced separately
  • 📝 Integration reference:
Nano Banana 2 Lite and Nano Banana 2 are two different models. Lite uses gemini-3.1-flash-lite-image and follows the same request patterns as Nano Banana Pro, so integration only requires replacing the model name with gemini-3.1-flash-lite-image. Lite is optimized for fast 1K lightweight generation. For 2K / 4K output, high-resolution final assets, or more complex image work, continue using gemini-3.1-flash-image (Nano Banana 2) or gemini-3-pro-image (Nano Banana Pro).

​
💻 Claude Sonnet 5 is live with official-aligned pricing

July 1, 2026
Claude Sonnet 5 is now available on LaoZhang API
  • 🆕 New model: claude-sonnet-5
  • 🧠 Positioning: Anthropic’s next-generation Sonnet model released on June 30, described as its most agentic Sonnet yet, suitable for coding agents, tool use, long-running tasks, and complex automation
  • 📊 Official benchmarks: SWE-bench Verified 85.2% and Terminal-Bench 2.1 80.4%, approaching flagship Opus 4.8 capability
  • 💵 Pricing: LaoZhang API pricing is aligned with Anthropic official pricing. Introductory pricing is $2 / $10 per 1M input / output tokens through August 31, 2026, then $3 / $15 per 1M input / output tokens
  • 🛡️ Route note: Currently served through pure AWS Claude official-forward resources with high cache-hit availability, suitable for Claude Code, Cursor, Cline, OpenClaw, and other developer tools
  • 📝 Integration reference:
The introductory price follows Anthropic’s official time window: $2/$10 per million tokens through August 31, 2026, then $3/$15 per million tokens. Actual billing is shown in the console model price and call logs.

​
📅 June 2026

​
⚠️ gpt-image-2-vip size is unavailable again; output is temporarily limited to 1K (Historical Notice)

June 23, 2026
Temporary gpt-image-2-vip size parameter update (historical state)
This notice is historical and is superseded by the July 9, 2026 restoration notice. gpt-image-2-vip currently supports size and quality again.
  • Based on customer reports, live testing, and code-level review this morning, default-group gpt-image-2-vip lost the restored size behavior again after another upstream rule change
  • At that time, gpt-image-2-vip generated 1K images normally, but submitted size values were silently ignored, so 2K / 4K could not be selected through this route
  • The gpt-image-2-vip model name and $0.03/call per-request billing remain unchanged
  • At that time, 2K / 4K or precise size control required switching to official-forward gpt-image-2 under the Sora2Official or GPTImage2 Enterprise group
  • Official-forward gpt-image-2 supports 4K / 2K and precise size control; it is billed by official input / output tokens, not by default-group per-call pricing
  • The June 18, 2026 restoration notice is superseded by this announcement
  • 📝 Developer documentation:
For the latest state, see the July 9, 2026 announcement and the GPT Image 2 API documentation.

​
🎨 gpt-image-2-vip Size and Quality Parameters Restored (Historical Notice)

June 18, 2026
Historical gpt-image-2-vip parameter capability update
This announcement is historical. gpt-image-2-vip lost size support again on June 23, 2026, and later restored size and quality support on July 9, 2026.
  • This entry describes the short-lived restoration state on June 18, 2026; use the July 9, 2026 announcement for the latest restored state
  • At that time, default-group gpt-image-2-vip temporarily restored size support
  • Common explicit 1K, 2K, and 4K pixel sizes were supported, including 1024x1024, 1536x1024, 2048x2048, 2048x1152, 3840x2160, and 2160x3840
  • The gpt-image-2-vip model name and $0.03/call per-request billing remain unchanged
  • For current 2K / 4K or precise size control, use default-group gpt-image-2-vip or official-forward gpt-image-2
  • 📝 Developer documentation:
Default-group gpt-image-2-vip currently supports size / quality again. Use gpt-image-2 under the Sora2Official / GPTImage2 Enterprise groups when you need pure official-key routing or stricter official parameter compatibility.

​
⚠️ sora-2 and sora-2-pro Official-Forward Models Will Be Retired on July 1

June 17, 2026
Sora 2 official-forward route retirement notice
  • Due to upstream OpenAI compute allocation changes, the sora-2 and sora-2-pro official-forward routes have recently experienced severe timeout issues and no longer meet production stability expectations
  • LaoZhang API will stop maintaining and retire the sora-2 / sora-2-pro official-forward models on July 1, 2026
  • Although the official retirement timeline may point to September 2026, these routes are already frequently unstable, so we do not recommend new integrations or production workloads
  • Existing users should migrate as early as possible; currently recommended alternatives are wan-2.7 and SeeDance2 / Seedance 2.0
  • 📝 Migration reference:
After July 1, sora-2 and sora-2-pro official-forward routes will no longer be maintained as stable entry points. Move production jobs ahead of time to avoid timeout or task failure impact.

​
⚠️ gpt-image-2-vip Size Parameter No Longer Supported (Historical Notice)

June 16, 2026
gpt-image-2-vip parameter support update
This is a historical notice. gpt-image-2-vip briefly restored size on June 18, 2026, lost it again on June 23, and restored size plus quality support on July 9, 2026.
  • This entry describes the temporary parameter adjustment on June 16, 2026
  • The gpt-image-2-vip model name and $0.03/call per-request billing remain unchanged
  • State at that time: default-group gpt-image-2-vip lost size support again; submitted size was silently ignored, and 2K / 4K could not be selected
  • Default-group gpt-image-2 still does not support size / quality
  • Use gpt-image-2 under the Sora2Official or GPTImage2 Enterprise group when you need full official Images API parameter compatibility
  • 📝 Developer documentation:
This section is historical. For current behavior, use the June 23, 2026 announcement and the GPT Image 2 API documentation.

​
📅 May 2026

​
🎬 Veo 3.1 Official API Forwarding Is Live With Low Unified 4K Pricing

May 21, 2026
Veo 3.1 official-forward route update
  • 🚀 New models:
    • veo-3.1-fast-generate-preview
    • veo-3.1-generate-preview
  • 💵 Pay-per-request billing:
    • veo-3.1-fast-generate-preview: $0.3/call
    • veo-3.1-generate-preview: $1.2/call
    • Set Billing mode to Pay-per-request when creating the token
    • Supported combinations use one unified price with no resolution surcharge; use 8 seconds for production integrations, and 1080p / 4K require 8 seconds
  • 📉 4K pricing advantage:
    • Based on Google’s 8-second 4K official price, Fast goes from about $2.40 to $0.3/call
    • Standard goes from about $4.80 to $1.2/call
    • 4K requests use unified pricing; verify final resolution from the downloaded MP4 metadata
  • 📝 Developer documentation:
The new route uses the same OpenAI Videos API style as Sora2 official forwarding: POST /v1/videos to create a task, GET /v1/videos/{id} to poll status, and GET /v1/videos/{id}/content to download MP4 bytes. The legacy-route incident notice still applies to old model names such as veo-3.1, veo-3.1-fast, and veo-3.1-fl; use the official-forward model names above for new integrations.

​
⚠️ Veo-3.1 Legacy Route Temporarily Unavailable

May 14, 2026
Veo-3.1 route incident notice
  • The veo-3.1 series legacy route began experiencing failures on May 14, 2026
  • The legacy route is temporarily unavailable; pause new calls and production integrations for now
  • Existing users should follow later announcements; recovery timing will be announced on this page and in the console
During this incident, do not use veo-3.1, veo-3.1-fast, veo-3.1-fl, or other Veo-3.1 legacy-route variants for production workloads.

​
🛡️ GPTImage2 Enterprise Pure Official-Key Group Is Live

May 13, 2026
GPT Image 2 official-compatible group update
  • New GPTImage2 Enterprise group: pure official-key routing with enterprise concurrency support
  • Billing is official pricing +20% to cover tax and operating cost, not profit markup
  • Sora2Official remains available as a mixed AZ + official-key transit group
  • Both official-compatible groups use model="gpt-image-2" with Images Generations and Images Edits
For quick testing or default-group routes, you can keep using default-group gpt-image-2 / gpt-image-2-vip. For official parameter compatibility and higher stability, choose GPTImage2 Enterprise.

​
🎨 gpt-image-2-vip Size Parameter Historical Notice

May 1, 2026
gpt-image-2-vip size capability update
This announcement preserves the historical state from May 1, 2026. gpt-image-2-vip stopped supporting size on June 16, briefly restored it on June 18, lost it again on June 23, and restored size plus quality support on July 9.
  • ✅ Parameter update:
    • gpt-image-2-vip now supports 1K, 2K, and 4K size tiers
    • 30 explicit pixel sizes are supported across square, portrait, landscape, widescreen, and ultrawide ratios
    • Pass an explicit pixel value such as 2048x2048, 3840x2160, or 2160x3840
    • Latest status: gpt-image-2-vip supports size and quality again
  • 🧩 Integration notes:
    • gpt-image-2-vip supports size
    • gpt-image-2-vip currently supports common 1K / 2K / 4K sizes again
    • Use gpt-image-2 under the Sora2Official mixed AZ + official-key group, or use the GPTImage2 Enterprise pure official-key group when you need pure official-key routing or stricter official parameter compatibility
  • 📝 Developer documentation:
This historical announcement records the gpt-image-2-vip size-parameter capability update at that time. It does not change the April 22 announcement for the initial GPT-Image-2 default-group route launch.

​
📅 April 2026

​
🎨 GPT-Image-2 Default-Group Routes Updated; sora_image Official Route Offline

April 22, 2026
Image generation route update
  • 🚀 New routes:
    • gpt-image-2 default standard route is now available for text-to-image and image-to-image workflows
    • gpt-image-2-vip is available; as of July 9, 2026, it supports size and quality again
  • ⚠️ Route change:
    • The sora_image official route is now offline
    • New image generation integrations should use gpt-image-2 or gpt-image-2-vip
    • Existing sora_image calls should migrate model and endpoint configuration as soon as possible
  • 💵 Pricing:
    • gpt-image-2 is billed per request at $0.03/call
    • gpt-image-2-vip is also billed per request at $0.03/call
    • You can test the model online at yingtu.ai before integrating the API
  • 📝 Developer documentation:
Default-group routes use Images Generations and Images Edits. Use gpt-image-2 or gpt-image-2-vip for basic text-to-image. For 2K / 4K, precise size, or full official parameter compatibility, use gpt-image-2 under the Sora2Official mixed AZ + official-key group, and choose GPTImage2 Enterprise when you want the pure official-key route.

​
🧠 Claude Opus 4.7 / Thinking Now Available

April 17, 2026
Claude Opus 4.7 is now available on LaoZhang API
  • 🚀 New Models: claude-opus-4-7 / claude-opus-4-7-thinking
  • 🌟 Launch Details:
    • Standard and Thinking variants are now available
    • Works directly through the OpenAI-compatible API by switching the model name
    • Suitable for complex reasoning, coding agents, and long-context tasks
  • 📝 Documentation Sync:
    • Announcement page has been updated
    • Related recommendation pages will be updated to the latest model version gradually
To try the latest Claude high-end model, switch the model field in your existing code or dashboard configuration to either of the model names above.

​
💰 Nano Banana Pricing Update Notice

April 13, 2026
New pricing is now live for Nano Banana Pro and Nano Banana2
  • 🎯 Affected models:
    • gemini-3-pro-image-preview (Nano Banana Pro)
    • gemini-3.1-flash-image-preview (Nano Banana2)
  • 💵 Price changes:
    • Nano Banana Pro: $0.05/request → $0.09/request
    • Nano Banana2: $0.045/request → $0.055/request
  • 📝 What was updated:
    • Documentation and pricing pages have been synced
    • Comparison pages, FAQs, and recommendations now reflect the new pricing
    • Actual charges are shown in the console call logs
This update is effective immediately. For bulk purchasing or stable large-scale usage, contact Telegram @laozhang_cn.

​
📅 January 2026

​
📚 Documentation Update for 2026

January 7, 2026
Documentation Optimization - 2026 New Year Update
  • 📅 Year Updates: All model recommendation pages updated to 2026
  • 🔄 Model Reference Updates: Default models in code examples updated to latest recommendations
  • ⚠️ Retirement Notice: Claude 3 Opus officially retired on January 5, 2026
  • 📝 Config Updates: Claude Code configuration method updated to settings.json
New year, new beginnings! LaoZhang API continues to provide you with the best AI services!
Back to announcements