API Updates

We are excited to announce the launch of Seedance 1.5 Pro, BytePlus's latest video generation model with integrated audio generation capabilities.

New Model

Seedance 1.5 Pro

• Model ID: seedance-1.5-pro
• Features: Text-to-Video and Image-to-Video generation with optional synchronized audio
• Highlights: Unified model supporting both T2V and I2V with AI-generated audio
• Resolution: 480p / 720p
• Duration: 4-12 seconds

Key Capabilities

• Text-to-Video: Generate videos directly from text descriptions
• Image-to-Video: Animate static images with motion
• Audio Generation: Optional synchronized audio including voice, sound effects, and background music
• Multiple Aspect Ratios: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, and Adaptive
• Reference Images: Support for 1-2 reference images for guided generation

Documentation

• Seedance 1.5 Pro API Documentation

We are excited to announce the launch of Suno AI music generation model, bringing you professional-quality AI-powered music creation capabilities.

New Model

Suno

• Model ID: suno-v5 (also supports suno-v4.5plus, suno-v4.5all, suno-v4.5, suno-v4)
• Features: AI-powered music generation with vocals, lyrics, and instrumental support
• Highlights: Create professional-quality songs from text prompts, multiple model versions
• Duration: Up to 4 minutes per song

Key Capabilities

• Simple Mode: Just provide a prompt, AI generates lyrics and melody automatically
• Custom Mode: Full control over style, title, and lyrics
• Instrumental Mode: Generate music without vocals
• Song Extension: Continue or extend existing songs

Documentation

• Suno API Documentation

We are excited to announce the launch of MiniMax Hailuo video generation model series, bringing you cutting-edge AI video creation capabilities.

New Models

Hailuo 2.3 Fast

• Model ID: MiniMax-Hailuo-2.3-Fast
• Features: Optimized for speed, Image-to-Video (I2V) mode only
• Highlights: Lowest latency, extreme physics effects, ideal for rapid iteration
• Resolution: 768P / 1080P
• Duration: 6s / 10s

Hailuo 2.3

• Model ID: MiniMax-Hailuo-2.3
• Features: High-quality output with Text-to-Video (T2V) and Image-to-Video (I2V) dual modes
• Highlights: SOTA instruction following, professional-grade quality
• Resolution: 768P / 1080P
• Duration: 6s / 10s

Hailuo 02

• Model ID: MiniMax-Hailuo-02
• Features: Full-featured with Text-to-Video (T2V), Image-to-Video (I2V), and First-Last-Frame (FLF) three modes
• Highlights: Supports 512P low-cost option, ideal for diverse creative needs
• Resolution: 512P / 768P / 1080P
• Duration: 6s / 10s

Key Capabilities

• 15 Camera Commands: Pan, Tilt, Zoom, Push, Pull, Truck, Pedestal, Static, Tracking, Shake and more
• Intelligent Mode Detection: System auto-detects mode based on input image count
• Prompt Optimizer: AI-powered prompt enhancement for better results
• Fast Pretreatment: Optional acceleration for image analysis

Documentation

• Hailuo 2.3 API Documentation
• Hailuo 02 API Documentation

Thank you for your support and feedback during the Phase 1 promotion. As the "Alibaba Model Full Series" Phase 1 promotion concludes, we are launching the Phase 2 pricing structure.

Promotion Details

• Phase 2 Pricing: Unified 30% off official prices (covering all Alibaba model series capabilities)

• Effective Date: December 26, 2025 00:00

• Scope: Alibaba model series (image/video generation, etc.) related billing items

Notes

After the new pricing takes effect, new API calls will be billed at Phase 2 promotional prices; historical bills remain unaffected.

1. GPT Image 1.5

   • gpt-image-1.5:

     • OpenAI's advanced image generation model.
     • Optimized for true-color precision and structured visual tasks.
     • Enhanced analytical visual outputs based on DALL-E 3 technology.
     • High-quality image generation with improved detail accuracy.

   • Documentation: GPT Image 1.5 API

2. Gemini 3 Flash Preview

   • gemini-3-flash-preview:

     • Google's latest fast inference model preview.
     • Optimized for speed while maintaining high quality output.
     • Extended context window support.
     • Ideal for high-throughput applications.

   • Documentation: Gemini 3 Flash Preview API

1. WAN 2.6 Text to Video

   • wan2.6-text-to-video:

     • Alibaba Tongyi Wanxiang 2.6 text-to-video generation.
     • Enhanced quality with 720p/1080p resolution support.
     • Multiple duration options: 5s, 10s, 15s.
     • Intelligent prompt rewriting for better results.

   • Documentation: WAN 2.6 Text to Video API

2. WAN 2.6 Image to Video

   • wan2.6-image-to-video:

     • Transform static images into dynamic videos.
     • First-frame generation with motion control.
     • Supports 5s, 10s, 15s duration at 720p/1080p quality.

   • Documentation: WAN 2.6 Image to Video API

3. WAN 2.6 Reference Video

   • wan2.6-reference-video:

     • Extract character appearance and voice from reference videos.
     • Generate new videos with consistent character identity.
     • Advanced video-to-video transformation capabilities.

   • Documentation: WAN 2.6 Reference Video API

1. OmniHuman 1.5 (Digital Human Video)

   • omnihuman-1.5:

     • AI-powered digital human video generation with audio-driven lip-sync.
     • Transform static images into talking avatars with natural facial expressions and movements.
     • Support for multiple aspect ratios: 1:1, 9:16, 16:9.
     • High-quality output with smooth lip synchronization.

   • Pricing:

     • $0.167/second (12 credits/second)
     • Billed based on audio duration

   • Key Features:

     • Audio-driven lip-sync technology
     • Natural facial expressions and head movements
     • Support for portrait images as input
     • Multiple output resolutions available

   • Documentation: OmniHuman 1.5 API

2. GPT-5.2 (Text/Multimodal)

   • gpt-5.2:

     • OpenAI's flagship model optimized for coding and agentic tasks.
     • 400K context window with 128K max output tokens.
     • Enhanced reasoning capabilities for complex multi-step workflows.
     • Built-in prompt caching for up to 90% cost reduction on repeated tokens.

   • Pricing:

     • Input: $1.75/1M tokens (VIP: 75% off)
     • Output: $14.00/1M tokens (VIP: 75% off)
     • Cache Hit: $0.175/1M tokens (VIP: 75% off)

   • Key Features:

     • Advanced reasoning for coding and analysis
     • Function calling and structured outputs
     • JSON mode for guaranteed valid responses
     • Real-time streaming support

   • Documentation: GPT-5.2 API

1. Z Image Turbo (Image)

   • z-image-turbo:

     • Ultra-fast image generation model based on Tongyi Lab's open-source architecture.
     • Generation time ~3 seconds, supports up to 4K resolution.
     • Ideal for high-concurrency and batch generation with excellent prompt adherence.
     • VIP pricing: ~$0.0036/image (28% savings vs market price)

   • Key Features:

     • Multiple aspect ratios: 1:1, 9:16, 16:9, etc.
     • Negative prompt control
     • NSFW content filtering toggle
     • Custom LoRA model loading

   • Documentation: Z Image Turbo

1. Kling O1 Series (Video)

   • kling-o1-image-to-video:

     • Generate video from images, supports up to 2 input images.
     • Duration: 5s or 10s.
     • VIP pricing: ~$0.111/second

   • kling-o1-video-edit:

     • AI-powered video editing with reference image support.
     • Duration: 3-10 seconds.
     • VIP pricing: ~$0.167/second

   • kling-o1-video-edit-fast:

     • Fast video editing mode.
     • Duration: 6-20 seconds.
     • VIP pricing: ~$0.094/second

   • Documentation:

     • Kling O1 Image to Video
     • Kling O1 Video Edit
     • Kling O1 Video Edit Fast

2. Seedream 4.5 (Image)

   • doubao-seedream-4.5:

     • Enhanced multi-image editing consistency.
     • Improved text rendering in images.
     • Supports up to 4K resolution.
     • VIP pricing: ~$0.035/image

   • Documentation: Seedream 4.5

1. Nano Banana 2 series

   • nano-banana-2-lite:

     • Supports size and resolution configuration.
     • VIP pricing:

       • 1K / 2K: ~$0.030/image
       • 4K: ~$0.033/image

   • nano-banana-2-pro (official direct):

     • Also supports size configuration; 4K option added.
     • VIP billing (about 30% off official):

       • Image input: ~$0.001/image
       • Image output (2K): ~$0.107/image
       • Image output (4K): ~$0.170/image

   • Documentation: Nano Banana 2 Documentation

2. Veo 3.1 Fast updates

   • Multi-image Reference:

     • Up to 3 reference images, pricing unchanged.
     • Documentation: Veo 3.1 Fast Documentation

   • Video Extend:

     • Supports “prompt + previous video ID” for extension.
     • Model: veo3.1-fast-extend; pricing same as veo3.1-fast.
     • Documentation: Veo 3.1 Fast Extend Documentation

1. Added dual versions

   • gemini-3-pro-image-preview: official channel with higher stability and controllability for demanding business scenarios.
   • nano-banana-2-lite: third-party version, extremely cost-effective; no size controls yet and slightly less stable.

2. Latest pricing

   • nano-banana-2-lite:

     • VIP: ~$0.030/time
     • Non-VIP: ~$0.044/time

   • gemini-3-pro-image-preview:

     • VIP: ~$0.107/time (about 30% off official)
     • Non-VIP: ~$0.122/time (about 20% off official)

3. Model naming

   • By default gemini-3-pro-image-preview points to the official version.
   • To switch to the cheaper Lite version, set the model name to nano-banana-2-lite (takes ~1 minute).

4. Effective time & upcoming upgrades

   • 1-hour buffer for VIP users; pricing takes effect afterward.
   • Pro will gradually open multi-image and 4K.
   • Lite will add more channels to improve capability and stability, with ongoing upgrades.

• evolink's Nano Banana 2 is now online, corresponding to the official fidelity model: gemini-3-pro-image-preview.

• Interface documentation: Nano Banana Pro Documentation​

• Current price: ~$0.030/time. Officials expect to further lower the price soon and synchronize users as soon as possible.

1. Sora 2 Pro is launched

   • VIP price (by duration and clarity):

     • 10s SD: ~$0.774/time

     • 10s HD: ~$1.702/time

     • 15s SD: ~$1.392/time

     • 15s HD: ~$3.249/time

   • Lower-priced channels will be evaluated in the future. If the stability reaches the standard, it will be launched and the price will be further reduced.

2. Gemini 3 status

   • Access has been completed, but the current test results do not meet the usage standards, and external calls are not available for the time being.

   • Users will be notified as soon as the standards are met.

1. Supported models

   • claude-haiku-4-5-20251001

   • claude-sonnet-4-5-20250929

   • claude-opus-4-1-20250805

   • claude-sonnet-4-20250514

2. Pricing and scenarios

   • VIP: 30% off official website price, further discounts for large quantities.

   • The project has been adapted to the coding scenario, and large customers have stable access.

3. Interface documentation: Claude Messages API documentation​

1. New models

   • Gemini 2.5 Flash:

     • VIP: 22% off official price

     • Non-VIP: 12% off official price

   • Seedance 1.0 Pro Fast:

     • VIP:

       • 720P：¥~$0.010/s

       • 1080P：¥~$0.022/s

     • Non-VIP:

       • 720P：¥~$0.014/s

       • 1080P：¥~$0.031/s

2. Function optimization

   • Payment: Added a new Credits page to optimize the recharge and payment experience.

   • Sora 2: Prompt character limit increased to 5000 characters.​

   • Log: Explanation of the new status, generation results and failure details of the call log.

1. Sora 2 duration upgrade

   • Sora 2 now supports generating 15-second videos.

   • Price:

     • With watermark: ~$0.037

     • Remove watermark: ~$0.051

2. Platform function update

   • Webhook: Callback parameters are supported.

   • Official website: The page supports multiple languages ​​(including Chinese), no browser translation plug-in is required.

3. Veo 3 offline notice

   • It is observed that users have basically switched to veo3.1-fast, and the old version of Veo 3 will be officially offline in 3 days.

   • If you are still using it, please change the model parameter to "veo3.1-fast".

1. Add new low-price channels

   • New channels that have passed the stability test have been connected:

     • VIP: ~$0.135/8s

     • Non-VIP: ~$0.844/8s (unchanged)

2. Intelligent routing logic

   • The system defaults to routing to the low-price channel of ~$0.135.

   • When the low-price channel is unavailable, it will automatically switch to the ~$0.338 high-price backup channel to ensure stability.

3. Follow-up plan

   -Continue to explore and access more stable and cost-effective channels.

1. Function support

   • Supports Vincent videos, Tusheng videos and customized first and last frame generated videos.

2. Model price (unit: 8s/time)

   • Evolink VIP: ~$0.338/time (about 22% off the official price)

   • Official price: ~$1.204/time

   • Evolink non-VIP: ~$0.844/time (about 30% off the official price)

3. Channels and planning

   • The current access is to a channel that is stable and has the same capabilities as the official one.

   • We will continue to evaluate other lower-priced channels in the future and further reduce prices while ensuring quality.

   • The ability of ultra-long videos (video continuation) is being tested and will be opened as soon as possible after meeting the standards.

4. Documentation: Veo 3.1 Fast Documentation​

1. Model advantages

   • The official direct connection channel is stable, has low latency, does not degrade your intelligence, and supports multi-modal input.

2. Phased price (unit: /1000 tokens)

   • VIP users:

     • Before October 15th: Input ~$0.001, output ~$0.009 (approximately 10% off official discount)

     • After October 15th: Input ~$0.001, output ~$0.008 (approximately 22% off official discount)

   • Non-VIP users:

     • Before October 15th: Official original price

     • After October 15th: 10% off official price

3. Interface documentation: Gemini 2.5 Pro Documentation​

4. Long-term pricing strategy

   • Non-VIP: 10% off official price

   • VIP: 30% off official price

5. Limited time VIP large benefit price

   • wan 2.5 video: ~$0.025/second (about 30% off)

   • wan 2.5 images: ~$0.011/image (about 40% off)

   • Qwen Image Edit: ~$0.017/image (about 40% off)

   • The duration of the benefit is related to the consumption speed of official coupons. It is expected to last until the end of the month and will be notified in advance before the end.

1. Price background review

   • Sora VIP price is ~$0.023/time.

   • The watermark removal function has been launched in the early stage, but the document does not yet support parameters. The platform will subsidize the cost of watermark removal out of its own pocket in stages.

2. Formal billing and parameter support

   • Control the watermark through the remove_watermark parameter:

     • true: remove watermark (high price range), which is the default value;

     • false: keep watermark (standard price).

   • When parameters are not passed explicitly, it will be regarded as the watermark-removed version by default. Please pay attention to billing.​

3. New price structure

   • VIP:

     • Sora with watermark: ~$0.023/time

     • Sora watermark removal: ~$0.037/time

   • Non-VIP:

     • Sora with watermark: ~$0.113/time

     • Sora watermark removal: ~$0.169/time

   • For details, see the latest documentation: Sora 2 Documentation​

• Starting from October 9th, you can upgrade to a VIP user by recharging ~$140.647 on evolink.ai.

• VIP available prices:

  • Sora 2: $0.023/10s (will be adjusted to the range of 0.16–$0.035/10s later based on parameters)

  • seedream 4.0: ~$0.017/ticket (official website ~$0.028/ticket, 40% off)

  • nano banana: 0.1–~$0.015/piece (official website ~$0.039/piece, about 3.5% off)

  • Veo3-Fast: about 0.72–~$0.141/8s (official website ~$1.406/8s, less than 10% off)

  • GPT-4O Image: about ~$0.017/image (official website ~$0.041/image, 4.1% off)

VIP Description

• Users who have obtained VIP qualifications enjoy lifetime VIP prices.

• If adjustments are required due to price changes in upstream suppliers or channels, an official notice will be issued in advance.

• Added horizontal screen and vertical screen parameter selection to support different screen ratios.

• Supports uploading reference images, please see the document for specific parameters and calling methods: Sora 2 Document​

Risk control tips (reference picture)

• OpenAI official review of reference images is extremely strict.

• Reference pictures containing real-life photos are likely to fail in the review. It is recommended to give priority to non-real-life pictures such as animations, landscapes, and concept pictures to increase the success rate.

• The Sora channel has been fully restored, and early instability issues have been investigated and fixed.

• In order to ensure the long-term stability of the service, fees will be officially charged starting from October 5th:

  • VIP price: ~$0.023/time

  • Non-VIP price: ~$0.113/time

• Review: In order to allow VIPs to experience it first, an ultra-low discount price of ~$0.000 has been provided for 3 consecutive days.

• Based on the experience in recent days, we will continue to upgrade interface services to improve stability and experience.

• Sora 2 API is open for use, non-VIP price: ~$0.098/time.​

• VIP benefit price on October 2nd: ~$0.000/time.

• If you have connected other video models, it only takes a few minutes to switch to Sora 2. Access the documentation: Sora 2 Documentation​

• Note: Sora 2 takes about 5 minutes to generate, please reserve sufficient time in the business logic.

Sora 2 Stability and Risk Control Instructions

• The Sora success rate was monitored at night to be about 88.24%, and the overall channel is still limited by the fact that the official stable interface has not been officially opened.

• From October 3rd, the VIP price will continue to be maintained at ~$0.000/time to reward users.

• Current failures are mostly focused on content review. Sora has strict risk control, and prompt words containing mild pornography, horror and other elements are prone to failure.

• It is recommended to optimize the prompt words. If the failure rate is still high for reasons other than risk control, you can contact the official to join the exclusive technical support group.

Thank you for paying attention to the EvoLink.AI platform. We are committed to providing developers with stable and lowest-priced model services in the market.

VIP upgrade: From October 1st to October 8th, recharge ~$28.129 to upgrade to VIP and enjoy the same price list (same as above).

Happy holidays, dear customers! EvoLink.AI launches new features.

New model online:

1. Image: qwen-image-edit, wan2.5-text-to-image, wan2.5-image-to-image. Documentation: Wan 2.5 text to image

2. Video: wan2.5-text-to-video, wan2.5-image-to-video. Document: Wan 2.5 text to video

Seedream size parameter extended range, see: Seedream document​

Preview: Gemini 2.5 Pro and Claude 4.5 will be launched soon, official channels, and excellent prices.

System update today.

GPT-4O-Image model update:

1. Supported sizes: 1024x1024 (1:1), 1024x1536 (2:3), 1536x1024 (3:2).

2. Batch generation: 1, 2, 4 pictures.

3. Documentation: GPT-4O Documentation​

SeeDream-4.0 model update:

1. Size: simplified (1K, 2K, 4K); precise (9 ratios including 1024x1024).

2. Batch generation: 1-15 pictures.

3. Documentation: SeeDream Documentation​

Thanks for the user suggestions and looking forward to feedback.

Thank you for your support to evolink.ai. We have observed fluctuations in the main channel of nano banana in the background, and the price may be ~$0.014/piece.

Channel Description:

1. 3 channels: ~$0.007/ticket, ~$0.014/ticket, ~$0.015/ticket, the system automatically routes the lowest price available channel.

2. The stability of Channel 1 ($0.007) has declined, and Channel 2 ($0.014) has become the mainstream.

3. Actively communicate with channel parties, test new channels, and provide progress notifications.​

Thank you for paying attention to the EvoLink.AI platform. We are committed to providing developers with stable and lowest-priced model services in the market.

VIP upgrade: From September 23rd to September 31st, recharge ~$14.065 to upgrade to VIP and enjoy the same price list (same as above).

PS: VIP prices are stable for life, and upstream changes will be notified in advance.

Thank you for paying attention to the EvoLink.AI platform. We are committed to providing developers with stable and lowest-priced model services in the market.

VIP Upgrade: From September 19th to September 31st, you can upgrade to VIP by completing one payment and enjoy the same price list (same as above).

Thank you for your trust in EvoLink, we have updated the system.

API key security improvements:

1. Set the quota limit and model range when creating a new key.

2. Support usage statistics and display the used/remaining balance.

3. Provide limit adjustment without changing the key.

Thanks for the user suggestions and looking forward to more feedback.

Thank you for paying attention to the EvoLink.AI platform. We are committed to providing developers with stable and lowest-priced model services in the market.

VIP activity: Register an account before September 19th to enjoy VIP prices:

• seedream 4.0: ~$0.017/ticket (official website ~$0.028/ticket, 40% off)

• nano banana: $0.007-$0.015 per piece (official website ~$0.039/ticket, less than 20% off)

• Veo3-Fast: ~~$0.101-~$0.141/8s (official website ~$1.406/8s, discount of less than 10%)

• GPT-4O Image: ~~$0.017/image (official website ~$0.041/image, 41% off)

• Documentation: GPT-4o Documentation​

PS:

1. The event ends on September 19th. No new VIP members with no threshold will be added in the future. You can recommend it to your friends.

2. VIP members enjoy lifetime prices, long-term stability, and will be notified in advance if upstream changes.

3. Maintain the group atmosphere. Any illegal advertising or malicious behavior will result in VIP cancellation and removal.