Skip to content
HiAPI Docs
HiAPI
Playground Get API Key
English
English 中文

Changelog

2026-10-23

Section titled “2026-10-23”

Kling 4.0 is available through POST /v1/tasks. kling-4.0/text-to-video turns a prompt into a 3–30 second clip at 720p or 1080p in 16:9, 9:16, 1:1 or 21:9, with synchronized audio generated together with the picture. kling-4.0/image-to-video animates one first-frame image and keeps the source framing when aspect ratio is left out. Both are billed per output second with no minimum charge.

2026-10-08

Section titled “2026-10-08”

Added Nano Banana 2.1 API parameters and integration examples for image generation and reference editing.

2026-10-14

Section titled “2026-10-14”

Added FLUX.3 Image and Muse Image documentation for generation, reference editing and asynchronous tasks.

October 2026

  1. New model: kimi-k3.1-pro-highspeed, the faster variant of Kimi K3.1 Pro, through POST /v1/chat/completions. It shares the same request contract (1M-token context, always-on reasoning with low/high/max, streaming, JSON and strict JSON Schema output, function tools, and cache reads), responds faster, and costs more per token. See the Kimi K3.1 Pro Highspeed reference.

  2. New model: kimi-k3.1-pro through POST /v1/chat/completions, with a 1M-token context, always-on reasoning (low/high/max, default max), streaming, JSON and strict JSON Schema output, function tools, and cache reads. See the Kimi K3.1 Pro reference.

  3. New endpoint: GET /v1/account/balance returns your account-level remaining balance and total usage in USD with any valid API key — even an exhausted one — for balance monitoring and recharge alerts. Free to call, 60 requests per minute per account. See the Account Balance docs.

  4. New models: recraft-v4/text-to-vector and recraft-v4-pro/text-to-vector generate editable SVG vector files from text through POST /v1/tasks, for logos, icons, flat illustration and layout assets. Both tiers share the same parameters (prompt, image_size, colors, background_color); Pro adds more detail. One SVG file per request. See the Recraft V4 Vector docs.

  5. Imagen 4 model IDs are now imagen-4.0, imagen-4.0-fast and imagen-4.0-ultra. The previous IDs Google-Imagen4, imagen4-fast and imagen4-ultra still work as aliases; parameters, pricing and doc URLs are unchanged.

  6. Ideogram 4.5 text-to-image model ID is now ideogram-v4.5/text-to-image. The previous ID ideogram-v4.5 is still accepted; parameters, pricing and the doc URL are unchanged. ideogram-v4.5/image-to-image is not affected. The docs for both Ideogram 4.5 models now state that num_images is fixed at 1 per request, matching the API.

  7. New model: flux-1-kontext-max — FLUX.1 Kontext Max via POST /v1/tasks. Write a prompt to generate an image, or add one source image to edit it. Optional aspect_ratio (21:9, 16:9, 4:3, 1:1, 3:4, 9:16; empty keeps the source ratio when editing), output_format jpeg/png, prompt_upsampling, and safety_tolerance 0–2. One image per request, billed per output image. See the FLUX.1 Kontext Max docs.

  8. New models: flux-3-max/text-to-video, flux-3-max/image-to-video, and flux-3-max/keyframes-to-video via POST /v1/tasks. All three generate 5–20 second clips at 720p/1080p with synchronized audio on by default and low/high reasoning_level. Image-to-video takes a required first frame and an optional last frame; keyframes-to-video places 1–10 keyframes by frame_index on a 24fps timeline (maximum duration × 24, unique per request). See the FLUX 3 Max docs.

  9. New model: recraft/creative-upscale — generative upscaling that redraws texture and detail. A single required image_url input (PNG recommended, up to 20MB, each side 256–4096px, at most 16MP), no prompt, billed per output image via POST /v1/tasks.

  10. google-virtual-try-on: num_images is now fixed at 1 — each request returns one try-on image. Requests with num_images above 1 are rejected; omit the field or send 1. Billing is unchanged (per image).

  11. New model: bria-eraser — Bria Eraser via POST /v1/tasks. Upload an image and a black-and-white mask with the same aspect ratio; white is erased and the background is filled in, with no prompt needed. Optional mask_type (manual/automatic) and preserve_alpha. One PNG per request at the input resolution, billed per output image. See the Bria Eraser docs.

  12. New model: bria-product-shot — Bria Product Shot via POST /v1/tasks. Upload a product photo and set the new scene with exactly one of an English prompt or a reference_image_url; place the product at one of 10 preset positions (measured 1024×1024 for square input) or keep its original position (optionally at the input size). Optional optimize_description and fast. One image per request, billed per output image. See the Bria Product Shot docs.

  13. creatify-boreal: the optional manifest_disclosure parameter has been removed; stop sending it in requests. Other parameters are unchanged. See the Creatify Boreal docs.

  14. Added mureka-9.5/lyrics-to-song documentation: complete lyrics become a finished vocal song through POST /v1/tasks, with optional style direction and vocal gender.

  15. Added mureka-9.5/instrumental documentation: a text description of genre, mood, instruments, and arrangement becomes a vocal-free instrumental track through POST /v1/tasks.

  16. New model: fashn-tryon-v1.6 virtual try-on via POST /v1/tasks. One person photo plus one garment image returns a portrait try-on (measured 972 × 1296 in the verified run) with optional category, mode, garment photo type, moderation, seed and PNG/JPEG output; no prompt is needed. See the FASHN Try-On v1.6 docs.

  17. Added wan2.7-image-standard docs: Wan 2.7 Image standard tier covers text-to-image and reference editing with up to nine image_urls, 1K/2K output, eight aspect ratios, optional seed, and one image per request via POST /v1/tasks.

  18. New model: flux-1-fill-pro — FLUX.1 Fill Pro via POST /v1/tasks. Upload a source image, a same-size black-and-white mask and a prompt; white is repainted and black is kept. Optional steps (15–50), guidance (1.5–100), seed, output_format jpg/png and prompt_upsampling. One image per request, billed per output image. See the FLUX.1 Fill Pro docs.

  19. New model: mirelo-sfx-2.0 — Mirelo SFX 2.0 text-to-audio via POST /v1/tasks. Describe the source, material, action, distance, and environment of a sound to generate one 1–30 second WAV effect; duration defaults to 5 seconds and billing follows the requested output seconds.

  20. New model: elevenlabs/sound-effects-v2 — ElevenLabs Sound Effects v2 via POST /v1/tasks. One description becomes a 0.5–22 second sound effect with explicit per-request duration, adjustable prompt influence, optional seamless looping, and fixed MP3 output. See the ElevenLabs Sound Effects v2 docs.

  21. Added recraft-v4.1/text-to-image documentation: same parameters as Flash with more detail, 6 size presets, optional colors and background_color, one image per request.

  22. Added krea-2-medium-turbo text-to-image documentation: 8 aspect ratios including 2.35:1, four creativity levels (default low), optional seed, one image per request.

  23. New models: kandinsky-6.0-pro/text-to-video and kandinsky-6.0-pro/image-to-video — Kandinsky 6.0 Pro via POST /v1/tasks. Both produce a fixed 5-second 480p clip with synchronized audio, five aspect ratios on text-to-video and auto matching on image-to-video. Optional negative prompt, seed and guidance scale. Billed per video. See the Kandinsky 6.0 Pro docs.

  24. Added krea-3/text-to-image documentation: berry/jam variants, reasoning_level low/medium, 6 size presets up to 1024 × 1024, negative prompt (berry only), seed and PNG/JPEG output; one image per request.

  25. Added ideogram-v3-character and ideogram-v3-character/edit documentation: one character reference image keeps the same character consistent across new scenes (output ratio follows the reference), and Edit inpaints the referenced character into a masked area.

  26. New models: vidu-q3-mix/reference-to-video and vidu-q3-ad/reference-to-video — Vidu Q3 reference-to-video via POST /v1/tasks. Both take 1-7 reference images and expose one 10-value size enum covering five frames at the 720P and 1080P tiers. Mix runs 1-16 seconds for general scenes; Ad runs 3-15 seconds for product ads and may adjust the actual length to keep shots coherent, with billing on the actual output seconds. Audio and watermark are optional and not billed. See the Vidu Q3 Mix docs.

  27. Added recraft-v4.1-flash/text-to-image documentation: 6 size presets, optional colors and background_color palettes, one image per request.

  28. Added fibo-gen-1.5/text-to-image documentation: 9 aspect ratios and a reproducible seed, one PNG of about 1 MP per request.

  29. New model: google-virtual-try-on — Google Virtual Try-On via POST /v1/tasks. Send a person_image_url and a product_image_url to get 1–4 on-model try-on images; no prompt needed, billed per requested image. See the Google Virtual Try-On docs.

  30. New model: creatify-boreal — Creatify Boreal via POST /v1/tasks. One prompt becomes a 1–20 second product, UGC or presenter video with native speech and sound at 720p/1080p/2K in 5 aspect ratios plus auto; add an optional image_url reference or audio_url narration. Billed by requested seconds. See the Creatify Boreal docs.

  31. Added fibo-edit-1.5/image-to-image documentation: 1–4 image_urls, aspect_ratio for 2 or more images, mask_url for single-image local edits, one PNG per request.

  32. Added ideogram-v4.5 text-to-image and ideogram-v4.5/image-to-image documentation. Generation supports low/medium/high quality, size presets, prompt expansion, seeds, and 1–8 outputs; editing adds a primary source image, optional references, masks, and regular/high edit precision.

  33. New model: recraft/crisp-upscale — doubles image width and height with sharper detail and unchanged content. A single required image_url input (JPEG/PNG/WEBP, up to 10MB), no prompt, JPEG output, billed per output image via POST /v1/tasks.

  34. New model: wan2.6-flash/image-to-video — Wan 2.6 Flash via POST /v1/tasks. One image becomes a 5, 10 or 15 second 720p/1080p video that follows the aspect ratio of the image; optional synchronized audio is billed at the audio rate. See the Wan 2.6 Flash docs.

  35. New model: ltx-2.5-fast/text-to-video and ltx-2.5-fast/image-to-video — LTX 2.5 Fast via POST /v1/tasks. Both support 720p/1080p, 2-20 s, 16:9 or 9:16 and native audio; image-to-video takes a first frame plus an optional last frame. Billed per second; audio does not change the price. See the LTX 2.5 Fast docs.

  36. New models: grok-imagine-1.5-lite/text-to-video and grok-imagine-1.5-lite/image-to-video generate 1–15 second clips at 480p/720p/1080p with built-in sound via POST /v1/tasks; text-to-video offers 7 aspect ratios, while image-to-video takes one image_url and follows its aspect ratio. See the Grok Imagine 1.5 Lite docs.

  37. New model: vidu-q4-preview/image-to-video and vidu-q4-preview/reference-to-video — Vidu Q4 Preview via POST /v1/tasks. Image-to-video animates one first frame (3-16 s, 540p-4K, aspect follows the image); reference-to-video takes 1-15 reference images plus up to 3 MP3 voice references (3-12 s each), frame set by aspect_ratio. Native audio on by default, not billed. See the Vidu Q4 Preview docs.

  38. Added Google Imagen 4 image-generation docs: Google-Imagen4, imagen4-fast, and imagen4-ultra. All use POST /v1/tasks with prompt, negative prompt, aspect ratio, and an optional seed; Fast defaults to 16:9 while the standard and Ultra tiers default to 1:1.

  39. Added separate MiniMax H3 Max Text-to-Video and Image-to-Video references: text-to-video offers six aspect ratios; image-to-video accepts a first frame, a last frame or both. Both references document 480P/768P/1080P, 0.92–15 second target durations, target audio, seed and prompt expansion. The legacy name minimax-h3-max remains available only for API compatibility; existing requests are unaffected.

  40. New model: omnihuman-1.5 — ByteDance OmniHuman 1.5 via POST /v1/tasks. Give one portrait image_url and a driving audio_url under 60 seconds; the character speaks with lip-sync, expressions and body motion at 720p/1080p, keeps the portrait aspect ratio, and is billed per actual output second.

  41. Added wan3.0-video-prime docs: the fast Wan 3.0 route with text, first/last frames, image/audio references, files and webpages, 2–30 s, 480P–1080P and synchronized audio; reference video input is not available yet.

  42. New models: Kling 3.0 Omni (可灵 O3) via POST /v1/tasks. kling-3.0-omni/text-to-video and kling-3.0-omni/image-to-video generate 3–15 second clips at 720p/1080p/4k with optional native audio, smart multi-shot, and elements subjects referenced as @name; image-to-video takes a first frame or first/last frames. kling-3.0-omni/reference-to-video accepts 1–7 reference images plus an optional reference video, and kling-3.0-omni/transformation rewrites a source video while keeping its camera motion. See the Kling 3.0 Omni docs.

  43. Runway Gen-4.5 Text-to-Video adds 9:16 portrait at 5/10s; 16:9 keeps 5/8/10s. Playground now applies aspect-based duration choices and price estimates. Kling 2.5 Turbo Image-to-Video negative prompts allow up to 2496 characters.

  44. Added kling-2.5-turbo/text-to-video docs: 5/10s, landscape, portrait and square, with audio. kling-2.5-turbo/image-to-video now documents first and optional last frames, 5/10s, six ratios, negative prompts and prompt adherence. Two frames support 16:9/9:16/1:1; output has no audio track.

  45. New models: pixverse-v6/text-to-video and pixverse-v6/image-to-video generate 1–15 second clips at 360p–1080p with optional synchronized audio and five style presets; text-to-video offers 8 aspect ratios, while image-to-video follows the first frame. Also added Luma Ray 3.2: ray-3.2/text-to-video generates 5- or 10-second clips from a prompt at 540p/720p/1080p in 6 aspect ratios, and ray-3.2/image-to-video turns a first frame and optional last frame into a 5-second clip at 540p/720p/1080p. See the PixVerse V6 and Ray 3.2 docs.

  46. New video model docs: kling-2.5-turbo/image-to-video (first-frame driven, fixed 5s 1080p, 16:9/9:16/1:1), runway-gen-4.5/text-to-video (720p 16:9, 5/8/10s) and runway-gen-4.5/image-to-video (first-frame driven, 720p, 5/8/10s, 16:9/9:16/4:3/3:4/1:1). All use POST /v1/tasks.

  47. Updated gemini-omni-1.1-flash docs: duration is a required integer (4/6/8/10), video_list items take url plus optional start/ends, and the input combination rules (first frame vs. reference media, 7 shared input slots) are documented.

  48. New model: kling-3.0/motion-control — Kling 3.0 Motion Control via POST /v1/tasks. Give one character image_url and a 3-30 second motion video_url; the character performs the reference motion and expressions at 720p/1080p. Output length follows the clip (up to 30s in video orientation, 10s in image orientation) and is billed per actual output second.

  49. New model: heygen-avatar-iv turns one portrait photo into a lip-synced talking video from a script and preset voice or from driving audio, with 102 voices, six aspect ratios including auto, 720p/1080p output, color or image backgrounds, and billing by actual generated-video seconds.

September 2026

  1. Added Seedream 5.0 Flash for image generation and reference editing, with 1K/1.5K/2K presets, custom dimensions, and watermark off by default.

  2. Added elevenlabs/music-v2.5 API documentation: generate songs or instrumentals from a music description or a chunk-by-chunk composition plan, with per-chunk styles, reference audio, seed, and output format inputs.

  3. Added lyria-3.5 API documentation for song generation from a musical description or optional lyrics, with title, tempo guidance, duration, and seed inputs.

September 2026

  1. Updated deepseek-v4.1-flash to its production model reference with low reasoning effort and text/image input documentation.

September 2026

  1. Added GPT Image 2.5 Flare and Sunburst references: each model supports text-to-image and editing, up to 16 references, six quality settings, and multiple layouts.

  2. New deepseek-v4.1-flash Preview reference: Responses and Chat Completions request shapes, none/high/max reasoning, stateless conversation history, streaming events, and token billing.

  3. Added minimax-h3-max API documentation: one model for text-to-video and first/last-frame guidance, with 480P / 768P and 5–15 second output.

  4. New gpt-6-astra documentation: streaming Responses, five reasoning efforts, function calls, strict JSON Schema, and cache-aware whole-request context-tier billing.

  5. New documentation for 851-labs/background-remover: submit one image URL, receive a transparent PNG, and explore a verified product example with asynchronous task retrieval.

September 2026

  1. New model: recraft/remove-background — one-click background removal to transparent PNG with hair and fur-level edge preservation. A single required image_url input (PNG/JPG/WebP, up to 5MB, 256–4096 px, up to 16MP), no prompt, billed per output image via POST /v1/tasks.

August 2026

  1. New model: heygen-avatar-v for presenter-led avatar video from a script and preset voice or from driving audio. It supports 497 avatar presets, 102 voices, MP4/WebM output, optional SRT captions, custom backgrounds, and billing by actual generated-video seconds.

  2. New model docs: qwen-image-3.0/text-to-image, qwen-image-3.0/image-to-image, qwen-image-3.0-pro/text-to-image, and qwen-image-3.0-pro/image-to-image. All use POST /v1/tasks; image-to-image requires 1–3 reference images, while every model supports 8 aspect ratios, 1K/2K output, PNG/JPEG delivery, prompt controls, and task callbacks.

  3. New model: minimax-music-3 — MiniMax high-fidelity song generation with controllable length. Required lyrics with structure tags, duration caps output at 1-300 seconds (default 60), and seed reproduces results. Lossless WAV output billed per second of requested duration.

  4. New models: grok-imagine-image-2.0/text-to-image and grok-imagine-image-2.0/image-to-image — Grok Image 2.0 generation and single-reference editing. Text-to-image supports low/medium quality, 1k/2k resolution, and 13 aspect ratios plus auto; image-to-image accepts one public image and follows the reference framing. See live pricing.

  5. deepseek-v4-pro is now documented for native POST /v1/responses and compatible Chat Completions, with a 1M-token context, 384K maximum output, none/low/high/max reasoning, streaming, JSON output, and tools.

  6. Remote MCP v0.4.0 now exposes 9 live-catalog tools. New generate_text support selects Chat Completions or Responses by model, get_task_status retrieves long-running media tasks, and generic parameters let newly listed task models work without a server release. The Agent Skills guide now includes the latest Seedance 2.5 and Seedream 5.0 Pro integrations.

  7. The seedance-2.0 ext route now exposes only its supported 720p, 1080p, and 4k tiers. The unsupported 2k option has been removed from pricing and request documentation.

  8. New models: seedance-2.5/text-to-video, seedance-2.5/image-to-video, and seedance-2.5/reference-to-video. The default is 480p for 5 seconds; you can choose 720p and 4–30 seconds. All support synchronized audio; image-to-video supports first/last-frame control, while reference-to-video requires 1–10 reference videos and accepts optional image and audio references.

  9. deepseek-v4-flash is available through POST /v1/chat/completions, with streaming, thinking controls, high/max reasoning effort, JSON mode, tools, and Token usage. Media models continue to use POST /v1/tasks.

  10. New model: flux-3 by Black Forest Labs for text-to-video, 1-10 image keyframe storyboards, and source-video continuation. It generates 5-20 second clips at 720p/1080p with optional synchronized audio and a lower-cost 720p Draft tier.

July 2026

  1. New model: minimax-h3 — native 2K video generation through POST /v1/tasks, with 4-15 second duration, text-to-video, first/last-frame control, and image/video/audio multimodal references. Billed per output second.

  2. New image-editing models: flux-2-klein-4b/image-to-image for low-cost single-reference edits with 0.25-4 MP output tiers, and flux-2-klein-9b/image-to-image for fast four-step edits with stronger detail preservation and text rendering.

  3. New models: flux-2-klein-4b/text-to-image for cost-efficient 0.25-4 MP generation, and flux-2-klein-9b/text-to-image for fast four-step output with stronger realistic detail and readable in-image text.

  4. seedance-2.0 now documents standard and ext routes on one page. Keep the base model name and pass top-level route: "ext"; the ext route supports 720p/1080p/4k plus image and audio references.

  5. Go and Java joined the official SDK lineup — go get github.com/HiAPIAI/hiapi-go and ai.hiapi:hiapi on Maven Central, alongside the existing Python SDK (pip install hiapi). All three now ship v0.2.1 with model route selection and Idempotency-Key retries built in. See the SDKs page.

  6. New models: Seedream 5.0 Pro Text to Image and Image to Image — HiAPI flagship quality tier. Upgraded photorealism with sharp in-image text rendering (brush calligraphy and signage verified), resolution 1K/2K output 1K/2K images billed per image; editing takes 1-10 reference images.

  7. New models: MiniMax Hailuo 2.3 — standard hailuo-2.3/text-to-video and image-to-video (6/10s per-video tiers, motion-physics leader), plus hailuo-2.3-fast image-to-video at a lower price for batch animation.

  8. New models: Kling 3.0 Turbo Text to Video and Image to Video — fast, lower-cost clips. 3-15 second clips at 720p/1080p with per-second tiered billing and lip-synced quoted dialogue; image-to-video is first-frame driven.

  9. New models: Grok Imagine Text to Image and Image to Image — xAI's image generation line with 13 aspect ratios (ultra-wide 2:1/20:9 to extra-tall 9:20) and reference edits with up to 3 images. Both bill one flat rate per image; for hero-grade output, grok-imagine-quality is tiered by 1k/2k resolution.

  10. New models: Seedream 4.5 Text to Image and Image to Image — ByteDance's community-favorite quality tier. Photorealistic detail with accurate in-image text rendering (English and Chinese), 8 aspect ratios, 2K/4K at one flat per-image price; editing takes up to 14 reference images with subject and text consistency.

  11. New model: FLUX.2 Image to Image — pro-tier image editing with up to 8 reference images per request. Multi-image composition, background replacement, style and material edits with strong subject and logo consistency; aspect_ratio: auto follows the first input, 1K/2K output billed per image.

  12. New model: MiniMax Music 2.6 — full-song music generation with natural vocals in English or Chinese. Lyrics up to 3,500 characters with 14 structure tags, instrumental mode via is_instrumental, and auto-generated lyrics when lyrics is left empty. Billed per song.

  13. POST /v1/tasks now accepts an optional top-level route parameter for models with multiple routes — passing the bare model name with route: "pro" is the preferred spelling of the legacy @pro suffix (the old suffix keeps working). An unknown route returns a 400 listing the available routes, and the task detail echoes route plus the resolved full model name. See Model routes on the Create Task page.

  14. New models: five additions across image, video and audio — Nano Banana 2 Lite (entry-tier 1K image generation), Qwen Image 2.0 Pro (pro-grade text rendering and photorealism), Ideogram V4 (best-in-class typography with TURBO/BALANCED/QUALITY tiers), Grok Imagine 1.5 Image to Video preview (upgraded motion, 1–15s), and MiniMax Music 1.5 (full songs up to 4 minutes with vocals, HiAPI's first music model).

  15. New models: Seedream 5.0 Lite Text to Image and Image to Image — ByteDance's reasoning-capable image model with real-time web knowledge and accurate multilingual text rendering. Editing supports up to 14 reference images and in-image text rewriting. 2K/4K output at the same per-image price.

  16. POST /v1/tasks now accepts an optional Idempotency-Key header — retries with the same key under the same account create the task only once, and replays return the original taskId, preventing duplicate tasks and duplicate charges from timeout retries. See Idempotency key in the Unified Async API intro.

  17. New models: Veo 3.1 Text to Video and Image to Video — Google's flagship video tier with cinematic quality, native audio, up to 4K, and 4/6/8-second clips. Also added Veo 3.1 Fast Image to Video, the cost-efficient way to animate stills.

  18. New model: ElevenLabs Text to Dialogue v3 — HiAPI's first audio model. Multi-speaker dialogue speech with a voice per line (67 presets), 70+ languages, tunable stability, billed per character.

  19. New models: Grok Imagine Text to Video and Image to Video — xAI Grok Imagine video generation with selectable motion mode, aspect ratio, 6–30s duration, and 480p/720p resolution.

  20. seedance-2.0 now supports 4k resolution — pick 480p, 720p, 1080p, or 4k for ultra HD output.

  21. New model: Seedance 2.0 Fast — ByteDance's high-speed video model for text-to-video, image-to-video (first/last frame), and multimodal reference-to-video (image/video/audio), with native audio. 480p/720p, 4–15s, billed per second.

June 2026

  1. New model: Seedance 2.0 Mini — ByteDance's cost-efficient video model for both text-to-video and image-to-video, with native audio, first/last-frame control, and image/video/audio multimodal references. 480p/720p, 4–15s, billed per second.

  2. Output Storage is live — keep the images and videos you create with POST /v1/tasks past the default 7 days. Pick a storage tier when you create a task, or promote existing outputs to long-term storage, then list and delete them from the API or your dashboard. Results are still fetched the same way, via GET /v1/tasks/:id or a callback.url.

May 2026

  1. New model: HappyHorse 1.0 text-to-video — 720p/1080p, 3–15s, multiple aspect ratios.

  2. Agent Skills — call a single model straight from Codex, Claude Code, OpenClaw and other agents with one install.

April 2026

  1. gpt-image-2 added 1K / 2K / 4K resolution tiers.

  2. Remote MCP server — connect any MCP client and generate with image and video tools over a single endpoint.

  3. New models: Qwen Image 2.0 and Seedance 2.0.