API Changelog - Apiframe

August 2026 — Kling video prices

Kling 2.1, 2.1 Master, 2.5 Turbo Pro, 2.6, 3.0, 3.0 Omni, and 3.0 Motion Control are cheaper.

See Credit costs for the full table.

August 2026 — Official model prices

Most official models are cheaper. Midjourney, Midjourney Video, Suno, Udio, and Producer are unchanged.

See Credit costs for the full table.

August 2026 — Midjourney, Flux LoRA, GPT Image 1.5

Midjourney imagine / variation / inpaint / outpaint / pan is now 10. Upsample is 2.
Flux LoRA inference is now 19 per image. LoRA training is 315.
GPT Image 1.5 is now 2 / 8 / 23 / 23 (low / medium / auto / high).
Mureka is now 8. 851-labs background remove is 1.

See Credit costs for the full table.

August 2026 — Udio and Suno stems

Udio is now 9 / 17 / 26 / 35 by duration (32s / 65s / 97s / 130s). Extend is 9. Remix matches the duration.
Suno stems is now 20.

See Credit costs for the full table.

August 2026 — Price updates

Several models are cheaper. Highlights:

Grok Video 1.5 is now 14/s (84 / 140 / 210).
Grok Image Fast is now 3 credits.
Wan 2.5 Fast 1080p-5s is 87 and 720p-10s is 116.
ElevenLabs Music is now 13 / 51 / 128 (short / medium / long).
Flux 2 Dev is now 1 / 2 / 4 from width × height (was a flat 6).
Seedance 2 / 2 Fast / 2 Mini, GPT Image low, Seedream 3–5, Flux 2 Pro / Flex / Max (lower MP tiers), and Topaz Video 1080p also dropped.

See Credit costs for the full table.

August 2026 — Grok Image 2 (Imagine Image 2.0)

xAI's Imagine Image 2.0 is on POST /v2/images/generate as grok-image. Text-to-image and editing, with quality (low / medium) and output up to 2K.

8 credits per generation. Existing grok-imagine-image (Grok Image Fast) is 3 credits.
Grok video models keep their API ids (grok-imagine-video, grok-imagine-video-1.5) and are labeled Grok Video / Grok Video 1.5.

See Credit costs for details.

August 2026 — Hailuo 03 768p and 2K regen

hailuo-03 now accepts hailuoParams.resolution of "768p" or "2K" (default still "2K"). Pass hailuoParams.base_video with the original prompt and frames or references to regenerate a 768p H3 clip at 2K.

Per-second pricing: 14/s at 768p, 22/s at 2K, 9/s for 2K regen (billed on the probed source duration). Extra reference images past the first five are 7 on generate and 4 on regen.

See Credit costs for details.

August 2026 — Ideogram v4 aspect ratio

Ideogram v4 dropped aspect_ratio as an input; size is controlled only by resolution. Requests that passed ideogramParams.aspect_ratio were accepted and silently returned a square.

aspect_ratio on ideogram-v4-turbo, ideogram-v4-balanced, and ideogram-v4-quality is now mapped to a matching pixel resolution (for example "16:9" → "1920x1088"). An explicit ideogramParams.resolution still wins. v2/v3 and Character are unchanged.

August 2026 — Remote MCP server

Apiframe now speaks MCP: point Claude, Cursor, or any MCP client at https://mcp.apiframe.ai with your API key in the X-API-Key header and generate from plain language.

Nine tools: generate_image, generate_video, generate_music, edit_image, upscale_image, upscale_video, remove_background, get_job, list_models.
Stateless streamable HTTP; the same jobs, credits, and rate limits as the REST API — tool arguments are validated with the same schemas.
list_models reports model ids, credit costs, and per-model parameter names so agents can discover the catalog before generating.

See the MCP docs for setup snippets.

August 2026 — Seedance 2.0 4K price update

Seedance 2.0's 4k tier is now 232/s (was 170/s) and 285/s with reference videos (was 213/s). All other Seedance 2.0 tiers are unchanged.

See Credit costs for details.

August 2026 — Seedance 2.5 (ByteDance)

ByteDance's next-generation video model lands on POST /v2/videos/generate as seedance-2.5.

Single-pass clips up to 30 seconds (any integer duration from 4 to 30) with native synchronized audio, at 480p or 720p.
Up to 50 multimodal references in one request via seedanceParams: reference_image_urls (max 30), reference_video_urls (max 10), and reference_audio_urls (max 10).
Three input modes, and frame anchors cannot be mixed with reference media: text only, first/last frame (start_image, end_image), or references.
Unlike Seedance 2.0 there is no web_search, camera_fixed, 1080p, or 4k.
Per-second pricing: 18/s at 480p, 40/s at 720p (21/s and 47/s with reference videos).

See Credit costs for details.

July 2026 — Hailuo 03 / MiniMax H3 (MiniMax)

MiniMax's H3 lands on POST /v2/videos/generate as hailuo-03.

Native 2K output from 4 to 15 seconds, with stereo audio generated in the same pass rather than dubbed on afterwards.
Three input modes in hailuoParams, and they cannot be mixed: text only, first/last frame (image, end_image), or references (reference_images up to 9, reference_videos up to 3, reference_audios up to 3). reference_audios needs at least one image or video reference alongside it.
Adds aspect_ratio with an auto option that follows the input media. Text-only requests must pick a concrete ratio. Prompts accept up to 7,000 characters.
Per-second pricing at 22/s, billed on output duration plus the measured duration of any reference videos. Reference videos are probed before submission and rejected if they exceed 15 seconds in total, so nothing is charged for a request upstream would refuse.
Reference images past the first five add 7 credits each.

See Credit costs for details.

July 2026 — Kling 3.0 Motion Control (Kuaishou)

Kuaishou's Kling 3.0 Motion Control lands on POST /v2/videos/generate as kling-3.0-motion-control.

Transfers motion from a reference video onto the character in a reference image — both are required in klingParams.
Adds mode (std 720p / pro 1080p), character_orientation (image caps the clip at 10s, video at 30s), and keep_original_sound to klingParams.
Per-second pricing billed on the reference video's measured duration: 12/s for std, 21/s for pro. Clips outside the allowed range are rejected before any credits are charged.

See Credit costs for details.

July 2026 — Kling 3.0 Omni (Kuaishou)

Kuaishou's unified Kling model lands on POST /v2/videos/generate as kling-3.0-omni.

One model for text-to-video, image-to-video, reference-to-video, and video editing/restyling with native audio.
Adds reference_images (up to 7; refer to them in the prompt as <<<image_1>>>, …), reference_video + video_reference_type (feature for style/camera, base for editing), and keep_original_sound to klingParams. multi_prompt is a JSON array of { prompt, duration } shots (max 6).
generate_audio is mutually exclusive with reference_video; when a reference video is set, video_reference_type is required and reference_images is capped at 4.
Same standard/pro/4K modes and per-second pricing as Kling 3.0: 29/s standard, 39/s pro, 72/s 4K (+audio: 43/s standard, 58/s pro; 4K bills 72/s with or without audio).

See Credit costs for details.

July 2026 — Stable Diffusion 3 & 3.5 (Stability AI)

Stability AI's Stable Diffusion models land on POST /v2/images/generate.

stable-diffusion-3.5-large: highest-quality SD 3.5 tier. 12 credits per image.
stable-diffusion-3.5-large-turbo: near-Large quality in ~4 steps for fast, cheap generation. 8 credits per image.
stable-diffusion-3.5-medium: efficient mid-size SD 3.5 model. 7 credits per image.
stable-diffusion-3: the original SD 3 Medium MMDiT model with strong prompt adherence and typography. 7 credits per image.
All four share stableDiffusionParams (aspect_ratio, cfg, steps, seed, negative_prompt, image, prompt_strength, output_format, output_quality) and support image-to-image via image.

See Credit costs for details.

July 2026 — Nano Banana 2 Lite (Google)

Google's fastest, most cost-efficient Nano Banana model lands on POST /v2/images/generate as nano-banana-2-lite.

Built on Gemini 3.1 Flash Lite Image — text-to-image in roughly 4 seconds, ideal for prototyping and high-volume workflows.
Outputs at 1K resolution only (no resolution parameter). Supports 14 aspect ratios, jpg/png output, image input, and Google Search / Image Search grounding via nanoBananaParams.
Flat pricing: 7 credits per image. See Credit costs.

June 2026 — Happy Horse 1.0 & 1.1 (Alibaba)

Alibaba's Happy Horse video models land on POST /v2/videos/generate, with automatic failover. Both bill per second of output by resolution and generate synchronized audio.

happyhorse-1.0: text-to-video and image-to-video (single first-frame image), 720p/1080p, 3–15 s. Pricing: 24/s @720p, 48/s @1080p.
happyhorse-1.1: adds reference-to-video — pass up to 9 images and reference them in the prompt as [Image 1], [Image 2], etc. Stronger motion and character consistency. Pricing: 24/s @720p, 31/s @1080p.
Mode is selected automatically: 1.0 from the presence of image; 1.1 from the number of images (0 = T2V, 1 = I2V, 2–9 = R2V).

See Credit costs for details.

April 2026 — GPT Image 2 (OpenAI)

OpenAI's new SOTA image model lands on POST /v2/images/generate as gpt-image-2, alongside the existing gpt-image-1.5.

Same dual-mode contract as 1.5: omit input_images for text-to-image, pass one or more URLs to edit / compose. The model always processes inputs at high fidelity.
New gptImage2Params.moderation (auto / low) for less restrictive content filtering.
webp is the default output format.
No transparent background — keep using gpt-image-1.5 for transparent PNGs.
Pricing per output image: low 4 / medium 9 / high 23 / auto 23, multiplied by number_of_images. See Credit costs and the gpt-image-2 reference.

April 2026 — AI Photos (LoRA training)

A brand-new family of endpoints lets you train a Flux LoRA from 15-30 subject photos and then generate AI photos of that subject from any text prompt.

POST /v2/loras — multipart upload + start training. The API auto-captions every image with a vision model, packages the dataset, and runs the LoRA training. Returns 202 with the new LoRA id.
GET /v2/loras — paginated list of your team's LoRAs.
GET /v2/loras/:id — single lookup; status transitions through PENDING → UPLOADING → TRAINING → READY (or FAILED). Optional webhookUrl fires on terminal state.
DELETE /v2/loras/:id — soft-archive.
POST /v2/images/generate — new model flux-lora: pass loraId + a prompt and the API resolves the trained weights and prepends the trigger word for you. 1-4 outputs per request.

Pricing is flat: 1 credit for create (upload+caption+zip), 268 credits for training, 16 credits per image for inference. See Credit costs → AI Photos and the AI Photos overview.

April 2026 — Wan 2.7

The Wan 2.7 family ships with a brand-new video-editing route:

POST /v2/videos/generate — wan-2.7: combined T2V + I2V at 720p/1080p, 2–15 s. New first-and-last-frame (last_frame) and clip-continuation (first_clip) anchors. Audio is auto-generated when audio is omitted.
POST /v2/videos/generate — wan-2.7-r2v: reference-to-video. Up to 5 reference_images and/or 5 reference_videos, plus shot_type for multi-shot narratives.
POST /v2/videos/edit (NEW) — wan-2.7-videoedit: prompt-driven restyle, outfit swap, and background replacement on existing clips. The route probes input duration via ffprobe when duration is omitted.

All three are billed per second of output. See Credit costs → Wan 2.7.

April 2026 — Editing endpoints

Four new endpoints for editing existing media, on dedicated routes alongside generation:

POST /v2/images/upscale — Topaz Image Upscale for realistic photos and Clarity Upscaler for creative AI art.
POST /v2/images/background-remove — Bria RMBG 2.0 for production-quality alpha mattes and 851-labs for cheap, high-volume jobs.
POST /v2/images/edit — Flux Fill Pro for masked inpainting and preset-driven outpainting (mode-switched).
POST /v2/videos/upscale — Topaz Video Upscale with up to 4K / 60 fps output and per-second pricing.

v2.0.0 — March 2026

Initial release of the Apiframe v2 API.

Image generation

Midjourney model with aspect ratio support
Nano Banana model with image-to-image and output format options

Video generation

Kling 2.6 Pro with 5s/10s duration, start image, audio generation, negative prompts

Music generation

Suno with custom lyrics mode, instrumental mode, style control, and model version selection (V4 through V5)

Platform

API key authentication with X-API-Key header
Webhook notifications for job progress, completion, and failure
Cursor-based pagination on all list endpoints
Idempotency key support for generation requests
Credit-based billing with automatic refunds on failures
Team management with role-based access

Changelog

On this page