gpt-image-2.5-flare
OnlineText-to-image and editing in one model, with up to 16 references.
gpt-image-2.5-flare Models Overview
Text models use POST /v1/responses or the compatible POST /v1/chat/completions, depending on the model. Image, video, and audio models use the asynchronous POST /v1/tasks endpoint. The same HiAPI API key works across enabled models, while endpoint and request shape depend on the protocol family.
Current pricing is maintained on the main site: HiAPI Pricing.
Image Models
Text-to-image, image-to-image, reference editing, and photorealistic generation.
gpt-image-2.5-sunburst
OnlineText-to-image and editing in one model, with up to 16 references.
gpt-image-2.5-sunburst 851-labs/background-remover
OnlineSingle-image background removal with transparent PNG output and no prompt.
851-labs/background-remover gpt-image-2/text-to-image
OnlineText-to-image with accurate text rendering; @beta / @ext routes available.
gpt-image-2/text-to-image gpt-image-2/image-to-image
OnlineImage-to-image from 1–6 references; an @ext route is also available.
gpt-image-2/image-to-image grok-imagine/text-to-image
OnlinexAI standard text-to-image: fast, low-cost, 13 aspect ratios.
grok-imagine/text-to-image grok-imagine/image-to-image
OnlinexAI image editing: reference-based repaint, composite, transform.
grok-imagine/image-to-image grok-imagine-image-2.0/text-to-image
OnlineGrok Image 2.0 text-to-image with 1k/2k output and flexible aspect ratios.
grok-imagine-image-2.0/text-to-image grok-imagine-image-2.0/image-to-image
OnlineGrok Image 2.0 image editing from one reference image and a natural-language instruction.
grok-imagine-image-2.0/image-to-image grok-imagine-quality/text-to-image
OnlinexAI quality text-to-image: hero-grade detail, 1k/2k tiers.
grok-imagine-quality/text-to-image grok-imagine-quality/image-to-image
OnlinexAI quality image editing with 1k/2k tiers.
grok-imagine-quality/image-to-image seedream-4.5/text-to-image
OnlineByteDance Seedream 4.5 text-to-image: 4K and in-image CJK text.
seedream-4.5/text-to-image seedream-4.5/image-to-image
OnlineSeedream 4.5 image editing with up to 14 reference images.
seedream-4.5/image-to-image flux-3-image
OnlineFLUX.3 Image API turns prompts and references into detailed visuals for products, spaces and creative work. Try online and view images, pricing and guides.
flux-3-image muse-image-1.0/text-to-image
OnlineMuse Image API creates illustrations and layouts for book covers, posters and content. Try online and explore images, live pricing and API guides.
muse-image-1.0/text-to-image muse-image-1.0/image-to-image
OnlineMuse Image API edits subjects, colors and layouts from references for covers and posters. Try online and see image comparisons, pricing and API guides.
muse-image-1.0/image-to-image seedream-5.0-flash
OnlineSeedream 5.0 Flash: generation, editing and multi-reference blending.
seedream-5.0-flash seedream-5.0-lite/text-to-image
OnlineSeedream 5.0 Lite text-to-image: budget-friendly volume generation.
seedream-5.0-lite/text-to-image seedream-5.0-lite/image-to-image
OnlineSeedream 5.0 Lite instruction-based image editing.
seedream-5.0-lite/image-to-image nano-banana
OnlineFast, prompt-tolerant text-to-image for quick iteration.
nano-banana gemini-nano-banana-2.1
OnlineImage generation and reference editing for product posters and ad banners.
gemini-nano-banana-2.1 nano-banana-2
OnlineBalanced tier with optional references and 1K / 2K / 4K output.
nano-banana-2 Nano-Banana-2-Lite
OnlineLite tier: low-cost, fast generation.
Nano-Banana-2-Lite nano-banana-pro
OnlinePremium brand visuals, reference editing, high-resolution output.
nano-banana-pro flux-2/text-to-image
OnlineFLUX.2 Pro text-to-image: photorealism with design control.
flux-2/text-to-image flux-2/image-to-image
OnlineFLUX.2 image editing: background swap, material edit, multi-image composite.
flux-2/image-to-image flux-1.1-pro
OnlinePhotorealistic generation with optional reference guidance.
flux-1.1-pro flux-schnell/text-to-image
OnlineFLUX schnell tier: sub-second-class generation.
flux-schnell/text-to-image qwen-image-2.0
OnlineLow-cost model with strong Chinese prompts and CJK text rendering.
qwen-image-2.0 qwen-image-2.0-pro
OnlineQwen image Pro tier: richer detail and layout.
qwen-image-2.0-pro ideogram-v3-character
OnlineIdeogram 3.0 Character keeps one referenced character consistent across new scenes.
ideogram-v3-character ideogram-v3-character/edit
OnlineIdeogram 3.0 Character Edit inpaints the referenced character into a masked area.
ideogram-v3-character/edit qwen-image-3.0/text-to-image
OnlineQwen Image 3.0 text-to-image for Chinese text, posters, and creative visuals.
qwen-image-3.0/text-to-image qwen-image-2.1-pro
OnlineQwen Image 2.1 Pro combines text-to-image and editing with up to 10 references.
qwen-image-2.1-pro qwen-image-2.1-turbo
OnlineQwen Image 2.1 Turbo is the fast, best-value tier sharing the Pro contract.
qwen-image-2.1-turbo qwen-image-3.0/image-to-image
OnlineQwen Image 3.0 image-to-image with 1–3 references for redraws and refinement.
qwen-image-3.0/image-to-image qwen-image-3.0-pro/text-to-image
OnlineQwen Image 3.0 Pro text-to-image for high-fidelity final assets, complex materials, and refined layouts.
qwen-image-3.0-pro/text-to-image qwen-image-3.0-pro/image-to-image
OnlineQwen Image 3.0 Pro image-to-image for high-fidelity reference redraws and refinement.
qwen-image-3.0-pro/image-to-image z-image
OnlinePhotoreal portraits and photographic scenes.
z-image wan2.7-image/text-to-image
OnlineAlibaba Wan 2.7 text-to-image with commercial-photo finish.
wan2.7-image/text-to-image wan2.7-image-standard
OnlineWan 2.7 Image standard tier combines text-to-image and reference editing with up to nine references at 1K/2K.
wan2.7-image-standard ideogram-v4
OnlineStrong at typography and logo design.
ideogram-v4 google-virtual-try-on
OnlineGoogle virtual try-on: a person photo plus a garment photo becomes an on-model image, one per request.
google-virtual-try-on ideogram-v4.5/text-to-image
OnlineIdeogram 4.5 text-to-image for typography-led logos, posters, and signage.
ideogram-v4.5/text-to-image ideogram-v4.5/image-to-image
OnlineIdeogram 4.5 Edit image editing with natural-language edits and reference composites.
ideogram-v4.5/image-to-image imagen-4.0
OnlineImagen 4 for everyday product and content images from text.
imagen-4.0 imagen-4.0-fast
OnlineImagen 4 Fast for quicker direction exploration and batch drafts.
imagen-4.0-fast imagen-4.0-ultra
OnlineImagen 4 Ultra for high-detail finished images from text.
imagen-4.0-ultra recraft/remove-background
OnlineOne-click background removal to transparent PNG with hair-level edges.
recraft/remove-background recraft/crisp-upscale
OnlineUpscale images 2× with sharper detail and unchanged content.
recraft/crisp-upscale recraft/creative-upscale
OnlineUpscale an image to a higher resolution with redrawn texture and detail, no prompt.
recraft/creative-upscale recraft-v4.1-flash/text-to-image
OnlineRecraft V4.1 Flash text-to-image for fast photos, illustrations and posters with custom palettes.
recraft-v4.1-flash/text-to-image krea-3/text-to-image
OnlineKrea 3 text-to-image with prompt reasoning, berry for quality or jam for speed, six sizes up to 1024 × 1024.
krea-3/text-to-image recraft-v4.1/text-to-image
OnlineRecraft V4.1 text-to-image for detailed photos, illustrations and posters with custom palettes.
recraft-v4.1/text-to-image recraft-v4/text-to-vector
OnlineRecraft V4 Vector turns text into editable SVG for logos, icons and flat illustration.
recraft-v4/text-to-vector recraft-v4-pro/text-to-vector
OnlineRecraft V4 Pro Vector produces higher-fidelity editable SVG for finished logos and detailed illustration.
recraft-v4-pro/text-to-vector fibo-gen-1.5/text-to-image
OnlineFIBO Gen 1.5 text-to-image for photoreal images and accurate in-image text.
fibo-gen-1.5/text-to-image krea-2-medium-turbo
OnlineKrea 2 Medium Turbo fast text-to-image with 8 ratios including 2.35:1 and 4 creativity levels.
krea-2-medium-turbo fibo-edit-1.5/image-to-image
OnlineFIBO Edit 1.5 image editing with multi-image compositing and mask edits.
fibo-edit-1.5/image-to-image fashn-tryon-v1.6
OnlineFASHN Try-On v1.6 virtual try-on: person photo plus garment image, supporting tops, bottoms and one-pieces.
fashn-tryon-v1.6 flux-1-fill-pro
OnlineFLUX.1 Fill Pro mask inpainting: white repaints, black keeps, for product retouching, background swaps and clean-up.
flux-1-fill-pro flux-1-kontext-max
OnlineFLUX.1 Kontext Max text-to-image and single-image editing: generate from a prompt or edit one photo while keeping subjects, text and style.
flux-1-kontext-max bria-eraser
OnlineBria Eraser mask-based object removal: white erases, black keeps, no prompt needed; removes passers-by, clutter and blemishes.
bria-eraser bria-product-shot
OnlineBria Product Shot product scenes from an English description or a scene reference, with preset or original placement.
bria-product-shot Video Models
Text-to-video, image-to-video, reference media, and short-form generation.
kling-2.5-turbo/image-to-video
OnlineKling 2.5 Turbo Image-to-Video: first frame and optional last frame, 5/10s, no audio track.
kling-2.5-turbo/image-to-video kling-2.5-turbo/text-to-video
OnlineKling 2.5 Turbo Text-to-Video: 5/10s, landscape, portrait and square, with audio.
kling-2.5-turbo/text-to-video runway-gen-4.5/text-to-video
OnlineRunway Gen-4.5 text-to-video: 720p landscape 5/8/10s or portrait 5/10s.
runway-gen-4.5/text-to-video runway-gen-4.5/image-to-video
OnlineRunway Gen-4.5 image-to-video: first-frame driven, 720p, multiple aspect ratios, 5/8/10s.
runway-gen-4.5/image-to-video minimax-h3-max/text-to-video
OnlineText-to-video in six aspect ratios, with 480P–1080P and fractional target durations.
minimax-h3-max/text-to-video minimax-h3-max/image-to-video
OnlineVideo from a first frame, a last frame or both, with image-based framing and soundtrack replacement.
minimax-h3-max/image-to-video wan3.0-video
OnlineWan 3.0 all-purpose video with text, first/last frames, reference media, and synchronized audio.
wan3.0-video wan3.0-video-prime
OnlineWan 3.0 Prime fast route with text, first/last frames, image/audio references, and synchronized audio.
wan3.0-video-prime veo-3.1/text-to-video
OnlineGoogle Veo 3.1 text-to-video with a 4K tier.
veo-3.1/text-to-video veo-3.1/image-to-video
OnlineVeo 3.1 image-to-video driven by a first frame.
veo-3.1/image-to-video veo-3.1-fast/text-to-video
OnlineVeo 3.1 Fast text-to-video: quicker and cheaper.
veo-3.1-fast/text-to-video veo-3.1-fast/image-to-video
OnlineVeo 3.1 Fast image-to-video.
veo-3.1-fast/image-to-video seedance-2.0
OnlineStandard and ext routes on one page, with reference media, synced audio, and multiple resolution tiers.
seedance-2.0 seedance-2.0-mini
OnlineSeedance mini tier: budget 480p / 720p clips.
seedance-2.0-mini seedance-2.0-fast
OnlineSeedance fast tier: speed-first generation.
seedance-2.0-fast seedance-2.5/text-to-video
OnlineSeedance 2.5 text-to-video with up to 30 seconds and synchronized audio.
seedance-2.5/text-to-video seedance-2.5/image-to-video
OnlineSeedance 2.5 image-to-video with first-frame and first/last-frame control.
seedance-2.5/image-to-video seedance-2.5/reference-to-video
OnlineSeedance 2.5 reference-to-video with image, video, and audio references.
seedance-2.5/reference-to-video flux-3
OnlineBFL native-audio video model with clips up to 20 seconds, keyframe storyboards, and video continuation.
flux-3 grok-imagine/text-to-video
OnlinexAI text-to-video for fast short clips.
grok-imagine/text-to-video grok-imagine/image-to-video
OnlinexAI image-to-video that animates a still.
grok-imagine/image-to-video grok-imagine-1.5/image-to-video
OnlinexAI 1.5-gen image-to-video with stronger motion and consistency.
grok-imagine-1.5/image-to-video happyhorse-1.0
OnlineShort text-to-video, 3-15s, 720p / 1080p, with audio.
happyhorse-1.0 happyhorse-1.1/text-to-video
OnlineHappyHorse 1.1 text-to-video.
happyhorse-1.1/text-to-video happyhorse-1.1/image-to-video
OnlineHappyHorse 1.1 image-to-video.
happyhorse-1.1/image-to-video happyhorse-1.1/reference-to-video
OnlineHappyHorse 1.1 reference-to-video with @-referenced subjects.
happyhorse-1.1/reference-to-video heygen-avatar-iv
OnlineHeyGen photo avatar: one photo plus a script or audio becomes a talking video.
heygen-avatar-iv creatify-boreal
OnlineCreatify Boreal: product, UGC and presenter videos with native speech from a prompt, optional image or audio, 1–20s, up to 2K.
creatify-boreal omnihuman-1.5
OnlineByteDance audio-driven avatar: portrait plus audio becomes a lip-synced talking video with expressions and gestures.
omnihuman-1.5 heygen-avatar-v
OnlineHeyGen avatar video with script or audio driving, plus optional captions and backgrounds.
heygen-avatar-v hailuo-2.3/text-to-video
OnlineMiniMax Hailuo 2.3 text-to-video with strong motion physics.
hailuo-2.3/text-to-video hailuo-2.3/image-to-video
OnlineHailuo 2.3 image-to-video driven by a first frame.
hailuo-2.3/image-to-video hailuo-2.3-fast/image-to-video
OnlineHailuo 2.3 Fast image-to-video: a low unit price for batch animation.
hailuo-2.3-fast/image-to-video kling-3.0-turbo/text-to-video
OnlineKling 3.0 Turbo text-to-video, per-second 720p / 1080p tiers.
kling-3.0-turbo/text-to-video kling-3.0-turbo/image-to-video
OnlineKling 3.0 Turbo image-to-video.
kling-3.0-turbo/image-to-video gemini-omni-1.1-flash
OnlineGemini Omni 1.1 Flash: text, reference-image, first/last-frame and video-to-video under one model ID.
gemini-omni-1.1-flash kling-3.0/motion-control
OnlineKling 3.0 Motion Control: transfer reference-video motion onto a character image.
kling-3.0/motion-control kling-3.0/text-to-video
OnlineKling 3.0 text-to-video, up to 4K with audio.
kling-3.0/text-to-video kling-3.0/image-to-video
OnlineKling 3.0 image-to-video.
kling-3.0/image-to-video kling-3.0-omni/text-to-video
OnlineKling 3.0 Omni text-to-video: 3–15s, 720p to 4k, native audio, smart multi-shot, and @name subjects.
kling-3.0-omni/text-to-video kling-3.0-omni/image-to-video
OnlineKling 3.0 Omni image-to-video: first frame or first/last frames, 3–15s, 720p to 4k, optional native audio.
kling-3.0-omni/image-to-video kling-3.0-omni/reference-to-video
OnlineKling 3.0 Omni reference-to-video: 1–7 reference images plus an optional reference video for subject, style, and motion.
kling-3.0-omni/reference-to-video kling-3.0-omni/transformation
OnlineKling 3.0 Omni transformation: rewrite a source video's style, scene, or subject from a prompt while keeping its camera motion.
kling-3.0-omni/transformation wan2.7-video/text-to-video
OnlineText-to-video with size, duration, prompt expansion, and shot controls.
wan2.7-video/text-to-video pixverse-v6/text-to-video
OnlinePixVerse V6 text-to-video: 1–15s, 8 aspect ratios, optional synchronized audio and style presets.
pixverse-v6/text-to-video kling-4.0/text-to-video
OnlineKling 4.0 text-to-video: 3–30s at 720p/1080p, picture and synchronized audio in one pass, up to 21:9 ultrawide.
kling-4.0/text-to-video kling-4.0/image-to-video
OnlineKling 4.0 image-to-video: animate one first frame into a 3–30s clip, source framing kept by default, with synchronized audio.
kling-4.0/image-to-video pixverse-v6/image-to-video
OnlinePixVerse V6 image-to-video: first-frame driven, 1–15s, optional synchronized audio.
pixverse-v6/image-to-video grok-imagine-1.5-lite/text-to-video
OnlineGrok Imagine 1.5 Lite text-to-video: 1–15s, 480p–1080p, 7 aspect ratios, built-in sound.
grok-imagine-1.5-lite/text-to-video grok-imagine-1.5-lite/image-to-video
OnlineGrok Imagine 1.5 Lite image-to-video: one image in, 1–15s, 480p–1080p, follows the image ratio, built-in sound.
grok-imagine-1.5-lite/image-to-video ray-3.2/text-to-video
OnlineLuma Ray 3.2 text-to-video: 5- or 10-second cinematic clips from a prompt in 6 aspect ratios.
ray-3.2/text-to-video ray-3.2/image-to-video
OnlineLuma Ray 3.2 image-to-video: 5-second cinematic clips from a first frame or first/last frames.
ray-3.2/image-to-video flux-3-max/text-to-video
OnlineFLUX 3 Max text-to-video: 5–20s at 720p/1080p, 7 fixed aspect ratios plus auto, with synchronized audio and two reasoning levels.
flux-3-max/text-to-video flux-3-max/image-to-video
OnlineFLUX 3 Max image-to-video: required first frame with an optional last frame, 5–20s at 720p/1080p in 7 fixed aspect ratios plus auto.
flux-3-max/image-to-video flux-3-max/keyframes-to-video
OnlineFLUX 3 Max keyframes-to-video: 1–10 keyframes placed by frame index on a 24fps timeline, 5–20s at 720p/1080p.
flux-3-max/keyframes-to-video vidu-q4-preview/image-to-video
OnlineVidu Q4 Preview image-to-video: one first frame becomes a 3-16s video with native audio, up to 4K.
vidu-q4-preview/image-to-video vidu-q4-preview/reference-to-video
OnlineVidu Q4 Preview reference-to-video: 15 images + 3 voice references for consistency.
vidu-q4-preview/reference-to-video wan2.6-flash/image-to-video
OnlineWan 2.6 Flash image-to-video: one image becomes a 5/10/15s 720p/1080p video with optional synchronized audio.
wan2.6-flash/image-to-video ltx-2.5-fast/text-to-video
OnlineLTX 2.5 Fast text-to-video: a prompt becomes a 2-20s 720p/1080p video, landscape or vertical, with native audio.
ltx-2.5-fast/text-to-video kandinsky-6.0-pro/text-to-video
OnlineKandinsky 6.0 Pro text-to-video: a prompt becomes a 5s 480p clip with synchronized audio in five aspect ratios.
kandinsky-6.0-pro/text-to-video kandinsky-6.0-pro/image-to-video
OnlineKandinsky 6.0 Pro image-to-video: one first frame becomes a 5s 480p clip with synchronized audio and automatic aspect matching.
kandinsky-6.0-pro/image-to-video ltx-2.5-fast/image-to-video
OnlineLTX 2.5 Fast image-to-video: first frame (optional last frame) becomes a 2-20s 720p/1080p video with native audio.
ltx-2.5-fast/image-to-video vidu-q3-mix/reference-to-video
OnlineVidu Q3 Mix reference-to-video: 1-7 reference images, 1-16s across 10 frame sizes.
vidu-q3-mix/reference-to-video vidu-q3-ad/reference-to-video
OnlineVidu Q3 Ad reference-to-video: a product shot becomes a 3-15s ad clip.
vidu-q3-ad/reference-to-video wan2.7-video/image-to-video
OnlineFirst-frame driven, with optional last frame, audio, or clip inputs.
wan2.7-video/image-to-video Audio Models
Music generation and multi-speaker dialogue synthesis.
elevenlabs/text-to-dialogue
OnlineMulti-speaker dialogue TTS with emotion tags and voice casting.
elevenlabs/text-to-dialogue minimax-music-1.5
OnlineMiniMax music generation from a text brief.
minimax-music-1.5 minimax-music-2.6
OnlineNext-gen music: auto lyrics, custom lyrics, or instrumental.
minimax-music-2.6 minimax-music-3
OnlineMiniMax high-fidelity music: length control, seed reproducibility, lossless WAV.
minimax-music-3 lyria-3-pro
OnlineGoogle Lyria 3 Pro: full songs up to approximately 3 minutes with image-inspired composition.
lyria-3-pro elevenlabs/music-v2.5
OnlineEleven Music v2.5: songs and instrumentals from a description or composition plan, with reference audio.
elevenlabs/music-v2.5 mureka-9.5/lyrics-to-song
OnlineMureka 9.5 lyrics-to-song: complete lyrics become a vocal song, with optional style direction and vocal gender.
mureka-9.5/lyrics-to-song mureka-9.5/instrumental
OnlineMureka 9.5 instrumental: text descriptions become vocal-free instrumental tracks.
mureka-9.5/instrumental elevenlabs/sound-effects-v2
OnlineElevenLabs Sound Effects v2: 0.5–22 second sound effects from a description, with seamless looping.
elevenlabs/sound-effects-v2 lyria-3.5
OnlineLyria 3.5: generate songs from a musical description and optional lyrics.
lyria-3.5 mirelo-sfx-2.0
OnlineMirelo SFX 2.0: 1–30 second WAV sound effects from text, for video foley, games, and short-form sound design.
mirelo-sfx-2.0 Text Models
Chat Completions for generation, reasoning, coding, structured output, and Agent workflows.
claude-opus-5-5
OnlineClaude Opus 5.5 for long-running agentic coding and knowledge work with always-on thinking and five effort levels.
claude-opus-5-5 claude-haiku-5-5
OnlineClaude Haiku 5.5 for fast text and coding workflows with native Chat Completions reasoning_effort.
claude-haiku-5-5 grok-4.6
OnlinexAI Grok 4.6 for Chat Completions, streaming, tools, JSON objects, and four reasoning efforts.
grok-4.6 grok-4.7
OnlinexAI Grok 4.7 through Chat Completions for text, streaming, tools, JSON objects, and four reasoning efforts.
grok-4.7 kimi-k3.1-pro
OnlineKimi K3.1 Pro with a 1M-token context, always-on reasoning, streaming, structured output, and function tools.
kimi-k3.1-pro kimi-k3.1-pro-highspeed
OnlineKimi K3.1 Pro Highspeed, the faster Kimi K3.1 Pro variant with a higher unit price, same 1M-token context, always-on reasoning, and function tools.
kimi-k3.1-pro-highspeed glm-5.3
OnlineZhipu GLM-5.3 through HiAPI’s OpenAI-compatible Chat Completions API.
glm-5.3 claude-sonnet-4-6
OnlineClaude Sonnet 4.6 for text conversations, coding assistance, and tool workflows.
claude-sonnet-4-6 deepseek-v4-flash-vision-exp
OnlineImage understanding, visual questions and multimodal workflows with Responses and Chat Completions.
deepseek-v4-flash-vision-exp deepseek-v4.1-flash
OnlineDeepSeek V4.1 Flash: text and image input, Responses, reasoning, and streaming.
deepseek-v4.1-flash deepseek-v4-pro
OnlineDeepSeek V4 Pro 0813 production release with a 1M-token context, native Responses, thinking, and Agent workflows.
deepseek-v4-pro deepseek-v4-flash
OnlineDeepSeek V4 efficiency tier with a 1M-token context window, thinking modes, streaming, JSON mode, and tool calls.
deepseek-v4-flash