MCP / Models
AI models MCP: image, video and LLMs with no API key
105 models that run today, each with its live inputs, its price from billing and requests to paste. One MCP reaches all of them, and every model is also an API.
$ YOUR NEXT RUN
Any agentUse AI models in your assistant
Paste this prompt into Claude Code, Codex, Cursor or any agent. It reads the guide and helps you connect.
Read https://flymy.ai/skill.md and https://flymy.ai/mcp/models.md. Help me connect the FlyMy.AI MCP to this assistant, then pick the best model on this page for my task and run it.
Image generation 27
Text to image: product shots, ads, posters and illustrations from a prompt, many with reference images.
GPT Image 2.6
OpenAI's current default image model: faster than 2.5, with text that stays readable.
Text to image / from $0.009 / run
GPT Image 2.6 Sunburst
The precision tier of 2.6 for packaging, campaigns and detailed illustration.
Text to image / from $0.009 / run
Nano Banana 2.1
Gemini's newest image model: 14 references, up to 4K, with adjustable thinking.
Text and image to image / from $0.0336 / image
Seedream 5.0 Pro
ByteDance's precise 5.0 tier for product shots and layouts, blending up to 10 reference images.
Text and image to image / from $0.045 / run
GPT Image 2.5
The 2.5 Flare tier: natural light and sharper detail than 2.0 at a short generation time.
Text to image / from $0.009 / run
GPT Image 2.5 Sunburst
The slower, more exact 2.5 tier for campaign and product imagery where detail matters.
Text to image / from $0.009 / run
Wan 2.7 Image Pro
Alibaba's pro image model: up to 4K, nine references, layout boxes and color palettes.
Text and image to image / $0.075 / image
Nano Banana 2 Lite
The cheapest Nano Banana 2 tier: 1K images in volume with the same prompt understanding.
Text and image to image / from $0.0376 / run
Seedream 5.0 Lite
The quick tier of Seedream 5.0, with better prompt following and in-image text than 4.5.
Text and image to image / $0.035 / run
GPT Image 2.0
OpenAI's 2.0 generator for pipelines tuned to it, with three sizes and transparent output.
Text to image / from $0.009 / run
Nano Banana 2
Gemini 3.1 Image: up to 10 images per run at up to 4K, with optional web search.
Text and image to image / from $0.071 / run
Nano Banana Pro
Gemini 3 Pro Image for posters, packaging and logos where the words must be right.
Text and image to image / from $0.15 / run
Nano Banana
The original Gemini 2.5 image model: quick drafts and conversational edits.
Text and image to image / $0.039 / run
Seedream 4.5
ByteDance's 4.5 release: keeps a product or face steady through edits, with up to 14 references.
Text and image to image / $0.04 / run
GPT Image 1.5
An earlier OpenAI image model, kept for pipelines built on it; transparent backgrounds supported.
Text to image / from $0.009 / run
Nano Banana 2 Flex
Nano Banana 2 on Google's lower-priced flex tier, for batches where cost matters most.
Text and image to image / from $0.0355 / run
Imagen 4
Google's standard Imagen 4: realistic images, up to four per run, with SynthID marking.
Text to image / $0.04 / run
Imagen 4 Fast
The low-cost Imagen 4 tier for drafts, thumbnails and big batches of images.
Text to image / $0.02 / run
Imagen 4 Ultra
Google's top Imagen 4 tier for hero images that must match a long prompt closely.
Text to image / $0.06 / run
Qwen-Image Fast
Alibaba's open Qwen-Image on our GPUs: posters and signs with English or Chinese text.
Text to image / $3.00 / hr
Z-Image Turbo LoRA
Z-Image Turbo with two LoRA slots: a trained style or character at turbo speed.
Text to image / $0.005 / run
Z-Image Turbo
Six billion parameters, eight steps: photoreal images fast and at a very low price.
Text to image / $0.005 / run
Seedream 4.0
The earlier Seedream: prompt-only images or edits of up to two pictures, at 2K sizes.
Text and image to image / $0.03 / run
Qwen-Image LoRA
Qwen-Image with up to two LoRA adapters: your trained style or character in every image.
Text to image / $0.018 / run
HiDream I1 Dev
Distilled 17B open model: fast text-to-image with fine detail, size and seed under your control.
Text to image / $0.10 / run
MiniMax Image-01
MiniMax's image model that keeps a character consistent from one reference photo.
Text and image to image / $0.04 / run
SDXL LoRA
Stable Diffusion XL with LoRAs from a link: niche styles and characters on our GPUs.
Text to image / $3.00 / hrImage editing 10
Change a picture you already have: background, objects, style, text in the frame, or its resolution.
GPT Image 2.6 Edit
OpenAI's current editor: fix packaging text or swap a product while the rest stays put.
Image editing / from $0.009 / run
GPT Image 2.6 Sunburst Edit
The 2.6 precision editor for brand assets and retouching that must not drift.
Image editing / from $0.009 / run
GPT Image 2.5 Edit
The 2.5 Flare editor: swap a product, background or headline and leave the rest alone.
Image editing / from $0.009 / run
GPT Image 2.5 Sunburst Edit
The 2.5 precision editor that holds composition steady across many rounds of changes.
Image editing / from $0.009 / run
Wan 2.7 Image Edit
Alibaba's editor for local and style changes, with layout boxes and color palettes.
Image editing / $0.03 / image
GPT Image 2.0 Edit
OpenAI's 2.0 editor, kept for pipelines that already depend on its output.
Image editing / from $0.009 / run
FLUX.1 Kontext Max
The top Kontext tier for demanding instruction edits and typography changes.
Image editing / $0.08 / run
FLUX.1 Kontext Pro
Black Forest Labs' everyday Kontext editor: swap backgrounds, outfits and objects.
Image editing / $0.04 / run
FLUX.1 Canny Pro
Black Forest Labs' edge-guided FLUX: keep a sketch's layout, restyle everything else.
Edge-guided image / $0.05 / run
Real-ESRGAN
The open upscaler: enlarge a photo up to 8x and clean up compression artifacts.
Upscaling / $5.00 / hrText to video 23
A written scene becomes a clip, many with sound generated in the same pass.
Gemini Omni 1.2 Flash Text to Video
Google's video model with native dialogue and timed directions, from 360p to 4K.
Text to video / from $0.024 / s
Wan 3.0 Text to Video
Alibaba's Wan 3.0: text to video up to 30 seconds, with its own soundtrack.
Text to video / from $0.05 / s
Seedance 2.5 Text to Video
ByteDance's newest text-to-video: multi-beat scenes up to 30 seconds with sound.
Text to video / from $0.10794 / s
Wan 2.7 Text to Video
Wan 2.7 from text: coherent scenes and natural motion in up to 10 seconds.
Text to video / from $0.10 / s
Wan 2.6 Text to Video
The previous Wan generation: 2 to 10 second clips with single or multi-shot cuts.
Text to video / from $0.10 / s
Seedance 2.0 Fast Text to Video
The quick Seedance 2.0 for drafts: prompt-only clips at 480p or 720p with sound.
Text to video / from $0.0538 / s
Seedance 2.0 Text to Video
Seedance 2.0 from text alone: cinematic motion and sound at up to 1080p.
Text to video / from $0.0673 / s
Veo 3.1 Fast
Veo 3.1 at draft speed: first and last frames, references and audio for less.
Text and image to video / from $0.40 / run
Veo 3.1
Google's flagship Veo 3.1 for motion-critical shots, with references and audio.
Text and image to video / from $0.80 / run
Wan 2.2 Fast Text to Video
Wan 2.2 A14B with LoRA slots: your trained style in text-to-video clips.
Text to video / from $0.135 / run
MiniMax Hailuo 02
MiniMax's Hailuo 02: physics-heavy motion like dance and sport, up to native 1080P.
Text and image to video / from $0.10 / run
Kling 3.0 Text to Video
Kuaishou's Kling 3.0 from text: directed shots, camera moves and native audio.
Text to video / $0.35 / run
MiniMax H3 Text to Video
MiniMax H3 from a prompt: native 2K video with audio, billed per second.
Text to video / from $0.08 / s
Seedance 2.0 4K Text to Video
Seedance 2.0 motion at 4K: written scenes rendered sharp enough for big screens.
Text to video / from $0.0673 / s
Seedance 2.0 Fast
The fast Seedance 2.0 on one endpoint: any input, a fixed price, quicker results.
Text and image to video / $0.85 / run
Seedance 2.0
Seedance 2.0 with every input on one endpoint and one fixed price per run.
Text and image to video / $1.10 / run
PixVerse Text to Video
PixVerse v3.5 to v5 from text, with ready styles from anime to cyberpunk.
Text to video / from $0.227273 / run
Kandinsky Video
Sber AI's Kandinsky video model: short text-to-video clips with frame and size control.
Text to video / $0.39 / run
Seedance 1.0 Lite Text to Video
First-generation Seedance at a low price: quick 5 to 12 second clips from a prompt.
Text to video / from $0.17 / run
Seedance 1.0 Pro
First-generation Seedance Pro: smooth multi-shot clips with first and last frames.
Text and image to video / from $0.24 / run
Sora 2
OpenAI's Sora 2: consistent, realistic shots with matching sound from text or a photo.
Text and image to video / $0.10 / run
Wan 2.2 Text to Video
Alibaba's open Wan 2.2 on our GPUs, with full control over frames and guidance.
Text to video / $5.97 / hr
MiniMax Text to Video
MiniMax's 720p text-to-video with shot control written straight into the prompt.
Text to video / $0.49 / runImage to video 19
Animate a photo, or move from a first frame to a last one.
Gemini Omni 1.2 Flash Image to Video
Gemini Omni from a photo: native sound, first-to-last-frame moves, up to 4K.
Image to video / from $0.024 / s
Wan 3.0 Image to Video
Wan 3.0 from your image: up to 30 seconds, adaptive framing and a soundtrack.
Image to video / from $0.05 / s
Seedance 2.5 Image to Video
Seedance 2.5 from a photo: up to 30 seconds, first-to-last-frame moves, real people allowed.
Image to video / from $0.10794 / s
Wan 2.7 Image to Video
Wan 2.7 from a still: first-to-last-frame moves with natural motion.
Image to video / from $0.10 / s
Wan 2.6 Image to Video
The previous Wan generation for animating a still at 720P or 1080P.
Image to video / from $0.10 / s
Seedance 2.0 Fast Image to Video
Quick Seedance 2.0 animation of one photo, for drafts at 480p or 720p.
Image to video / from $0.0538 / s
Seedance 2.0 Image to Video
Seedance 2.0 from one keyframe: a still becomes a clip with motion and sound.
Image to video / from $0.0673 / s
Wan 2.2 Fast Image to Video
Wan 2.2 A14B animating your image with LoRA effects such as an orbit shot.
Image to video / from $0.135 / run
MiniMax Image to Video
MiniMax's image-to-video for natural movement from one still picture.
Image to video / $3.00 / hr
Kling 3.0 Image to Video
Kuaishou's Kling 3.0 from a frame: identity kept, masks for motion, native audio.
Image to video / $0.70 / run
MiniMax H3 Image to Video
MiniMax H3 from a frame: native 2K animation with audio, priced per second.
Image to video / from $0.08 / s
PixVerse 5.5 Image to Video
PixVerse 5.5: photo animation with optional sound and multi-clip cuts.
Image to video / $1.50 / run
PixVerse Image to Video
PixVerse v3.5 to v5 animating your image, from quick 360p to 1080p.
Image to video / $1.00 / run
MiniMax Hailuo 2.3
MiniMax Hailuo 2.3: dance, flips and micro-expressions from a single frame.
Image to video / $1.50 / run
MiniMax Hailuo 2.3 Fast
The quick Hailuo 2.3 for batches: smooth 1080P motion from one frame.
Image to video / $1.50 / run
Seedance 1.0 Lite Image to Video
Low-cost first-generation Seedance for animating product and social photos.
Image to video / from $0.17 / run
Wan 2.1 First and Last Frame
Open Wan 2.1 bridging a start and an end image with coherent motion.
First and last frame to video / $3.00 / hr
MiniMax I2V-01 Director
MiniMax's Director model: camera instructions in the prompt, applied to your frame.
Image to video / $3.00 / hr
HunyuanCustom
Tencent's open model for videos where the person or product from a photo stays the same.
Image to video / $5.97 / hrReference video, editing and lip sync 11
Keep characters and products from references, edit or extend a clip, sync lips to a voice.
Gemini Omni 1.2 Flash Reference to Video
Gemini Omni from references: two characters and their products, kept across the clip.
Reference to video / from $0.024 / s
Gemini Omni 1.2 Flash Video Edit
Gemini Omni editing a clip by instruction: swap the product, the sky or the style.
Video editing / from $0.024 / s
Gemini Omni 1.2 Flash Video Extend
Gemini Omni that continues your clip with matching motion, cast and sound.
Video extension / from $0.024 / s
OmniHuman 2.0
One photo plus a voice track: a presenter, singer or character that moves in sync.
Talking video / $0.07 / s
Wan 3.0 Reference to Video
Wan 3.0 from references: the same cast, location and voice across 30 seconds.
Reference to video / from $0.05 / s
Wan 2.7 Video Edit
Wan 2.7 restyling a real clip, with up to four reference images.
Video editing / from $0.20 / s
Seedance 2.5 Reference to Video
Seedance 2.5 from many references: keep a cast consistent, or edit and extend a clip.
Reference to video / from $0.10794 / s
Wan 2.7 Reference to Video
Wan 2.7 for keeping a character or style steady across a short clip.
Reference to video / from $0.10 / s
Seedance 2.0 Fast Reference to Video
Quick Seedance 2.0 drafts that keep a character or style from your references.
Reference to video / from $0.0538 / s
Seedance 2.0 Reference to Video
Seedance 2.0 for brand and character consistency across a whole clip.
Reference to video / from $0.0673 / s
LatentSync
ByteDance's open lip-sync model: match a speaker's mouth to any new voice track.
Lip sync / $0.04 / runVoice and music 2
Clone a voice from a short sample or turn lyrics and a style into a song.
Language models 9
Chat and reasoning models for code, documents and agents, plus typed decisions for routing and triage.
Kimi K3.1 Pro
Moonshot's flagship for agentic coding: tool calls, images and a 1M-token context.
Chat model / $2.00 / $10.00 per 1M tokens
DeepSeek V4.1 Flash
DeepSeek's quick reasoning model with tool calls, images and a priority tier.
Chat model / $0.30 / $1.20 per 1M tokens
Grok 4.7
xAI's reasoning model with a 500K-token window for codebases and long contracts.
Chat model / $2.00 / $6.00 per 1M tokens
TypeSafe Jev 1.13
FlyMy.AI's decision model: route, label and gate with probabilities, not prose.
Typed decisions / $0.042 per 1M tokens
Gemini 3 Flash
The Gemini 3 generation at Flash speed, with thinking you can turn down.
Chat model / $0.50 / $3.00 per 1M tokens
Gemini 3.1 Flash Lite
The cheapest Gemini text model for extraction, labels and short drafts at scale.
Chat model / $0.25 / $1.50 per 1M tokens
Gemini 3.1 Pro
Gemini 3.1 Pro for the hard problems: long documents, code and careful reasoning.
Chat model / $2.00 / $12.00 per 1M tokens
Gemini 2.5 Flash
Google's fast general model: thinking on demand, JSON output, image input.
Chat model / $0.30 / $2.50 per 1M tokens
MiniMax M1
MiniMax's open reasoning model with function tools and long inputs.
Chat model / $3.00 / hrVision and OCR 3
Read images, video and scanned pages: describe them, pull out the text, answer questions about them.
Gemini 3.8 Flash Vision
Gemini vision for photos, video and YouTube: OCR, comparisons and timestamped summaries.
Vision model / $0.75 / $3.75 per 1M tokensDeepSeek-OCR
DeepSeek's OCR model that turns scans and screenshots into text or Markdown.
OCR / $5.00 / hr
Qwen3-VL Instruct
Alibaba's Qwen3-VL for questions about photos, charts and scanned documents.
Vision model / $3.00 / hrLoRA training 1
Train a style or character adapter on your own images and use it with the image models.
For agents and crawlers
From the FlyMy.AI model catalog of 2026-11-09: inputs from the model's live schema, prices from FlyMy.AI billing. Requests are examples to paste, not recorded runs.