IMAGE
Image Generation
Z-Image
Alibaba Z-Image — a lightweight, low-cost text-to-image model with multiple aspect ratios, ideal for posters, e-commerce visuals, and bulk content output
Input
Output
from
≈ $0.004/img
8 credits /img
Showing 49 groups
Alibaba Z-Image — a lightweight, low-cost text-to-image model with multiple aspect ratios, ideal for posters, e-commerce visuals, and bulk content output
Input
Output
from
8 credits /img
OpenAI GPT-Image 2 — text-to-image generation and editing (inpainting, multi-reference blending) up to 4K, billed by token, for refined ad and product design
Input
Output
from
30 credits /img
Google Nano Banana — a fast, reliable multi-channel image model with text/image-to-image generation, up to 5 reference images, for everyday creative work
Input
Output
from
15 credits /img
Google Nano Banana 2 Lite (Gemini 3.1 Flash-Lite Image) — a lightweight DeepMind model for fast 1K generation and low-latency prompt editing
Input
Output
from
45 credits /img
GPT Image 2.5 Flare alias for fast image generation and editing with six quality tiers, 1K–4K output, reference images, masks, and transparent backgrounds.
Input
Output
from
60 credits /img
GPT Image 2.5 Flare API for lower-latency everyday image generation and editing with explicit quality, resolution, reference, and output controls.
Input
Output
from
60 credits /img
GPT Image 2.5 Sunburst API for precise image generation, masked editing, multi-reference workflows, and premium outputs across low-to-max quality and 1K–4K tiers.
Input
Output
from
60 credits /img
Google Nano Banana 2 — a high-quality image model with text/image-to-image generation, up to 4K output and 14 reference images, for e-commerce and design
Input
Output
from
25 credits /img
Google Nano Banana Pro — the flagship Nano Banana tier for professional workflows, delivering higher-fidelity 4K image generation with up to 14 reference images
Input
Output
from
60 credits /img
ByteDance Seedance 5.0, via the official Volcengine Ark channel — text/image-to-image generation up to 3K resolution, for e-commerce and marketing imagery
Input
Output
from
70 credits /img
ByteDance Seedance 2.0 — a cinematic-grade video model with soundtrack audio and reference input, generating 5-15 second clips up to 1080p, for ads and shorts
Input
Output
from
720 credits /video
ByteDance Seedance 1.0 — a lightweight, fast image-to-video model generating 5-10 second clips at low cost, for bulk short-video and marketing assets
Input
Output
from
70 credits /video
ByteDance Seedance 1.5 — improved motion and detail over 1.0, with soundtrack audio and image-to-video clips up to 12 seconds, for higher-polish short videos
Input
Output
from
150 credits /video
Google Veo 3.1 Fast — a fast text/image-to-video model with native synchronized audio in 16:9 or 9:16, ideal for social short-form video prioritizing speed
Input
Output
from
330 credits /video
DeepSeek V4.1 Flash: multimodal reasoning, coding and tool use with a 1M-token context window. Separate from DeepSeek V4 Flash.
Input
Output
Input
≈ $0.375
Output
≈ $1.5
Cache
≈ $0.0075
DeepSeek V4 Flash: a distinct text-only V4 model for reasoning, coding and tool use. This model ID does not select V4.1.
Input
Output
Input
≈ $0.525
Output
≈ $1.57
Cache
≈ $0.0175
Image safety detection for NSFW classification.
Input
Output
from
0.5 credits /img
Wan 3.0 Prime text-to-video generation for fast 2-30 second clips at 480p, 720p or 1080p with optional audio.
Input
Output
from
786 credits /video
MiniMax H3 (Hailuo 3) text-to-video with 768p or 2K output and 4-15 second durations.
Input
Output
from
760 credits /video
MiniMax H3 (Hailuo 3) image-to-video with first/last frame control, 768p or 2K output.
Input
Output
from
760 credits /video
MiniMax H3 (Hailuo 3) reference-guided video with up to 9 images, 3 videos and 3 audio references.
Input
Output
from
1,520 credits /video
Seedance 2.5 text-to-video with 4-30 second output, 480p/720p/1080p and synchronized audio.
Input
Output
from
1,380 credits /video
Seedance 2.5 image-to-video with first/last frame control, 4-30 second output and audio.
Input
Output
from
1,380 credits /video
Seedance 2.5 reference-guided video with up to 30 images, 10 videos and 10 audio references.
Input
Output
from
1,680 credits /video
Seedance 2.5 video editing guided by a source clip and text instructions.
Input
Output
from
1,680 credits /video
Seedance 2.5 video extension that continues an existing clip with prompt guidance.
Input
Output
from
1,680 credits /video
Lightweight Seedance 2.0 Mini text-to-video for low-cost drafts, 4-15 seconds at 480p/720p.
Input
Output
from
192 credits /video
Seedance 2.0 Mini image-to-video with first/last frame control at 480p/720p.
Input
Output
from
192 credits /video
Seedance 2.0 Mini reference-guided video with image, video or audio references at 480p/720p.
Input
Output
from
240 credits /video
Google Gemini Omni text-to-video, via the APIPod channel — generates 6, 8, or 10 second clips at 720p or 1080p straight from text, no reference image needed
Input
Output
from
500 credits /video
GLM 5.3 Flash: multimodal reasoning, coding and tool use with a 1M-token context window. Thinking is always enabled with low, high or max effort.
Input
Output
Input
≈ $0.14
Output
≈ $0.49
Cache
≈ $0.0405
Google Gemini 3.5 Flash — a fast, cost-efficient multimodal chat model with image+text input and a million-token context window, for high-concurrency workloads
Input
Output
Input
≈ $0.938
Output
≈ $6.25
Cache
≈ $0.0938
MiniMax M3 — a large language model with a million-token context window, excelling at long-document understanding, complex reasoning, and tool use
Input
Output
Input
≈ $1.2
Output
≈ $5
Cache
≈ $1.5
DeepSeek V4 — a reasoning-focused LLM with a 128K-token context window, excelling at code generation and complex logic at a highly competitive price
Input
Output
Input
≈ $0.212
Output
≈ $0.475
Cache
≈ $0.025
OpenAI GPT-5.5 — a flagship model for complex reasoning, code generation, and multi-step instructions, with a 400K-token context window for demanding apps
Input
Output
Input
≈ $4.25
Output
≈ $25
Cache
≈ $0.425
OpenAI GPT-5.6 — a flagship model for complex reasoning, code generation, and multi-step instructions, with a 400K-token context window for demanding apps
Input
Output
Input
≈ $6
Output
≈ $40
Cache
≈ $0.85
OpenAI GPT-6 — a flagship model for complex reasoning, code generation, and multi-step instructions, with a 400K-token context window for demanding apps
Input
Output
Input
≈ $3.5
Output
≈ $30
Cache
≈ $0.531
Grok 4.5 is an advanced AI model designed to deliver fast, writing, coding, research, data analysis, and creative problem-solving through natural conversation
Input
Output
Input
≈ $0.6
Output
≈ $1.2
Cache
≈ $0.6
Grok 4.6 is an advanced AI model designed to deliver fast, writing, coding, research, data analysis, and creative problem-solving through natural conversation
Input
Output
Input
≈ $0.6
Output
≈ $1.2
Cache
≈ $0.6
A premium reasoning route for visual front-end prototyping, repository-scale coding, large evidence sets, long-running agents, and complex knowledge work that benefits from a 1.05M-token working context.
Input
Output
Input
≈ $2
Output
≈ $10
Cache
≈ $0.2
Grok 4.7 for text conversations and coding through an OpenAI-compatible API. Priced at the same credit rates as Grok 4.6.
Input
Output
Input
≈ $0.6
Output
≈ $1.2
Cache
≈ $0.6
Google Gemini 2.5 Flash Lite — an ultra-low-cost, low-latency chat model with a million-token context window, ideal for high-frequency everyday tasks
Input
Output
Input
≈ $0.1
Output
≈ $0.15
Cache
≈ $0.01
Google Gemini 3.1 Flash Lite — improved reasoning over the 2.5 generation while staying economical, balancing speed and quality for lightweight tasks
Input
Output
Input
≈ $0.15
Output
≈ $1
Cache
≈ $0.0125
Google Gemini 3.1 Pro — the flagship multimodal Gemini model, offering strong complex reasoning and long-context capability for demanding production apps
Input
Output
Input
≈ $1.25
Output
≈ $7.5
Cache
≈ $0.625
OpenAI GPT-4o mini — a fast, affordable multimodal chat model with quick responses and low cost, ideal for everyday Q&A and lightweight coding help
Input
Output
Input
≈ $0.275
Output
≈ $0.412
Cache
≈ $0.0138
OpenAI GPT-5.4 — a high-capability model for advanced reasoning, code generation, and agentic workflows, with a 400K-token context window for production use
Input
Output
Input
≈ $2.5
Output
≈ $15
Cache
≈ $0.25
Anthropic Claude Opus 4.8 — the flagship Claude model for the most demanding reasoning, coding, and long-form writing tasks, with excellent long context
Input
Output
Input
≈ $2.5
Output
≈ $12
Cache
≈ $0.25
Anthropic Claude Opus 5 from APIAny — Anthropic’s newest Opus-tier flagship for the hardest coding, long-running agents, and judgment-heavy review.
Input
Output
Input
≈ $3.75
Output
≈ $18.75
Cache
≈ $0.375
Anthropic Claude Sonnet 4.6 — a balanced flagship model delivering strong reasoning at production speed and cost, for large-scale, stable deployment
Input
Output
Input
≈ $1.5
Output
≈ $7.5
Cache
≈ $1
APIAny is a live catalog of public chat, image, video, audio, and safety models you can call with one OpenAI-compatible API key.
By APIAny Editorial · Updated
Filter by type or provider, compare credit prices, then open a model page for playground tests and request examples.
Sources
The quotations below are from official API documentation that APIAny implements against.
The Chat Completions API endpoint will generate a model response from a list of messages comprising a conversation.
The Gemini API provides access to Google's most capable generative AI models.
The Images API provides several endpoints that let you generate images from text prompts or create edits of existing images.
The APIAny models catalog is the live list of public chat, image, video, audio, and safety models you can call with one API key.
