Model catalog — text, image, video, and audio models — AgentSky
Every model, one key.
78 models from 16 makers, covering text, image, video, and audio. Compare capabilities and current prices in one place.
Model type
All types 78
- Text 47
- Image 8
- Video 9
- Audio 14
Maker
All makers
- Anthropic 7
- Bytedance 3
- DeepSeek 2
- Elevenlabs 1
- Fish Audio 4
- Google 6
- Happyhorse 2
- Meta 3
- MiniMax 8
- Moonshot AI 4
- OpenAI 11
- Qwen 11
- TypeSafe AI 1
- Wan 5
- xAI 1
- Z.ai 9
Sorted by name
Claude Fable 5
Anthropic · Text
A Mythos-class model for demanding reasoning and long-running autonomous work, with always-on adaptive thinking.
Input / output per 1M tokens
Price: $10.00/Price: $50.00Claude Fable 5.1
Anthropic · Text
The latest Mythos-class model for demanding reasoning and long-horizon agentic work, with always-on adaptive thinking and cache reads at a quarter of Fable 5's price.
Input / output per 1M tokens
Price: $10.00/Price: $50.00Claude Haiku 4.5
Anthropic · Text
The fastest and cheapest model in the family, for high-volume work where latency matters more than depth.
Input / output per 1M tokens
Price: $1.00/Price: $5.00Claude Opus 4.8
Anthropic · Text
The previous Opus generation for complex reasoning and agentic work, superseded by Opus 5.
Input / output per 1M tokens
Price: $5.00/Price: $25.00Claude Opus 5
Anthropic · Text
Anthropic's flagship model for complex agentic coding and long-horizon professional work, with adaptive reasoning across a million-token window.
Input / output per 1M tokens
Price: $5.00/Price: $25.00Claude Sonnet 4.6
Anthropic · Text
The previous Sonnet generation for general coding and assistant workloads, superseded by Sonnet 5.
Input / output per 1M tokens
Price: $3.00/Price: $15.00Claude Sonnet 5
Anthropic · Text
A mid-tier model balancing latency against reasoning quality for everyday application and assistant work.
Input / output per 1M tokens
Price: $2.00/Price: $10.00DeepSeek V4 Pro
DeepSeek · Text
The higher-capability V4 text model, with thinking mode on by default and a million-token window.
Input / output per 1M tokens
Price: $1.32/Price: $3.96DeepSeek V4.1 Flash
DeepSeek · Text
DeepSeek V4.1 Flash, available through the canonical deepseek-flash model id.
Input / output per 1M tokens
Price: $0.3/Price: $1.20Fish Audio S1
Fish Audio · Audio
Turn text into spoken audio, in a saved or cloned voice.
Billed per byte
Price: $0.000015Fish Audio S2 Pro
Fish Audio · Audio
Turn text into spoken audio, in a saved or cloned voice.
Billed per byte
Price: $0.000015Fish Audio S2.1 Pro Free
Fish Audio · Audio
Turn text into spoken audio, in a saved or cloned voice.
Billed per byte
Price: $0Gemini 3 Flash Preview
Google · Text
The preview-channel Flash model, with the same multimodal input envelope as 3.5 Flash.
Input / output per 1M tokens
Price: $0.5/Price: $3.00Gemini 3.5 Flash
Google · Text
A multimodal Flash model for agentic and coding work, taking text, images, audio, video, and documents.
Input / output per 1M tokens
Price: $1.50/Price: $9.00Gemini 3.8 Flash
Google · Text
The most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows, taking text, images, audio, video, and documents.
Input / output per 1M tokens
Price: $0.75/Price: $3.75gemini-2.5-flash-image
Google · Image
Generate an image from a written description.
Token prices
Text input / 1M tokens Price: $0.3 Text output / 1M tokens Price: $2.50 Image output / 1M tokens Price: $30.00gemini-3-pro-image
Google · Image
Generate an image from a written description.
Token prices
Text input / 1M tokens Price: $2.00 Text output / 1M tokens Price: $12.00 Image output / 1M tokens Price: $120.00gemini-3.1-flash-image
Google · Image
Generate an image from a written description.
Token prices
Text input / 1M tokens Price: $0.5 Text output / 1M tokens Price: $3.00 Image output / 1M tokens Price: $60.00Generate a sound effect
Elevenlabs · Audio
Generate a sound effect from a written description.
Billed per call
Price: $0.0192GLM-4.5 Air
Z.ai · Text
The lightweight, lower-priced member of the GLM-4.5 family.
Input / output per 1M tokens
Price: $0.2/Price: $1.10GLM-4.5V
Z.ai · Text
A vision-language model taking images, video, and documents alongside text.
Input / output per 1M tokens
Price: $0.6/Price: $1.80GLM-4.7
Z.ai · Text
A prior-generation text model for code generation and long-context understanding.
Input / output per 1M tokens
Price: $0.6/Price: $2.20GLM-5
Z.ai · Text
The first GLM-5 generation for agentic engineering, with thinking mode.
Input / output per 1M tokens
Price: $1.00/Price: $3.20GLM-5.1
Z.ai · Text
A text model for autonomous multi-step execution, with planning and iterative refinement.
Input / output per 1M tokens
Price: $1.40/Price: $4.40GLM-5.2
Z.ai · Text
A long-context text model aimed at long-horizon coding and engineering tasks.
Input / output per 1M tokens
Price: $1.40/Price: $4.40GLM-5.3
Z.ai · Text
The current GLM flagship for software engineering and agent workloads, with configurable reasoning effort.
Input / output per 1M tokens
Price: $1.40/Price: $4.40GLM-5.3-Flash
Z.ai · Text
A natively multimodal Flash model for efficient coding and long-horizon agent tasks, taking text, images, and video.
Input / output per 1M tokens
Price: $0.15/Price: $0.5GPT Image 2.5 Flare
OpenAI · Image
Generate or edit images with text and optional reference images.
Token prices
Text input / 1M tokens Price: $5.00 Cached text input / 1M tokens Price: $1.25 Image input / 1M tokens Price: $8.00 Cached image input / 1M tokens Price: $2.00 Text output / 1M tokens Price: $0 Image output / 1M tokens Price: $30.00GPT Image 2.5 Sunburst
OpenAI · Image
Generate or edit images with text and optional reference images.
Token prices
Text input / 1M tokens Price: $5.00 Cached text input / 1M tokens Price: $1.25 Image input / 1M tokens Price: $8.00 Cached image input / 1M tokens Price: $2.00 Text output / 1M tokens Price: $0 Image output / 1M tokens Price: $30.00GPT-5.5
OpenAI · Text
A prior flagship reasoning model for coding and professional work.
Input / output per 1M tokens
Price: $5.00/Price: $30.00GPT-5.6 Luna
OpenAI · Text
The cost-optimised GPT-5.6 tier, built for high-volume workloads.
Input / output per 1M tokens
Price: $0.2/Price: $1.20GPT-5.6 Sol
OpenAI · Text
The flagship GPT-5.6 tier for complex professional work, with reasoning effort configurable from none to maximum.
Input / output per 1M tokens
Price: $4.00/Price: $20.00GPT-5.6 Terra
OpenAI · Text
The middle GPT-5.6 tier, trading some capability for a lower price.
Input / output per 1M tokens
Price: $2.00/Price: $12.00GPT-6 Astra
OpenAI · Text
OpenAI's flagship for the hardest end-to-end work across complex reasoning, coding, computer use, research, and document creation.
Input / output per 1M tokens
Price: $10.00/Price: $50.00GPT-6 Luna
OpenAI · Text
OpenAI's most efficient GPT-6 tier for focused, high-volume workloads.
Input / output per 1M tokens
From Price: $0.1/from Price: $0.5 See rates by context and modeGPT-6 Sol
OpenAI · Text
OpenAI's balanced GPT-6 tier for complex coding, reasoning, and agentic workflows.
Input / output per 1M tokens
From Price: $2.00/from Price: $10.00 See rates by context and modegpt-image-2
OpenAI · Image
Generate an image from a written description.
Token prices
Text input / 1M tokens Price: $5.00 Text output / 1M tokens Price: $0 Image output / 1M tokens Price: $30.00Grok 4.6
xAI · Text
xAI's frontier model for coding, agentic tasks, and knowledge work, with four reasoning-effort levels.
Input / output per 1M tokens
Price: $2.00/Price: $6.00happyhorse-1.0-t2v
Happyhorse · Video
Generate video from a text prompt.
Billed per second
720P (default): Price: $0.14 1080P: Price: $0.24happyhorse-1.1-t2v
Happyhorse · Video
Generate a five-second video from text.
Billed per second
480P: Unavailable 720P: Unavailable 1080P (default): UnavailableJev 1.13
TypeSafe AI · Text
A structured decision model: it answers named yes/no, choice, and score questions about supplied state, each with a calibrated probability. It does not generate text and is not a chat model.
Input / output per 1M tokens
Price: $0.042/Price: $0Kimi K2.6
Moonshot AI · Text
A general-purpose multimodal model offering both thinking and non-thinking modes.
Input / output per 1M tokens
Price: $0.95/Price: $4.00Kimi K2.7 Code
Moonshot AI · Text
A coding-oriented multimodal model supporting extended reasoning.
Input / output per 1M tokens
Price: $0.95/Price: $4.00Kimi K2.7 Code Highspeed
Moonshot AI · Text
The higher-throughput serving variant of K2.7 Code, at twice the price.
Input / output per 1M tokens
Price: $1.90/Price: $8.00Kimi K3
Moonshot AI · Text
Moonshot's flagship multimodal model, with always-on reasoning and a selectable effort level.
Input / output per 1M tokens
Price: $3.00/Price: $15.00MiniMax M3
MiniMax · Text
A reasoning model with image and video understanding and tool calling.
Input / output per 1M tokens
From Price: $0.3/from Price: $1.20 See rates by context and modeMiniMax-H3
MiniMax · Video
Generate video from a text prompt or reference images.
Billed per second
768p (default) Reference $0.08 Plan $0.08Muse Spark 1.1
Meta · Text
Standard-tier multimodal reasoning model with function tool calling.
Input / output per 1M tokens
Price: $1.25/Price: $4.25Muse Spark 1.2
Meta · Text
Standard-tier multimodal reasoning model with function tool calling.
Input / output per 1M tokens
Price: $1.25/Price: $4.25Muse Voice Transcribe 1.0
Meta · Audio
Transcribe a WAV recording.
Billed per second
Price: $0.00005Qwen Flash
Qwen · Text
A speed- and cost-oriented model with switchable thinking mode.
Input / output per 1M tokens
From Price: $0.05/from Price: $0.4 See rates by context and modeQwen Max
Qwen · Text
An earlier-generation flagship text model with a short window.
Input / output per 1M tokens
From Price: $3.17/from Price: $15.80 See rates by context and modeQwen Plus
Qwen · Text
The balanced tier, supporting function calling, structured output, and batch inference.
Input / output per 1M tokens
From Price: $0.4/from Price: $1.20 See rates by context and modeQwen VL Max
Qwen · Text
The higher-capability vision-language tier, taking text, images, and video.
Input / output per 1M tokens
From Price: $0.8/from Price: $3.20 See rates by context and modeQwen VL Plus
Qwen · Text
The balanced vision-language tier, taking text, images, and video.
Input / output per 1M tokens
From Price: $0.21/from Price: $0.63 See rates by context and modeQwen3 Coder Flash
Qwen · Text
The smaller Coder tier, with the same window and multi-turn tool use.
Input / output per 1M tokens
From Price: $0.3/from Price: $1.50 See rates by context and modeQwen3 Coder Plus
Qwen · Text
A code model with agentic tool calling and repository-level understanding.
Input / output per 1M tokens
From Price: $1.00/from Price: $5.00 See rates by context and modeQwen3.5 Flash
Qwen · Text
A lower-cost Qwen 3.5 tier taking text, images, and video.
Input / output per 1M tokens
From Price: $0.1/from Price: $0.4 See rates by context and modeQwen3.6 Flash
Qwen · Text
A fast multimodal Qwen model.
Input / output per 1M tokens
From Price: $0.25/from Price: $1.50 See rates by context and modeQwen3.7 Max
Qwen · Text
The Qwen flagship, with hybrid thinking and non-thinking modes.
Input / output per 1M tokens
From Price: $2.50/from Price: $7.50 See rates by context and modeQwen3.8 Max
Qwen · Text
A Qwen flagship with thinking and non-thinking modes.
Input / output per 1M tokens
From Price: $2.00/from Price: $6.00 See rates by context and modeSeedance 2.0
Bytedance · Video
Generate a video from a text prompt.
Billed per token
480p: Price: $0.0000077 720p (default): Price: $0.0000071 1080p: Price: $0.0000077Seedance 2.0 Fast
Bytedance · Video
Generate a video from a text prompt.
Billed per token
480p: Unavailable 720p (default): UnavailableSeedance 2.5
Bytedance · Video
Generate a video from text and reference media.
Billed per token
without_video (default): Price: $0.0000107 with_video: Price: $0.0000064Speech 02 HD
MiniMax · Audio
Turn text into spoken audio in a chosen voice.
Billed per character
Price: $0.0001Speech 02 Turbo
MiniMax · Audio
Turn text into spoken audio in a chosen voice.
Billed per character
Price: $0.00006Speech 2.6 HD
MiniMax · Audio
Turn text into spoken audio in a chosen voice.
Billed per character
Price: $0.0001Speech 2.6 Turbo
MiniMax · Audio
Turn text into spoken audio in a chosen voice.
Billed per character
Price: $0.00006Speech 2.8 HD
MiniMax · Audio
Turn text into spoken audio in a chosen voice.
Billed per character
Price: $0.0001Speech 2.8 Turbo
MiniMax · Audio
Turn text into spoken audio in a chosen voice.
Billed per character
Price: $0.00006Transcribe audio
Z.ai · Audio
Turn a short recording into text.
Billed per second
Price: $0.00004Transcribe with timestamps
Fish Audio · Audio
Turn a recording into text with per-segment timings.
Billed per second
Price: $0.0001Transcribe with word timestamps
OpenAI · Audio
Turn a recording into text with the start and end of every word.
Billed per second
Price: $0.0001wan2.6-i2v-flash
Wan · Video
Animate a first-frame image with optional generated audio.
Billed per second
720P, audio: false: Unavailable 720P, audio: true: Unavailable 1080P, audio: false: Unavailable 1080P, audio: true (default): Unavailablewan2.7-i2v
Wan · Video
Animate a first-frame image.
Billed per second
720P (default): Price: $0.11 1080P: Price: $0.15wan2.7-image
Wan · Image
Generate PNG images from a text description.
Billed per image
Price: $0.03wan2.7-image-pro
Wan · Image
Generate PNG images from a text description.
Billed per image
Price: $0.075wan2.7-t2v
Wan · Video
Generate video from a text prompt.
Billed per second
720P (default): Price: $0.11 1080P: Price: $0.15