API model market
One API for every model you ship
Explore production-ready LLMs and the next wave of image and video routes from one OmniaKey account.
Choose a provider7
Model capabilities
14 results
ByteDance
Seedance 2.0 Fast
dreamina-seedance-2-0-fast-260128
Seedance 2.0 Fast is the speed tier of Seedance 2.0 on OmniaKey, callable as dreamina-seedance-2-0-fast-260128: the same prompt, first-frame, reference and audio behaviour on a cheaper price list capped at 720P.
$0.03–$0.06 per secondSave 50%Text to videoImage to video
ByteDance
Seedance 2.0 Mini
dreamina-seedance-2-0-mini-260615
Seedance 2.0 Mini is the cheapest Seedance route on OmniaKey, id dreamina-seedance-2-0-mini-260615: text to video, first-frame and reference generation at 480P or 720P, for up to 15 seconds per job.
$0.02–$0.04 per secondSave 50%Text to videoImage to video
MiniMax
MiniMax H3
minimax-h3
MiniMax H3 is MiniMax's video route on OmniaKey: one model id covers text to video, a first frame with an optional last frame, and reference-driven shots in 768P or 2K.
$0.0269–$0.0431 per secondSave 82%Text to videoImage to video
Alibaba
HappyHorse 1.1
happyhorse-1.1-t2v +2
HappyHorse 1.1 is Alibaba's newest HappyHorse video family on OmniaKey. One card covers all three ways to use it, and each way has its own model id: happyhorse-1.1-t2v for text to video, happyhorse-1.1-i2v to animate a first frame, and happyhorse-1.1-r2v to drive the shot from up to nine reference images.
$0.042–$0.108 per secondSave 40%Text to videoImage to video
Alibaba
HappyHorse 1.0
happyhorse-1.0-t2v +2
HappyHorse 1.0 is the first-generation HappyHorse video family on OmniaKey, published as one card with a model id per operation: happyhorse-1.0-t2v for text to video, happyhorse-1.0-i2v for a first frame, and happyhorse-1.0-r2v for reference-driven shots.
$0.112–$0.192 per secondSave 20%Text to videoImage to video
Alibaba
Wan 3.0
wan3.0-video
Wan 3.0 is Alibaba's all-in-one video model on OmniaKey: one id covers text to video, a first frame, and reference-driven shots, and every clip comes back with its own soundtrack.
$0.04–$0.16 per secondSave 20%Text to videoImage to video
ByteDance
Seedance 2.5
dreamina-seedance-2-5-260628
Seedance 2.5 is ByteDance's flagship video route on OmniaKey: the provider ID dreamina-seedance-2-5-260628 serves text to video, a first frame and reference images, and every clip comes back with an AI-generated soundtrack.
$0.1133–$0.6259 per secondText to videoImage to video
ByteDance
Seedance 2.0
dreamina-seedance-2-0-260128
Seedance 2.0 is the previous Seedance generation on OmniaKey, published under the provider ID dreamina-seedance-2-0-260128: one id covers text to video, a first frame and reference-driven shots of up to 15 seconds, always with an audio track.
$0.077–$0.407 per secondText to videoImage to video
Alibaba
Wan 3.0 Video Prime
wan3.0-video-prime
Wan 3.0 Video Prime is the high-speed build of the same Wan 3.0 model on OmniaKey: identical operations, references and audio, with a much shorter end-to-end turnaround.
$0.078–$0.38 per secondText to videoImage to video
xAI
Grok Imagine Video 1.5
grok-imagine-video-1.5
Grok Imagine Video 1.5 is xAI's first live video route on OmniaKey: it renders text-to-video and image-to-video clips through the same asynchronous media API, priced per second of output instead of per call.
$0.30 per secondText to videoImage to video
Kling
Kling 3.0
kling-3.0
Kling 3.0 is Kling's video route on OmniaKey: text to video and a first frame with an optional last frame, in a standard and a high-quality tier, at fixed lengths of 5, 10 or 15 seconds.
$0.80–$3.00 per callText to videoImage to video
KlingComing soon
Kling 3.0 Turbo
kling-3-turbo
Asynchronous video generation with status polling and a signed result URL.
Text to videoImage to video
- GPT-6.1 Sol OpenAI: GPT-6.1 Sol is OpenAI's frontier GPT-6.1 reasoning route, with 1M context, image input, and tool use.
- GPT-6 Sol OpenAI: GPT-6 Sol is OpenAI's frontier GPT-6 reasoning route, with 1M context, image input, and tool use.
- GPT-6 Luna OpenAI: GPT-6 Luna is the fast, lower-priced GPT-6 route with 1M context, image input, and tool use.
- Claude Opus 5.5 Anthropic: Claude Opus 5.5 is Anthropic's newest Opus route: the September 2026 rate card drops to $4 / $20 per million tokens while keeping 1M context, vision, tool use, and always-on adaptive thinking.
- Claude Sonnet 5.5 Anthropic: Claude Sonnet 5.5 is Anthropic's newest Sonnet route: it keeps Sonnet 5's $2 / $10 rate card and 1M context, and adds always-on adaptive thinking to the balanced vision-and-tools mix.
- Claude Haiku 5.5 Anthropic: Claude Haiku 5.5 is the fast Claude route with a 1M context window, vision, tools and adaptive thinking, launched at 20% below Anthropic's official token rates.
- Jev 1.14 TypeSafe AI: Jev is TypeSafe AI's typed decision route: one request returns schema-bound choices, scores, and confidence for a state you supply.
- GPT-6 Astra OpenAI: GPT-6 Astra is OpenAI's newest flagship route, with 1M context, image input, and tool use.
- GPT-5.6 Sol OpenAI: GPT-5.6 Sol is the featured top-rate GPT-5.6 coding route, with 1M context, vision, and structured tool use for agent workflows.
- GPT-5.6 Terra OpenAI: GPT-5.6 Terra is the middle-priced 5.6 route, retaining the same listed 1M context, vision, and tool use.
- GPT-5.6 Luna OpenAI: GPT-5.6 Luna is the fast, lowest-priced 5.6 route with 1M context, vision, and tool use.
- GPT-5.5 OpenAI: GPT-5.5 remains available as a 1M-context model with vision and tool use alongside the newer 5.6 family.
- Claude Fable 5 Anthropic: Claude Fable 5 is Anthropic's most capable widely released model for demanding reasoning and long-horizon agents, with 1M context and always-on adaptive thinking.
- Claude Fable 5.1 Anthropic: Claude Fable 5.1 keeps Fable 5's 1M context and adaptive thinking while lowering the listed cache-read rate to $0.25 per million tokens.
- Claude Opus 5 Anthropic: Claude Opus 5 is the featured Opus route for complex coding agents, with 1M context, vision, and structured tool use.
- Claude Opus 4.8 Anthropic: Claude Opus 4.8 remains available with a 1M context window, vision, and structured tool use.
- Claude Opus 4.7 Anthropic: Claude Opus 4.7 keeps the same listed 1M context, vision, tool use, and token price as the adjacent Opus revisions.
- Claude Opus 4.6 Anthropic: Claude Opus 4.6 remains available with a 1M context window, vision, and tool use for version-pinned clients.
- Claude Sonnet 5 Anthropic: Claude Sonnet 5 is the balanced Claude coding route for daily agent work, with 1M context, vision, and structured tool use below the Opus 5 rate.
- Claude Sonnet 4.6 Anthropic: Claude Sonnet 4.6 provides 1M context, vision, and tool use for clients that remain pinned to the 4.6 line.
- Claude Haiku 4.5 Anthropic: Claude Haiku 4.5 is the fast Claude option, with a 200K context window and the lowest listed Claude token price.
- Gemini 3.1 Pro Preview Google: Gemini 3.1 Pro Preview is the featured Gemini preview with 1M context, vision, and tool use.
- Gemini 4 Argon Google: Gemini 4 Argon is Google's newest 1M-context Pro route on OmniaKey, launched at a half-price introductory rate before it reverts to the standard Pro tier.
- Gemini 2.5 Pro Google: Gemini 2.5 Pro is the non-preview Pro option with 1M context, vision, and tool use.
- Gemini 3.8 Flash Google: Gemini 3.8 Flash is the current mainline Gemini Flash route: 1M context, vision, and tool use at the 3.x Flash rate.
- Gemini 3.7 Flash Google: Gemini 3.7 Flash is the previous Flash snapshot, kept at the same 1M context, capabilities, and rate as 3.8 Flash.
- Gemini 3.6 Flash Google: Gemini 3.6 Flash is an earlier Flash snapshot published at the same 1M context, capabilities, and rate as the rest of the 3.x line.
- Gemini 3.5 Flash-Lite Google: Gemini 3.5 Flash-Lite is the newest low-cost Gemini route: 1M context, vision, and tool use at a Lite rate.
- Gemini 2.5 Flash Google: Gemini 2.5 Flash is the 2.5-generation fast route: 1M context, vision, and tool use at a Lite-tier rate.
- Gemini 2.5 Flash-Lite Google: Gemini 2.5 Flash-Lite is the cheapest Gemini route on the gateway, keeping 1M context, vision, and tool use.
- Grok 4.7 xAI: Grok 4.7 is xAI's newest flagship coding model here, with a 500K context window, vision, and structured tool use.
- Grok 4.6 xAI: Grok 4.6 remains available with a 500K context window, vision, and structured tool use.
- Grok 4.5 xAI: Grok 4.5 remains available with a 500K context window, vision, and structured tool use.
- Qwen3.8 Max Alibaba Cloud: Qwen3.8 Max is Alibaba Cloud's featured Qwen route here, with 1M context and structured tool use for coding agents.
- Qwen3.8 Flash Alibaba Cloud: Qwen3.8 Flash is the newest low-cost Qwen route, with 1M context, image and video input, and tool use.
- Qwen3.7 Max Alibaba Cloud: Qwen3.7 Max provides 1M context and tool use at the flagship 3.7 family rate.
- DeepSeek V4.1 Flash DeepSeek: DeepSeek V4.1 Flash is DeepSeek's newest Flash route, and OmniaKey already serves the October 17, 2026 (1017) build: 1M context, native image input, and thinking modes from low to max.
- DeepSeek V4 Flash DeepSeek: DeepSeek V4 Flash is the lower-priced DeepSeek V4 route for fast coding and agent workloads.
- DeepSeek V4 Flash Vision (exp) DeepSeek: DeepSeek V4 Flash Vision is the experimental image-capable build of V4 Flash, at the same token rates as the text route.
- DeepSeek V4 Pro DeepSeek: DeepSeek V4 Pro is DeepSeek's flagship route with 1M context, thinking modes, and structured tool use.
- GLM-5.3 Z.ai: GLM-5.3 is the newest Z.ai coding route in the OmniaKey catalog, with 1M context, tool use, and a flat 20% of Z.ai list rates.
- GLM-5.3-Flash Z.ai: GLM-5.3-Flash is Z.ai's high-throughput multimodal route, with 1M context, image and video input, and always-on thinking.
- GLM-5.3-FlashX Z.ai: GLM-5.3-FlashX is Z.ai's speed-tuned Flash route with 1M context and tool use, positioned between Flash and GLM-5.3.
- Kimi K3.1 Pro Moonshot AI: Kimi K3.1 Pro is Moonshot AI's flagship 1M-context route, with image input, tool use, and a lower rate card than K3.
- Kimi K3 Moonshot AI: Kimi K3 is Moonshot AI's flagship route in the OmniaKey catalog, with 1M context, image input, and tool use.
- Kimi K2.8 Moonshot AI: Kimi K2.8 is Moonshot's compact 256K route with tool use, priced in line with K2.7 Code.
- Kimi K2.7 Code Moonshot AI: Kimi K2.7 Code is Moonshot's coding-tuned route, with a 256K context, tool use, and rates well below K3.
- MiniMax M3 MiniMax: MiniMax M3 is MiniMax's long-context flagship, with a 1M window and tool use, at a single flat 20% of list.
- MiniMax M3.1 Flash MiniMax: MiniMax M3.1 Flash is MiniMax's low-cost 1M-context route with tool use, built for high-volume traffic.
- MiniMax M2.7 MiniMax: MiniMax M2.7 is MiniMax's standard text route for agent workloads, with a 200K context and tool use.
- MiniMax M2.7 Highspeed MiniMax: MiniMax M2.7 Highspeed serves the same M2.7 model on MiniMax's latency-tuned route, at twice the standard token rate.
- MiMo V2.5 Xiaomi MiMo: MiMo V2.5 is Xiaomi's multimodal route with 1M context, vision, and tool use.
- MiMo V2.5 Pro Xiaomi MiMo: MiMo V2.5 Pro is Xiaomi's long-horizon reasoning route with 1M context and structured tool use.
- MiMo V2.6 Flash Xiaomi MiMo: MiMo V2.6 Flash is Xiaomi's fast 1M-context route with tool use, built for cheap high-volume calls.
- MiMo V2.6 Pro Xiaomi MiMo: MiMo V2.6 Pro is Xiaomi's 1M-context flagship with structured tool use, succeeding V2.5 Pro.
- Hy3 Tencent Hunyuan: Hy3 is Tencent Hunyuan's reasoning route with a 256K context and structured tool use.
- Hy4 Preview Tencent Hunyuan: Hy4 Preview is Tencent Hunyuan's preview reasoning route with a 256K context and structured tool use.
- GPT-Image 2.5 Flare OpenAI: GPT Image 2.5 Flare — Text-to-image generation and reference editing, priced per image in 1K, 2K and 4K tiers. Quality does not change the price.
- GPT-Image 2.5 Sunburst OpenAI: GPT Image 2.5 Sunburst — Text-to-image generation and reference editing, priced per image in 1K, 2K and 4K tiers. Quality does not change the price.
- Nano Banana 2.1 Google: Nano Banana 2.1 generates and edits images on OmniaKey, with a per-call price for each output size.
- Nano Banana Pro Google: Nano Banana Pro is Google's higher-fidelity Gemini 3 Pro image route on OmniaKey, built for detailed text-to-image work and reasoning-heavy reference edits.
- Nano Banana 2 Google: Nano Banana 2 is Google's fast Gemini 3.1 Flash image route on OmniaKey, covering text-to-image generation and reference-based edits at a low per-call price.
- GPT-Image 2 OpenAI: GPT Image 2 — Text-to-image generation and reference editing, priced per image in 1K, 2K and 4K tiers. Quality does not change the price.
- Nano Banana 2 Lite Google: Nano Banana 2 Lite generates and edits 1K images on OmniaKey for $0.019 per call.
- Nano Banana Google: Nano Banana is Google's original Gemini 2.5 Flash Image route on OmniaKey, supporting text-to-image generation and reference-based edits through the media API.
- Qwen Image 3 Alibaba: Qwen Image 3 is Alibaba's Qwen-Image 3 route on OmniaKey, combining text-to-image generation and reference edits with strong Chinese and English text rendering in one per-call media API.
- Qwen Image 3 Pro Alibaba: Qwen Image 3 Pro is Alibaba's flagship Qwen-Image 3 route on OmniaKey, tuned for dense layouts, small on-image text, and material-accurate rendering across generation and edits.
- Wan 2.7 Image Pro Alibaba: Wan 2.7 Image Pro is Alibaba's flagship Wan image route on OmniaKey, handling text-to-image generation and reference edits with high-resolution output and strong text rendering.
- Seedream 5.0 Pro ByteDance: Seedream 5.0 Pro is ByteDance's high-precision image route on OmniaKey, covering text-to-image generation and reference edits with precise control over layout and individual elements.
- Seedream 5.0 Lite ByteDance: Seedream 5.0 Lite is ByteDance's lower-cost Seedream route on OmniaKey, handling text-to-image generation and reference edits through the same asynchronous media API.
- Grok Imagine xAI: Grok Imagine is xAI's entry image route on OmniaKey, turning text prompts into images through the same asynchronous, per-call media API.
- Grok Imagine Quality xAI: Grok Imagine Quality is xAI's higher-fidelity image route on OmniaKey, trading speed for more detailed text-to-image output at the same per-call price.
- Grok Imagine 2.0 xAI: Grok Imagine 2.0 is xAI's newest image route on OmniaKey, serving the latest Grok image model through the asynchronous, per-call media API.
- Suno v4.5 Suno: Suno v4.5 is OmniaKey's first live music route: describe a style and let the model write the words, or send your own lyrics with a style tag, and one finished song comes back through the same asynchronous media API as images and video.
- Suno v6 Suno: Suno v6 is the newest music model on OmniaKey: describe a style and let the model write the words, or send your own lyrics with a style tag, and one finished song comes back through the same asynchronous media API as images and video.
Common questions
Choose an API for your task
01Which image generation API should I use in my app?
Start with your task: creating a new image, editing a reference, or generating text inside an image. Compare GPT Image and Nano Banana on the same input, then check supported sizes and current prices. OmniaKey lets you try these models with one key and balance; the image API guide covers the first request.
02How do I add AI video generation to my product?
Choose a model that supports your input, duration, and resolution, such as Kling or Seedance. With OmniaKey, submit a media task, save its ID, and poll its status to retrieve the finished video. Follow the video API guide to complete one generation before adding it to your app.
03How do I connect a model to Claude Code or Codex?
Choose a model supported by your tool, then configure your OmniaKey key and the matching API address. Follow the Claude Code guide or Codex guide, since their settings differ. Run one small coding task and review its usage before starting a longer session.