One AI API for every model.
Route LLM, image, and video generation through a single OpenAI-compatible endpoint. Compare transparent model pricing for GPT Image, Nano Banana, Veo, Kling, Seedance, Claude, and Gemini.
$5 free credits · no card required
Stop writing per-provider glue code.
OttoPort normalizes requests and responses so you integrate once and swap models with a string.
Unified LLM API
OpenAI-compatible /chat/completions across GPT, Claude, and Gemini. Streaming, system prompts, and token usage normalized for you.
/v1/chat/completionsUnified Image API
One request shape for GPT Image and Nano Banana. Text-to-image and image-to-image return the same tidy { data: [{ url }] }.
/v1/images/generationsUnified Video API
Veo, Kling, Seedance, and Gemini video models behind one schema. OttoPort handles the async queue and hands you a finished URL.
/v1/videos/generationsAdd a model, change a string.
One OttoPort API for your users; OttoPort connects each model directly to its official provider API.
LLM
gpt-5.6-solOpenAI's latest flagship for complex reasoning, coding, and long-horizon agents.
$5 / $30 per 1M tok
Open playground →gpt-5.6-terraBalanced GPT-5.6 model for everyday coding, reasoning, and agent workflows.
$2.5 / $15 per 1M tok
Open playground →gpt-5.6-lunaFast, cost-efficient GPT-5.6 model for high-volume and latency-sensitive tasks.
$1 / $6 per 1M tok
Open playground →gpt-5.5OpenAI flagship model for complex reasoning and coding.
$5 / $30 per 1M tok
Open playground →gpt-5.4OpenAI affordable frontier model for professional work.
$2.5 / $15 per 1M tok
Open playground →gpt-5.4-miniOpenAI fast mini model for coding, computer use, and subagents.
$0.75 / $4.5 per 1M tok
Open playground →gpt-5.4-nanoOpenAI lowest-cost model for high-volume lightweight tasks.
$0.2 / $1.25 per 1M tok
Open playground →claude-fable-5Anthropic next-generation model for long-running agents.
$10 / $50 per 1M tok
Open playground →claude-opus-4.8Anthropic complex agentic coding and enterprise model.
$5 / $25 per 1M tok
Open playground →claude-sonnet-5Anthropic speed/intelligence balance for production agents.
$2 / $10 per 1M tok
Open playground →claude-haiku-4.5Anthropic fastest model with near-frontier intelligence.
$1 / $5 per 1M tok
Open playground →gemini-3.5-flashGoogle frontier model built for speed, search, and grounding.
$1.5 / $9 per 1M tok
Open playground →gemini-3.1-pro-previewGoogle advanced multimodal and agentic reasoning preview.
$2.25 / $18 per 1M tok
Open playground →gemini-3.1-flash-liteGoogle cost-efficient model for high-volume agentic tasks.
$0.25 / $1.5 per 1M tok
Open playground →kimi-k3Moonshot AI's flagship multimodal reasoning model for long-context coding and agent workflows.
$3 / $15 per 1M tok
Open playground →kimi-k2.7-codeKimi's coding-focused K2 release with persistent reasoning and long-context agent workflows.
$0.72 / $3.5 per 1M tok
Open playground →kimi-k2.6A K2-series multimodal model for coding, UI generation, and multi-agent orchestration.
$0.66 / $3.41 per 1M tok
Open playground →kimi-k2.5A multimodal K2 model for general reasoning, visual coding, and tool use.
$0.375 / $2.025 per 1M tok
Open playground →kimi-k2-thinkingA K2-series reasoning model for long-horizon analysis, coding, and tool calls.
$0.6 / $2.5 per 1M tok
Open playground →kimi-k2-0905The September K2 update with a larger 262K context window and improved agentic coding.
$0.6 / $2.5 per 1M tok
Open playground →kimi-k2The original K2 instruct release for coding, reasoning, and tool use.
$0.57 / $2.3 per 1M tok
Open playground →glm-5.2Z.ai's long-context reasoning model for complex agent and coding tasks.
$1.4 / $4.4 per 1M tok
Open playground →grok-4.5xAI's flagship model for coding, knowledge work, and STEM tasks.
$2 / $6 per 1M tok
Open playground →Image
gpt-image-2OpenAI state-of-the-art image generation and editing model.
$5 / $30 per 1M tok
Open playground →gpt-image-1.5OpenAI image model with strong text rendering.
$5 / $10 per 1M tok
Open playground →gpt-image-1-miniOpenAI lower-cost image model.
$2 / $8 per 1M tok
Open playground →nano-banana-2Google high-efficiency image generation and editing.
$0.134 / image
Open playground →nano-banana-proGoogle professional image model for 4K visuals and text.
$0.24 / image
Open playground →nano-banana-liteGoogle ultra-low-latency image model for high-volume use.
$0.039 / image
Open playground →midjourney-v7Midjourney image generation through Legnext's asynchronous API.
$0.08 / image
Open playground →midjourney-v8.1Midjourney V8.1 image generation through Legnext's asynchronous API.
$0.086 / image
Open playground →seedream-5.0ByteDance flagship image generation and multi-reference editing model.
$0.075 / image
Open playground →seedream-5.0-liteByteDance efficient Seedream 5 model for text-to-image and edits.
$0.035 / image
Open playground →Video
veo-3.1Google latest cinematic video generation with audio.
$0.4 / sec
Open playground →veo-3.1-fastGoogle faster, lower-cost Veo 3.1 variant.
$0.1 / sec
Open playground →veo-3.1-liteGoogle efficient Veo 3.1 video generation for developer workflows.
$0.05 / sec
Open playground →gemini-omni-flashGoogle conversational video generation and editing preview.
$0.1 / sec
Open playground →kling-3.0Kuaishou latest Kling video generation model.
$0.084 / sec
Open playground →kling-3.0-turboKuaishou faster Kling 3.0 variant for production video.
$0.095 / sec
Open playground →seedance-2.0ByteDance multimodal audio-video generation model.
$0.112 / sec
Open playground →seedance-2.0-fastByteDance accelerated Seedance 2.0 variant for low latency.
$0.09 / sec
Open playground →seedance-2.0-miniByteDance lower-cost Seedance 2.0 variant.
$0.056 / sec
Open playground →hailuo-2.3MiniMax flagship text-to-video and image-to-video model.
$0.12 / sec
Open playground →hailuo-2.3-fastMiniMax value-oriented image-to-video model.
$0.09 / sec
Open playground →hailuo-02MiniMax high-resolution text-to-video and image-to-video model.
$0.1 / sec
Open playground →wan2.7-t2vAlibaba Wan text-to-video with audio and multi-shot generation.
$0.12 / sec
Open playground →wan2.7-i2vAlibaba Wan image-to-video with keyframe and audio support.
$0.12 / sec
Open playground →wan2.6-t2vAlibaba Wan multi-shot text-to-video with audio.
$0.1 / sec
Open playground →wan2.6-i2vAlibaba Wan image-to-video with audio and multi-shot control.
$0.1 / sec
Open playground →wan2.6-i2v-flashAlibaba Wan fast image-to-video model.
$0.075 / sec
Open playground →wan2.5-t2vAlibaba Wan text-to-video with audio synchronization.
$0.085 / sec
Open playground →wan2.5-i2vAlibaba Wan image-to-video with audio synchronization.
$0.085 / sec
Open playground →Top up once. Use any model.
Prepaid credits work like a wallet: add a balance, call any model, and pay only for the tokens, images, or video seconds you use.
$25
A quick top-up for testing and small projects.
$1 paid = $1 of API usage balance
- $25 usage balance
- No monthly subscription
- Use across every model
- Top up again anytime
$50
A simple starting balance for active development.
$1 paid = $1 of API usage balance
- $50 usage balance
- No monthly subscription
- Use across every model
- Top up again anytime
$100
Keep a healthy balance for production workloads.
$1 paid = $1 of API usage balance
- $100 usage balance
- No monthly subscription
- Use across every model
- Top up again anytime
$200
For teams with sustained API usage.
$1 paid = $1 of API usage balance
- $200 usage balance
- No monthly subscription
- Use across every model
- Top up again anytime
Usage prices stay visible.
Credits are consumed by the actual model unit: LLM tokens, generated images, or video seconds.
One wallet, clear usage.
Your balance is shared across chat, image, and video APIs. There are no plans to manage and no credits to move between models.
Enterprise stays simple.
Need committed spend, custom model routing, invoices, or SLAs? We can map credits to a private contract without changing the API.