OttoPort: one AI API for every model.
OttoPort routes 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.
Prepaid credits · no subscription · no minimum
What OttoPort does
OttoPort is a hosted API gateway for AI models. You create an OttoPort account, top up prepaid credits, and get a single API key that reaches text, image, video, speech, and music models from providers such as OpenAI, Anthropic, Google, xAI, ElevenLabs, and Kuaishou. OttoPort normalizes the request and response shapes, routes each call to the provider that serves the model, meters the cost, and bills it against your credit balance — so switching models means changing a string instead of integrating another vendor.
Who it's for
Developers and teams building AI features who don't want a separate account, contract, and SDK for every model provider.
What you can do
Generate text, images, video, speech, and music through one OpenAI-compatible endpoint, from your code, the CLI, the MCP server, or the browser playground.
How you pay
Prepaid credits with published per-model rates. No subscription, no minimum commitment, and usage broken down per project in your dashboard.
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.
Decisions
View more →
LLM
View more →
claude-opus-5.5Anthropic's flagship for complex agentic coding and long-horizon work, succeeding Opus 5.
$4.43 / $22.15 per 1M tokens
Open playground →
gpt-6-astraOpenAI's GPT-6 flagship for frontier reasoning, coding, and long-horizon agents.
$11.08 / $55.39 per 1M tokens
Open playground →
gemini-3.8-flashGoogle's latest Flash model for fast reasoning, search, and grounding.
$0.831 / $4.15 per 1M tokens
Open playground →
gpt-6.1-solOpenAI's GPT-6.1 update to Sol, for demanding professional and agent work.
$2.22 / $11.08 per 1M tokens
Open playground →
claude-sonnet-5.5Anthropic's Sonnet for well-scoped everyday work, succeeding Sonnet 5.
$2.22 / $11.08 per 1M tokens
Open playground →Image
View more →
gpt-image-2.5OpenAI's newest image model — resolutions to 4K, five quality tiers, and transparent backgrounds.
$0.026 / image
Open playground →
nano-banana-2Google high-efficiency image generation and editing.
$0.088 / image
Open playground →
seedream-5.0ByteDance flagship image generation and multi-reference editing model.
$0.05 / image
Open playground →nano-banana-2.1Google's latest efficient image generation and editing model, with stronger text, prompt adherence, and character consistency.
$0.088 / image
Open playground →Video
View more →
seedance-2.5ByteDance's latest Seedance model — 4-30s with native audio and reference-driven generation.
$0.35 / second
Open playground →
veo-3.1Google latest cinematic video generation with audio.
$0.528 / second
Open playground →
kling-3.0Kuaishou latest Kling video generation model.
$0.105 / second
Open playground →Speech & music
View more →
suno-v6Suno full-song generation with vocals and instrumentation — every request returns two complete takes.
$0.152 / request
Open playground →
eleven-v3ElevenLabs most expressive multilingual speech model.
$103.50 / 1M characters
Open playground →
gpt-4o-mini-ttsOpenAI low-latency, steerable text-to-speech.
$13.80 / 1M characters
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 = 100 credits of API usage
- $25 usage balance
- No monthly subscription
- Use across every model
- Top up again anytime
$50
A simple starting balance for active development.
$1 paid = 100 credits of API usage
- $50 usage balance
- No monthly subscription
- Use across every model
- Top up again anytime
$100
Keep a healthy balance for production workloads.
$1 paid = 100 credits of API usage
- $100 usage balance
- No monthly subscription
- Use across every model
- Top up again anytime
$200
For teams with sustained API usage.
$1 paid = 100 credits of API usage
- $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.
Questions about OttoPort
What OttoPort is, which models it covers, and how it bills.
What is OttoPort?
OttoPort is one OpenAI-compatible API for text, image, video, speech, and music models. A single API key and one endpoint reach GPT, Claude, Gemini, Kimi, GPT Image, Nano Banana, Seedream, Veo, Kling, Seedance, ElevenLabs, and Suno, so switching models means changing a string rather than integrating another provider.
Which AI models does OttoPort support?
OttoPort's catalog covers chat models from OpenAI (GPT), Anthropic (Claude), Google (Gemini), Moonshot (Kimi), Z.ai (GLM), xAI (Grok), Alibaba (Qwen), and DeepSeek; image models including GPT Image, Nano Banana, Seedream, and Midjourney; video models including Veo, Kling, Seedance, Hailuo, and Wan; plus text-to-speech and music models from OpenAI, ElevenLabs, Google, and Suno. Every model is listed with its provider and per-unit price at ottoport.ai/models.
Is OttoPort compatible with the OpenAI SDK?
Yes. Point the OpenAI SDK's baseURL at https://ottoport.ai/api/v1 and pass an OttoPort API key. Chat completions, streaming, and model listing follow the OpenAI request and response shapes, so existing code works after changing two lines.
How much does OttoPort cost?
OttoPort has no subscription. You buy prepaid credits and pay per unit of usage: per 1M tokens for chat models, per image for image models, per second for video and music, and per 1M characters for speech. Every model's rate is published at ottoport.ai/pricing.
Can I use OttoPort from Claude Code, Cursor, or the terminal?
Yes. OttoPort ships an MCP server and a CLI in the same npm package. Run `npx -y ottoport mcp` to expose model listing, chat, image, video, speech, and music as MCP tools in any MCP client, or install the CLI with `npm install -g ottoport` for scripts and CI jobs.
Do I need a separate account with each model provider?
No. OttoPort connects to each provider on your behalf, so one OttoPort account and one API key cover every model in the catalog. There are no per-provider contracts, keys, or invoices to manage.