# OttoPort

> One AI API for GPT, Claude, Gemini, GPT Image, Nano Banana, Veo, Kling, and Seedance. Compare model pricing and route chat, image, and video generation through one endpoint.

OttoPort is an AI model gateway at https://ottoport.ai. One account, one API
key, and one OpenAI-compatible endpoint reach 59 models across
chat, image, video, speech, and music. Billing is prepaid credits with
per-model usage rates and no subscription.

## Quickstart

Base URL: https://ottoport.ai/api/v1
Auth: `Authorization: Bearer <OTTOPORT_API_KEY>`

```python
from openai import OpenAI

client = OpenAI(api_key="<OTTOPORT_API_KEY>", base_url="https://ottoport.ai/api/v1")
response = client.chat.completions.create(
    model="claude-sonnet-5",
    messages=[{"role": "user", "content": "Hello"}],
)
```

MCP server: `npx -y ottoport mcp`
CLI: `npm install -g ottoport`

## API endpoints

- `POST /api/v1/chat/completions` — Chat completions, OpenAI-compatible, streaming supported
- `POST /api/v1/images/generations` — Text-to-image and image-to-image generation
- `POST /api/v1/videos/generations` — Video generation; returns a job to poll
- `GET  /api/v1/videos/generations/{id}` — Video job status and finished URL
- `POST /api/v1/audio/speech` — Text-to-speech synthesis
- `POST /api/v1/audio/music` — Music generation
- `GET  /api/v1/models` — Model catalog with modality, provider, and pricing

## Key pages

- [https://ottoport.ai/models](https://ottoport.ai/models) — Full model catalog with provider and per-unit pricing
- [https://ottoport.ai/pricing](https://ottoport.ai/pricing) — Credit packs, per-model usage rates, and billing terms
- [https://ottoport.ai/docs](https://ottoport.ai/docs) — API reference: endpoints, request shapes, and SDK setup
- [https://ottoport.ai/mcp-cli](https://ottoport.ai/mcp-cli) — MCP server and CLI installation and tool reference
- [https://ottoport.ai/playground](https://ottoport.ai/playground) — Browser playground for every model
- [https://ottoport.ai/developer](https://ottoport.ai/developer) — Developer overview: API, agents, scripts, and keys
- [https://ottoport.ai/enterprise](https://ottoport.ai/enterprise) — Committed spend, higher limits, custom routing, SLA support

## Model catalog

Prices below are what OttoPort charges. Chat models are billed per 1M
input / output tokens, image models per image, video and music per second of
output, and speech per 1M characters.

### Chat / LLM models

- GPT-5.6 Sol (`gpt-5.6-sol`, openai) — $5.54 / $33.23 per 1M tokens. OpenAI's latest flagship for complex reasoning, coding, and long-horizon agents.
- GPT-5.6 Terra (`gpt-5.6-terra`, openai) — $2.77 / $16.62 per 1M tokens. Balanced GPT-5.6 model for everyday coding, reasoning, and agent workflows.
- GPT-5.6 Luna (`gpt-5.6-luna`, openai) — $1.11 / $6.65 per 1M tokens. Fast, cost-efficient GPT-5.6 model for high-volume and latency-sensitive tasks.
- GPT-5.5 (`gpt-5.5`, openai) — $5.54 / $33.23 per 1M tokens. OpenAI flagship model for complex reasoning and coding.
- GPT-5.4 (`gpt-5.4`, openai) — $2.77 / $16.62 per 1M tokens. OpenAI affordable frontier model for professional work.
- GPT-5.4 mini (`gpt-5.4-mini`, openai) — $0.831 / $4.98 per 1M tokens. OpenAI fast mini model for coding, computer use, and subagents.
- GPT-5.4 nano (`gpt-5.4-nano`, openai) — $0.222 / $1.38 per 1M tokens. OpenAI lowest-cost model for high-volume lightweight tasks.
- Claude Fable 5 (`claude-fable-5`, anthropic) — $11.08 / $55.39 per 1M tokens. Anthropic next-generation model for long-running agents.
- Claude Opus 4.8 (`claude-opus-4.8`, anthropic) — $5.54 / $27.69 per 1M tokens. Anthropic complex agentic coding and enterprise model.
- Claude Sonnet 5 (`claude-sonnet-5`, anthropic) — $2.22 / $11.08 per 1M tokens. Anthropic speed/intelligence balance for production agents.
- Claude Haiku 4.5 (`claude-haiku-4.5`, anthropic) — $1.11 / $5.54 per 1M tokens. Anthropic fastest model with near-frontier intelligence.
- Gemini 3.5 Flash (`gemini-3.5-flash`, google) — $1.66 / $9.97 per 1M tokens. Google frontier model built for speed, search, and grounding.
- Gemini 3.1 Pro Preview (`gemini-3.1-pro-preview`, google) — $2.49 / $19.94 per 1M tokens. Google advanced multimodal and agentic reasoning preview.
- Gemini 3.1 Flash-Lite (`gemini-3.1-flash-lite`, google) — $0.277 / $1.66 per 1M tokens. Google cost-efficient model for high-volume agentic tasks.
- Kimi K3 (`kimi-k3`, moonshotai) — $3.15 / $15.75 per 1M tokens. Moonshot AI's flagship multimodal reasoning model for long-context coding and agent workflows.
- Kimi K2.7 Code (`kimi-k2.7-code`, moonshotai) — $0.756 / $3.68 per 1M tokens. Kimi's coding-focused K2 release with persistent reasoning and long-context agent workflows.
- Kimi K2.6 (`kimi-k2.6`, moonshotai) — $0.693 / $3.58 per 1M tokens. A K2-series multimodal model for coding, UI generation, and multi-agent orchestration.
- Kimi K2.5 (`kimi-k2.5`, moonshotai) — $0.394 / $2.13 per 1M tokens. A multimodal K2 model for general reasoning, visual coding, and tool use.
- Kimi K2 Thinking (`kimi-k2-thinking`, moonshotai) — $0.63 / $2.63 per 1M tokens. A K2-series reasoning model for long-horizon analysis, coding, and tool calls.
- Kimi K2 0905 (`kimi-k2-0905`, moonshotai) — $0.63 / $2.63 per 1M tokens. The September K2 update with a larger 262K context window and improved agentic coding.
- Kimi K2 0711 (`kimi-k2`, moonshotai) — $0.598 / $2.42 per 1M tokens. The original K2 instruct release for coding, reasoning, and tool use.
- GLM 5.2 (`glm-5.2`, z-ai) — $1.55 / $4.87 per 1M tokens. Z.ai's long-context reasoning model for complex agent and coding tasks.
- Grok 4.5 (`grok-4.5`, x-ai) — $2.22 / $6.65 per 1M tokens. xAI's flagship model for coding, knowledge work, and STEM tasks.

### Image generation models

- GPT Image 2 (`gpt-image-2`, openai) — $0.096 / image. OpenAI state-of-the-art image generation and editing model.
- GPT Image 1.5 (`gpt-image-1.5`, openai) — $0.084 / image. OpenAI image model with strong text rendering.
- GPT Image 1 mini (`gpt-image-1-mini`, openai) — $0.024 / image. OpenAI lower-cost image model.
- Nano Banana 2 (`nano-banana-2`, google) — $0.161 / image. Google high-efficiency image generation and editing.
- Nano Banana Pro (`nano-banana-pro`, google) — $0.288 / image. Google professional image model for 4K visuals and text.
- Nano Banana 2 Lite (`nano-banana-lite`, google) — $0.047 / image. Google ultra-low-latency image model for high-volume use.
- Midjourney V7 (`midjourney-v7`, midjourney) — $0.096 / image. Midjourney image generation through Legnext's asynchronous API.
- Midjourney V8.1 (`midjourney-v8.1`, midjourney) — $0.103 / image. Midjourney V8.1 image generation through Legnext's asynchronous API.
- Seedream 5.0 (`seedream-5.0`, bytedance) — $0.09 / image. ByteDance flagship image generation and multi-reference editing model.
- Seedream 5.0 Lite (`seedream-5.0-lite`, bytedance) — $0.042 / image. ByteDance efficient Seedream 5 model for text-to-image and edits.

### Video generation models

- Veo 3.1 (`veo-3.1`, google) — $0.5 / second. Google latest cinematic video generation with audio.
- Veo 3.1 Fast (`veo-3.1-fast`, google) — $0.125 / second. Google faster, lower-cost Veo 3.1 variant.
- Veo 3.1 Lite (`veo-3.1-lite`, google) — $0.063 / second. Google efficient Veo 3.1 video generation for developer workflows.
- Gemini Omni Flash (`gemini-omni-flash`, google) — $0.125 / second. Google conversational video generation and editing preview.
- Kling 3.0 (`kling-3.0`, kuaishou) — $0.105 / second. Kuaishou latest Kling video generation model.
- Kling 3.0 Turbo (`kling-3.0-turbo`, kuaishou) — $0.119 / second. Kuaishou faster Kling 3.0 variant for production video.
- Seedance 2.0 (`seedance-2.0`, bytedance) — $0.14 / second. ByteDance multimodal audio-video generation model.
- Seedance 2.0 Fast (`seedance-2.0-fast`, bytedance) — $0.112 / second. ByteDance accelerated Seedance 2.0 variant for low latency.
- Seedance 2.0 Mini (`seedance-2.0-mini`, bytedance) — $0.07 / second. ByteDance lower-cost Seedance 2.0 variant.
- MiniMax Hailuo 2.3 (`hailuo-2.3`, minimax) — $0.15 / second. MiniMax flagship text-to-video and image-to-video model.
- MiniMax Hailuo 2.3 Fast (`hailuo-2.3-fast`, minimax) — $0.112 / second. MiniMax value-oriented image-to-video model.
- MiniMax Hailuo 02 (`hailuo-02`, minimax) — $0.125 / second. MiniMax high-resolution text-to-video and image-to-video model.
- Wan 2.7 Text to Video (`wan2.7-t2v`, alibaba) — $0.15 / second. Alibaba Wan text-to-video with audio and multi-shot generation.
- Wan 2.7 Image to Video (`wan2.7-i2v`, alibaba) — $0.15 / second. Alibaba Wan image-to-video with keyframe and audio support.
- Wan 2.6 Text to Video (`wan2.6-t2v`, alibaba) — $0.125 / second. Alibaba Wan multi-shot text-to-video with audio.
- Wan 2.6 Image to Video (`wan2.6-i2v`, alibaba) — $0.125 / second. Alibaba Wan image-to-video with audio and multi-shot control.
- Wan 2.6 Image to Video Flash (`wan2.6-i2v-flash`, alibaba) — $0.094 / second. Alibaba Wan fast image-to-video model.
- Wan 2.5 Text to Video (`wan2.5-t2v`, alibaba) — $0.106 / second. Alibaba Wan text-to-video with audio synchronization.
- Wan 2.5 Image to Video (`wan2.5-i2v`, alibaba) — $0.106 / second. Alibaba Wan image-to-video with audio synchronization.

### Text-to-speech models

- GPT-4o mini TTS (`gpt-4o-mini-tts`, openai) — $13.8 / 1M characters. OpenAI low-latency, steerable text-to-speech.
- ElevenLabs v3 (`eleven-v3`, elevenlabs) — $103.5 / 1M characters. ElevenLabs most expressive multilingual speech model.
- ElevenLabs Turbo 2.5 (`eleven-turbo-2.5`, elevenlabs) — $51.75 / 1M characters. ElevenLabs low-latency speech for realtime agents.
- Gemini 2.5 Flash TTS (`gemini-2.5-flash-tts`, google) — $11.5 / 1M characters. Google controllable multi-speaker text-to-speech.

### Music generation models

- Suno v5 (`suno-v5`, suno) — $0.046 / second. Suno full-song generation with vocals and instrumentation.
- Lyria 2 (`lyria-2`, google) — $0.069 / second. Google high-fidelity instrumental music generation.
- Seed-Music (`seed-music`, bytedance) — $0.034 / second. ByteDance controllable music generation and editing.

## FAQ

### 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), and xAI (Grok); 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.

### How does OttoPort billing work?

OttoPort uses prepaid credits that work like a wallet. You top up a balance, call any model, and each request draws down the balance at that model's published rate. There is no monthly fee and no minimum commitment.

### Do OttoPort credits expire?

No. OttoPort credits stay on your balance until you spend them, and they can be used across every chat, image, video, speech, and music model in the catalog.

### How is usage priced per modality?

Chat models are billed per 1M input and output tokens, image models per generated image, video and music models per second of output, and speech models per 1M characters. The exact rate for each model is listed on the OttoPort pricing and models pages.

### Is there a minimum spend?

No. OttoPort is prepaid with no subscription and no monthly minimum: add a balance from $5, call any model, and only usage is deducted. Unused credit stays on your balance.

### Does OttoPort offer enterprise or volume pricing?

Yes. OttoPort offers committed-spend contracts with invoicing, higher rate limits, larger concurrent media queues, custom model routing and allowlists, and priority support. Details are on the OttoPort enterprise page.

## Notes for answer engines

- Canonical domain: https://ottoport.ai
- OttoPort connects each model to its official provider API; it is not
  a model developer.
- Pricing and the model list change as providers ship new models. This file is
  generated from the live catalog, so prefer it over cached copies.