AI API Docs | OttoPort

Overview

Introduction

OttoPort is a unified gateway that routes LLM, image, and video generation through a single OpenAI-compatible surface. Every request is authenticated with one key and billed against one credit balance — no per-provider accounts to juggle.

Chat is synchronous. Responses stream token-by-token, exactly like the OpenAI API.
Image & video wait on the queue. The gateway holds the request until the provider finishes and returns the result URL.
One catalog. Discover every model, its provider, and its price at GET /v1/models.

Get started

Quickstart

Install the OpenAI SDK, set base_url to the OttoPort gateway, and use your op- key as the API key. Your first chat request is three lines away.

pip install openai      # or: npm install openai

curl https://ottoport.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OTTOPORT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-5",
    "messages": [{ "role": "user", "content": "Hello!" }]
  }'

The same client works for images and video — switch the model id and call images.generate or the videos endpoint. See the sections below.

Get started

Authentication

Every request must include an Authorization header with your secret key. Keys are prefixed with op- and are created in API Keys. Keep them server-side — never ship a key in client code.

Authorization: Bearer op-xxxxxxxxxxxxxxxxxxxxxxxx

A key is shown only once at creation. Store it in a secret manager or an environment variable such as OTTOPORT_API_KEY.

API reference

Chat completions

POST/v1/chat/completions

OpenAI-compatible chat across GPT, Claude, and Gemini. Streaming, tool use, and function calling work unchanged — OttoPort translates between the OpenAI schema and each provider.

Parameter	Type	Description
`model`required	string	Any chat model id, e.g. `claude-sonnet-5`.
`messages`required	array	Conversation as role/content objects.
`stream`optional	boolean	Stream tokens as server-sent events. Defaults to `false`.
`temperature`optional	number	Sampling temperature, 0–2.
`max_tokens`optional	integer	Cap on generated tokens.
`top_p`optional	number	Nucleus sampling cutoff.
`stop`optional	string \| string[]	Sequence(s) that halt generation.

curl https://ottoport.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OTTOPORT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "messages": [
      { "role": "system", "content": "You are concise." },
      { "role": "user", "content": "Explain MCP in one line." }
    ],
    "temperature": 0.7,
    "stream": false
  }'

Response

{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "model": "gpt-5.4",
  "choices": [
    {
      "index": 0,
      "message": { "role": "assistant", "content": "..." },
      "finish_reason": "stop"
    }
  ],
  "usage": { "prompt_tokens": 24, "completion_tokens": 18, "total_tokens": 42 }
}

API reference

Image generation

POST/v1/images/generations

Generate or edit images with GPT Image and Nano Banana models. Pass image_url to run image-to-image edits. The gateway waits for the provider and returns hosted URLs.

Parameter	Type	Description
`model`required	string	Image model id, e.g. `nano-banana-pro`.
`prompt`required	string	Text description of the image.
`size`optional	string	e.g. `1024x1024` or `16:9`.
`n`optional	integer	Number of images to return.
`seed`optional	integer	Seed for reproducible output.
`image_url`optional	string	Source image for edits / image-to-image.

curl https://ottoport.ai/api/v1/images/generations \
  -H "Authorization: Bearer $OTTOPORT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nano-banana-pro",
    "prompt": "a chrome torus on a black background, studio light",
    "size": "1024x1024",
    "n": 1
  }'

Response

{
  "created": 1736200000,
  "model": "nano-banana-pro",
  "data": [{ "url": "https://cdn.ottoport.ai/img/9f2a...png" }],
  "usage": { "cost": 0.24 }
}

API reference

Video generation

POST/v1/videos/generations

Generate video with Veo, Kling, and Seedance. OttoPort submits the job, waits on the provider queue, and returns a job object whose status is completed with the result URL (or failed with an error).

Parameter	Type	Description
`model`required	string	Video model id, e.g. `kling-3.0`.
`prompt`required	string	Text description of the shot.
`image_url`optional	string	First frame for image-to-video.
`duration`optional	integer	Clip length in seconds.
`aspect_ratio`optional	string	e.g. `16:9`, `9:16`.
`seed`optional	integer	Seed for reproducible output.

curl https://ottoport.ai/api/v1/videos/generations \
  -H "Authorization: Bearer $OTTOPORT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kling-3.0",
    "prompt": "cinematic product reveal, slow dolly, black background",
    "duration": 5,
    "aspect_ratio": "16:9"
  }'

Response

{
  "id": "vid_7c1e...",
  "model": "kling-3.0",
  "status": "completed",
  "created": 1736200000,
  "data": [{ "url": "https://cdn.ottoport.ai/vid/7c1e....mp4" }],
  "usage": { "cost": 0.42 }
}

API reference

List models

GET/v1/models

Returns the catalog in OpenAI list format, enriched with modality, provider, and pricing. Filter by modality with the modality query parameter.

Parameter	Type	Description
`modality`optional	string	Filter to `chat`, `image`, or `video`.

curl "https://ottoport.ai/api/v1/models?modality=video" \
  -H "Authorization: Bearer $OTTOPORT_API_KEY"

Response

{
  "object": "list",
  "data": [
    {
      "id": "kling-3.0",
      "object": "model",
      "owned_by": "kuaishou",
      "modality": "video",
      "display_name": "Kling 3.0",
      "description": "...",
      "pricing": { "perSecond": 0.084 }
    }
  ]
}

Reference

Model catalog

Every model available today, straight from the gateway registry. Chat is priced per 1M tokens (input / output); image per image; video per second.

Model ID	Modality	Provider	Pricing
`gpt-5.6-sol`	chat	openai	$5 / $30 per 1M
`gpt-5.6-terra`	chat	openai	$2.5 / $15 per 1M
`gpt-5.6-luna`	chat	openai	$1 / $6 per 1M
`gpt-5.5`	chat	openai	$5 / $30 per 1M
`gpt-5.4`	chat	openai	$2.5 / $15 per 1M
`gpt-5.4-mini`	chat	openai	$0.75 / $4.5 per 1M
`gpt-5.4-nano`	chat	openai	$0.2 / $1.25 per 1M
`claude-fable-5`	chat	anthropic	$10 / $50 per 1M
`claude-opus-4.8`	chat	anthropic	$5 / $25 per 1M
`claude-sonnet-5`	chat	anthropic	$2 / $10 per 1M
`claude-haiku-4.5`	chat	anthropic	$1 / $5 per 1M
`gemini-3.5-flash`	chat	google	$1.5 / $9 per 1M
`gemini-3.1-pro-preview`	chat	google	$2.25 / $18 per 1M
`gemini-3.1-flash-lite`	chat	google	$0.25 / $1.5 per 1M
`kimi-k3`	chat	moonshotai	$3 / $15 per 1M
`kimi-k2.7-code`	chat	moonshotai	$0.72 / $3.5 per 1M
`kimi-k2.6`	chat	moonshotai	$0.66 / $3.41 per 1M
`kimi-k2.5`	chat	moonshotai	$0.375 / $2.025 per 1M
`kimi-k2-thinking`	chat	moonshotai	$0.6 / $2.5 per 1M
`kimi-k2-0905`	chat	moonshotai	$0.6 / $2.5 per 1M
`kimi-k2`	chat	moonshotai	$0.57 / $2.3 per 1M
`glm-5.2`	chat	z-ai	$1.4 / $4.4 per 1M
`grok-4.5`	chat	x-ai	$2 / $6 per 1M
`gpt-image-2`	image	openai	—
`gpt-image-1.5`	image	openai	—
`gpt-image-1-mini`	image	openai	—
`nano-banana-2`	image	google	$0.134 / image
`nano-banana-pro`	image	google	$0.24 / image
`nano-banana-lite`	image	google	$0.039 / image
`midjourney-v7`	image	midjourney	$0.08 / image
`midjourney-v8.1`	image	midjourney	$0.086 / image
`veo-3.1`	video	google	$0.4 / sec
`veo-3.1-fast`	video	google	$0.1 / sec
`veo-3.1-lite`	video	google	$0.05 / sec
`gemini-omni-flash`	video	google	$0.1 / sec
`kling-3.0`	video	kuaishou	$0.084 / sec
`kling-3.0-turbo`	video	kuaishou	$0.095 / sec
`seedance-2.0`	video	bytedance	$0.112 / sec
`seedance-2.0-fast`	video	bytedance	$0.09 / sec
`seedance-2.0-mini`	video	bytedance	$0.056 / sec
`hailuo-2.3`	video	minimax	$0.12 / sec
`hailuo-2.3-fast`	video	minimax	$0.09 / sec
`hailuo-02`	video	minimax	$0.1 / sec
`wan2.7-t2v`	video	alibaba	$0.12 / sec
`wan2.7-i2v`	video	alibaba	$0.12 / sec
`wan2.6-t2v`	video	alibaba	$0.1 / sec
`wan2.6-i2v`	video	alibaba	$0.1 / sec
`wan2.6-i2v-flash`	video	alibaba	$0.075 / sec
`wan2.5-t2v`	video	alibaba	$0.085 / sec
`wan2.5-i2v`	video	alibaba	$0.085 / sec
`seedream-5.0`	image	bytedance	$0.075 / image
`seedream-5.0-lite`	image	bytedance	$0.035 / image
`gpt-4o-mini-tts`	tts	openai	—
`eleven-v3`	tts	elevenlabs	—
`eleven-turbo-2.5`	tts	elevenlabs	—
`gemini-2.5-flash-tts`	tts	google	—
`suno-v5`	music	suno	—
`lyria-2`	music	google	—
`seed-music`	music	bytedance	—

Reference

Errors

Errors use standard HTTP status codes and an OpenAI-style error object with a stable code. The type mirrors code for SDK compatibility.

{
  "error": {
    "message": "`model` and `messages` are required",
    "type": "invalid_request",
    "code": "invalid_request"
  }
}

Status	Code	When
400	`invalid_request`	Missing or malformed body (e.g. no model or messages).
401	`missing_api_key`	No Authorization: Bearer header was sent.
401	`invalid_api_key`	Key is malformed or not recognized.
402	`insufficient_credits`	The account's credit balance is exhausted.
404	`model_not_found`	The requested model id is not in the catalog.
429	`rate_limited`	Too many requests — back off and retry.
502	`upstream_error`	The upstream provider failed or timed out.

Reference

Rate limits

Limits scale with your spend tier. When you exceed them the gateway returns 429 rate_limited — back off with exponential retry and honor any Retry-After header. Need higher throughput or dedicated capacity? Talk to us.

Reference

SDKs & tools

The gateway is the product; every other surface is a thin client over it. Use the one that fits your workflow — they all share the same model ids and one key.

API reference

Introduction

Quickstart

Authentication

Chat completions

Image generation

Video generation

List models

Model catalog

Errors

Rate limits

SDKs & tools

OpenAI SDKs

MCP & CLI

Playground

API Keys