otari 0.0.2

Python client for the otari gateway

otari (Python)

Python client for otari-gateway. Communicate with any LLM provider through the gateway using a single, typed interface.

TypeScript SDK | Documentation | Platform (Beta)

Quickstart

Generate an API token at otari.ai/organization-settings/api-tokens, then add a provider key (e.g. OpenAI) at otari.ai/organization-settings/provider-keys so the gateway can route requests to that provider. Then use the client:

from otari import OtariClient

client = OtariClient(
    platform_token="tk_your_api_token",
)

response = await client.completion(
    model="openai:gpt-4o-mini",
    messages=[{"role": "user", "content": "Hello!"}],
)

print(response.choices[0].message.content)

That's it! With no api_base, the client defaults to the hosted gateway at https://api.otari.ai. Change the model string to switch between LLM providers through the gateway.

Prefer to keep secrets out of code? Set OTARI_AI_TOKEN in your environment and OtariClient() picks up the token automatically.

Self-hosting the gateway

Prefer to run the gateway yourself instead of using the hosted otari.ai? Follow the setup in the otari gateway repo, then point the SDK at it:

client = OtariClient(
    api_base="http://localhost:8000",  # or wherever you host the gateway
    api_key="your-gateway-api-key",
)

The SDK sends api_key via the custom Otari-Key: Bearer … header. Env: GATEWAY_API_BASE + GATEWAY_API_KEY.

Make sure your gateway has provider keys configured (e.g. OpenAI) so it can route requests upstream — see the otari gateway repo for setup.

Installation

Requirements

• Python 3.11 or newer
• A running otari-gateway instance

Install

pip install otari

Setting Up Credentials

For the hosted gateway, set your platform token (no api_base needed — it defaults to https://api.otari.ai):

export OTARI_AI_TOKEN="tk_your_api_token"

GATEWAY_PLATFORM_TOKEN is kept as a legacy alias for OTARI_AI_TOKEN; the canonical name takes precedence when both are set.

For a self-hosted gateway, set the base URL and an API key instead:

export GATEWAY_API_BASE="http://localhost:8000"
export GATEWAY_API_KEY="your-key-here"

Alternatively, pass credentials directly when creating the client (see Usage examples).

otari-gateway

This Python SDK is a client for otari-gateway, an optional FastAPI-based proxy server that adds enterprise-grade features on top of the core library:

• Budget Management - Enforce spending limits with automatic daily, weekly, or monthly resets
• API Key Management - Issue, revoke, and monitor virtual API keys without exposing provider credentials
• Usage Analytics - Track every request with full token counts, costs, and metadata
• Multi-tenant Support - Manage access and budgets across users and teams

The gateway sits between your applications and LLM providers, exposing an OpenAI-compatible API that works with any supported provider.

Quick Start

docker run \
  -e GATEWAY_MASTER_KEY="your-secure-master-key" \
  -e OPENAI_API_KEY="your-api-key" \
  -p 8000:8000 \
  ghcr.io/mozilla-ai/otari/gateway:latest

Note: You can use a specific release version instead of latest (e.g., 1.2.0). See available versions.

Managed Platform (Beta)

Prefer a hosted experience? The otari platform provides a managed control plane for keys, usage tracking, and cost visibility across providers, while still building on the same otari interfaces.

Usage

Authentication Modes

The client supports two authentication modes, matching the TypeScript SDK:

Platform Mode (Recommended)

Uses a Bearer token in the standard Authorization header. On the hosted platform, generate an API token at otari.ai/organization-settings/api-tokens and add a provider key (e.g. OpenAI) at otari.ai/organization-settings/provider-keys so the gateway can route requests to that provider. With no api_base, the client defaults to the hosted gateway at https://api.otari.ai:

client = OtariClient(
    platform_token="tk_your_api_token",
)

Non-Platform Mode (Self-Hosted)

Sends the API key via a custom Otari-Key header. This targets a self-hosted gateway, so an explicit api_base is required:

client = OtariClient(
    api_base="http://localhost:8000",
    api_key="your-api-key",
)

Auto-Detection from Environment Variables

When no explicit credentials are provided, the client reads from environment variables:

# Platform mode: OTARI_AI_TOKEN (or legacy GATEWAY_PLATFORM_TOKEN),
# defaulting to the hosted gateway.
# Self-hosted: GATEWAY_API_BASE + GATEWAY_API_KEY.
client = OtariClient()

Chat Completions

response = await client.completion(
    model="openai:gpt-4o-mini",
    messages=[{"role": "user", "content": "Hello!"}],
)

print(response.choices[0].message.content)

Streaming

stream = await client.completion(
    model="openai:gpt-4o-mini",
    messages=[{"role": "user", "content": "Tell me a story."}],
    stream=True,
)

async for chunk in stream:
    content = chunk.choices[0].delta.content
    if content:
        print(content, end="", flush=True)

Responses API

response = await client.response(
    model="openai:gpt-4o-mini",
    input="Summarize this in one sentence.",
)

print(response.output_text)

Embeddings

result = await client.embedding(
    model="openai:text-embedding-3-small",
    input="Hello world",
)

print(result.data[0].embedding)

Listing Models

models = await client.list_models()
for model in models:
    print(model.id)

Error Handling

In platform mode, HTTP errors are mapped to typed exceptions:

from otari import OtariClient, AuthenticationError, RateLimitError

try:
    response = await client.completion(
        model="openai:gpt-4o-mini",
        messages=[{"role": "user", "content": "Hello!"}],
    )
except AuthenticationError as e:
    print(f"Invalid credentials: {e.message}")
except RateLimitError as e:
    print(f"Rate limited, retry after: {e.retry_after}")

HTTP Status	Error Class	Description
400 (capability)	UnsupportedCapabilityError	Selected provider does not support the requested capability
401, 403	AuthenticationError	Invalid or missing credentials
402	InsufficientFundsError	Budget or credits exhausted
404	ModelNotFoundError	Model not found, or no provider key configured for the requested provider. The exception's message carries the gateway's detail.
429	RateLimitError	Rate limit exceeded (includes retry_after)
502	UpstreamProviderError	Upstream provider unreachable
504	GatewayTimeoutError	Gateway timed out waiting for provider

UnsupportedCapabilityError surfaces in both platform and non-platform modes; the other mappings are platform-mode only.

Context Manager

The client supports async context manager for automatic cleanup:

async with OtariClient(api_base="http://localhost:8000") as client:
    response = await client.completion(
        model="openai:gpt-4o-mini",
        messages=[{"role": "user", "content": "Hello!"}],
    )

Why choose otari?

• Simple, unified interface - Single client for all providers through the gateway, switch models with just a string change
• Developer friendly - Full type hints for better IDE support and clear, actionable error messages
• Leverages the OpenAI SDK - Built on the official OpenAI Python SDK for maximum compatibility
• Async-first - Built on AsyncOpenAI for modern async Python applications
• Stays framework-agnostic so it can be used across different projects and use cases
• Battle-tested - Powers our own production tools (any-agent)

Development

# Create a virtual environment
python -m venv .venv
source .venv/bin/activate

# Install with dev dependencies
pip install -e ".[dev]"

# Run unit tests
pytest tests/

# Lint
ruff check src/ tests/

# Type-check
mypy src/

Documentation

• Full Documentation - Complete guides and API reference
• Supported Providers - List of all supported LLM providers
• Gateway Documentation - Gateway setup and deployment
• TypeScript SDK - The TypeScript SDK for Node.js applications
• otari Platform (Beta) - Hosted control plane for key management, usage tracking, and cost visibility

Contributing

We welcome contributions from developers of all skill levels! Please see the Contributing Guide or open an issue to discuss changes.

License

This project is licensed under the Apache License 2.0 - see the LICENSE file for details.