OpenPaths is an open source model router and AI gateway. One API key and one base URL (https://openpaths.io/v1) reach language, image, video, speech, music, embedding and 3D models from many providers.

Is OpenPaths compatible with the OpenAI and Anthropic SDKs?

Yes. POST /v1/chat/completions follows the OpenAI schema and POST /v1/messages follows the Anthropic schema. Change the base URL and keep your existing code.

How does OpenPaths pricing work?

Pay as you go at the provider price with near-zero markup. Requests on your own provider keys (BYOK) are recorded at $0. See https://openpaths.io/pricing.

What does openpaths/auto do?

openpaths/auto routes each request to a suitable model automatically, with automatic fallbacks when a provider fails or rate-limits.

Is there an OpenAPI spec or MCP server?

Yes. The OpenAPI 3.1 spec is at https://openpaths.io/openapi.json, the MCP endpoint is https://openpaths.io/mcp, and llms.txt plus llms-full.txt list every model id.

How much does OpenAI: GPT-6 Luna Pro cost per million tokens?

OpenAI: GPT-6 Luna Pro costs $0.11 in / $0.53 out per 1M tokens. Prompts over 272K tokens bill the whole request at $0.21 in / $0.79 out per 1M tokens.

Is there a discount for cached tokens on OpenAI: GPT-6 Luna Pro?

Yes. Cached input is $0.011 per 1M tokens instead of $0.11.

What does a typical chatbot cost on OpenAI: GPT-6 Luna Pro?

A chatbot sending 300,000 requests per month (1,500 input and 400 output tokens each, 50% cached) costs about $89.42 per month on OpenAI: GPT-6 Luna Pro.

What is the context window of OpenAI: GPT-6 Luna Pro?

OpenAI: GPT-6 Luna Pro supports 1.05M tokens of context and up to 128K output tokens.

What is a cheaper alternative to OpenAI: GPT-6 Luna Pro?

DeepSeek: DeepSeek V4.1 Flash is cheaper at $0.11 in / $0.51 out per 1M tokens.

OpenAI: GPT-6 Luna Pro API Pricing (2026): $0.11 in / $0.53 out per 1M tokens

OpenAI: GPT-6 Luna Pro pricing: $0.11 in / $0.53 out per 1M tokens. Prompts over 272K tokens cost more. Tier-aware calculator, cheaper alternatives and Artificial Analysis benchmarks.