OpenAI API
OpenAI
First-party
OpenAI-compatible API
First-party Chat Completions and Responses APIs for OpenAI models.
Hosts directory
A sourced directory of the places models run. First-party provider APIs sit here beside dedicated inference hosts and gateways that route across backends. When a host exposes an OpenAI-compatible surface, harnesses that speak that protocol can point at it the way they point at hardware you own.
Open the plannerRows were last checked on 2026-08-05. Catalogs and API shapes move; confirm pricing and endpoint support against each operator’s current docs before you wire anything up.
Filters
33 of 33 hosts
The OpenAI-compatible marker is what lets a harness treat a host like a local endpoint. See which tools speak that protocol in the harness directory.
OpenAI
OpenAI-compatible API
First-party Chat Completions and Responses APIs for OpenAI models.
Anthropic
Messages API is the native surface. An OpenAI-compatible shim exists in some SDKs; confirm against current Anthropic docs before relying on it.
OpenAI-compatible API
Gemini Developer API with an OpenAI-compatible endpoint option.
Google Cloud
OpenAI-compatible API
Enterprise Gemini plus Model Garden open models. Catalog is Google-managed; arbitrary self-upload is outside what we mark as BYO here.
xAI
OpenAI-compatible API
Grok models behind an OpenAI-compatible chat completions surface.
DeepSeek
OpenAI-compatible API
Hosted DeepSeek models. Open-weight checkpoints are published separately for self-hosting; this row covers the first-party API only.
Moonshot AI
OpenAI-compatible API
Kimi models via an OpenAI-compatible platform API.
Alibaba Cloud
OpenAI-compatible API
Qwen and related Model Studio models, including open-weight Qwen variants in the catalog.
Zhipu AI
OpenAI-compatible API
GLM models on the Z.ai platform with an OpenAI-compatible API path.
Mistral AI
OpenAI-compatible API
La Plateforme serves Mistral open and commercial models through an OpenAI-compatible API.
Amazon Web Services
Multi-provider catalog on AWS. Native Bedrock APIs are the documented path; OpenAI-compatible access is not counted as first-class here.
Cohere
Command and Embed models on Cohere’s native API surface.
MiniMax
OpenAI-compatible API
MiniMax text and speech models. Confirm current OpenAI-compatible path in their platform docs.
ByteDance / Volcengine
OpenAI-compatible API
Volcengine ModelArk hosts Doubao and related ByteDance models. Pricing pages are region-specific; confirm on the console you use.
Baidu
OpenAI-compatible API
Qianfan platform for ERNIE and selected open models. Capability marks are conservative pending console verification.
Thinking Machines Lab
Tinker is positioned for fine-tuning and sampling open models. Pricing and OpenAI-compatibility were not clear from public pages at check time, so both marks stay conservative.
NVIDIA
OpenAI-compatible API
Microservice containers and hosted endpoints for NVIDIA-optimized and partner open models.
Cerebras
OpenAI-compatible API
Positions on wafer-scale chips for very high tokens-per-second on supported models.
Catalog of open models on Cerebras hardware. BYO custom weights are outside the public inference product as checked.
Groq
OpenAI-compatible API
LPU inference marketed for low latency on a fixed open-model catalog.
OpenAI-compatible chat and audio endpoints for Groq’s hosted model list.
Together AI
OpenAI-compatible API
Serverless open-model inference plus dedicated endpoints and fine-tuning.
Fireworks AI
OpenAI-compatible API
Fast open-model inference with deployment options for custom fine-tunes.
DeepInfra
OpenAI-compatible API
Broad open-model catalog with OpenAI-compatible and native HTTP APIs.
Baseten
OpenAI-compatible API
Model deployment platform; OpenAI-compatible wrappers are common on deployed Truss apps.
Nebius
OpenAI-compatible API
Open-model serving on Nebius cloud. Custom weight upload was not clearly documented at check time.
Lambda
OpenAI-compatible API
Inference API alongside Lambda GPU cloud. Catalog coverage changes; confirm the live model list.
Novita AI
OpenAI-compatible API
Open-model serverless API with GPU deployment options.
Hyperbolic
OpenAI-compatible API
Open-model inference API. BYO custom weights were not clearly offered on the public API at check time.
Replicate
OpenAI-compatible API
Strong on image, video, and audio models alongside LLMs. OpenAI-compatible HTTP is available for a subset of language models.
OpenRouter
OpenAI-compatible API
One OpenAI-compatible key across many provider backends and open-model hosts.
Vercel
OpenAI-compatible API
Routes through Vercel’s AI Gateway to multiple providers with shared observability.
BerriAI
OpenAI-compatible API
Self-hosted (or proxied) gateway that translates one OpenAI-compatible surface onto many providers. You run the proxy; usage cost is whatever backends you attach.
Cloudflare
OpenAI-compatible API
Proxy layer in front of provider APIs for caching, logging, and rate controls.
Portkey
OpenAI-compatible API
AI gateway with routing, guardrails, and an OpenAI-compatible control plane.