SkyPilot Tokens
Product
SkyPilot Tokens is an inference API serving open models across verified GPU fleets for AI developers.
- Currently Offered
SkyPilot Tokens provides an API for running inference with open models through an OpenAI- and Anthropic-compatible endpoint. The service routes requests across verified GPU fleets and dedicated compute.
Developers can use it with existing SDKs and agent workflows; the offering also supports customer-provided provider keys for accessing additional model APIs.
SkyPilot Tokens is an inference API serving open models across verified GPU fleets for AI developers.
Serverless Inference serves open models through an OpenAI-compatible API billed by token use.
Open source AI gateway routing every model behind one zero-markup OpenAI-compatible endpoint.
Train models on B200s, T4s and inference-optimized infra with one-click deploy to production.
Dedicated Endpoints serves one model on GPU capacity reserved for an organization.
Hosted gateway for routing and governing traffic across hosted and self-hosted AI models.
A unified OpenAI-compatible API and gateway for accessing hundreds of LLMs from many providers.
Conifer Gateway is one OpenAI- and Anthropic-compatible endpoint for more than 200 models.
Baseten Embeddings Inference (BEI) with 2x throughput and lower latency than alternatives.
Pre-optimized APIs for Kimi, DeepSeek, GLM on Baseten Inference Stack.
Secure enterprise portal for multiple large language model platforms with reusable language skills and usage-based pricing.
Baseten Inference Stack for high performance with custom kernels, decoding, caching on optimized infra.
Model Deployments manages immutable model releases with promotion, rollback, logs and analytics.
Developer API for Anthropic's Claude family of frontier language models including Opus, Sonnet, and Haiku.
OpenAI-compatible API proxy with built-in conversational memory supporting 300+ models.
An integrated compute, training, inference, and sandbox stack for enterprises to train and deploy their own AI models.
Cloudflare AI: serverless inference, agents, RAG, and secure runtime primitives on the global edge.
GLM Model API is Z.ai's developer platform for calling its GLM large language models and agent services over an API.
Serverless Inference serves open models through an OpenAI-compatible API billed by token use.
Open source AI gateway routing every model behind one zero-markup OpenAI-compatible endpoint.
An open-source AI gateway and proxy that calls many large language model APIs in the OpenAI format.
Train models on B200s, T4s and inference-optimized infra with one-click deploy to production.
Dedicated Endpoints serves one model on GPU capacity reserved for an organization.
Hosted gateway for routing and governing traffic across hosted and self-hosted AI models.
A unified OpenAI-compatible API and gateway for accessing hundreds of LLMs from many providers.
Conifer Gateway is one OpenAI- and Anthropic-compatible endpoint for more than 200 models.
Adaptive OpenAI-compatible endpoint coordinating open-weight models for chat and agents.
Baseten Embeddings Inference (BEI) with 2x throughput and lower latency than alternatives.
Pre-optimized APIs for Kimi, DeepSeek, GLM on Baseten Inference Stack.
Secure enterprise portal for multiple large language model platforms with reusable language skills and usage-based pricing.
Baseten Inference Stack for high performance with custom kernels, decoding, caching on optimized infra.
Model Deployments manages immutable model releases with promotion, rollback, logs and analytics.
Venice AI API for private, uncensored AI inference.
Developer API for Anthropic's Claude family of frontier language models including Opus, Sonnet, and Haiku.
OpenAI-compatible API proxy with built-in conversational memory supporting 300+ models.
An integrated compute, training, inference, and sandbox stack for enterprises to train and deploy their own AI models.
Cloudflare AI: serverless inference, agents, RAG, and secure runtime primitives on the global edge.
GLM Model API is Z.ai's developer platform for calling its GLM large language models and agent services over an API.