API providers
Where to run frontier models — pricing, throughput, and full model catalogs.
9 of 9 providers
Anthropic
Anthropic hosts 5 active AI models, with input pricing from $1.00 per 1M tokens, averaging 50 tok/s output throughput, with up to 1.0M context window. Compare Anthropic's API pricing, latency, and feature support against other LLM providers.
Amazon Bedrock
Bedrock hosts 0 active AI models. Compare Bedrock's API pricing, latency, and feature support against other LLM providers.
DeepInfra
DeepInfra hosts 12 active AI models, with input pricing from $0.06 per 1M tokens, averaging 69 tok/s output throughput, with up to 1.0M context window. Compare DeepInfra's API pricing, latency, and feature support against other LLM providers.
Fal
Fal hosts 29 active AI models, with up to 8K context window. Compare Fal's API pricing, latency, and feature support against other LLM providers.
Google hosts 14 active AI models, with input pricing from $0.25 per 1M tokens, averaging 88 tok/s output throughput, with up to 1.0M context window. Compare Google's API pricing, latency, and feature support against other LLM providers.
Novita
Novita hosts 20 active AI models, with input pricing from $0.08 per 1M tokens, averaging 53 tok/s output throughput, with up to 262K context window. Compare Novita's API pricing, latency, and feature support against other LLM providers.
OpenAI
OpenAI hosts 34 active AI models, with input pricing from $0.10 per 1M tokens, averaging 103 tok/s output throughput, with up to 1.1M context window. Compare OpenAI's API pricing, latency, and feature support against other LLM providers.
Replicate
Replicate hosts 35 active AI models, with up to 10K context window. Compare Replicate's API pricing, latency, and feature support against other LLM providers.
Xai
xAI hosts 10 active AI models, with input pricing from $0.20 per 1M tokens, averaging 90 tok/s output throughput, with up to 2.0M context window. Compare xAI's API pricing, latency, and feature support against other LLM providers.