CostUse

AI model prices

Pick a provider, then a model. Rates, source, and check date are on the model page.

Azure

Azure OpenAI Service Global Standard pay-as-you-go token rates for enterprise GPT models.

Baseten

Model APIs and dedicated GPU inference with public per-token list rates.

IBM

IBM watsonx.ai foundation models with public pay-as-you-go per-million token rates.

SiliconFlow

Serverless open-model inference with public per-token rates for DeepSeek, Qwen, GLM, and more.

Parasail

Serverless open-model inference with public per-token rates and cache discounts.

Inception

Diffusion LLMs (Mercury) with public per-token API rates for high-throughput generation.

Mercury 2

Mercury 2

$0.25 in · $0.75 out per 1M tokens

Jina AI

Multimodal embeddings and search foundation APIs with prepaid token packages.