CostUse

AI model token cost calculators

Start with a provider or open a model directly. Each page combines its published rates with workload controls, budget tables, and the original pricing source.

Together AI

Open-model serverless inference, image, audio, and dedicated GPU endpoints.

Perplexity

Search-grounded Sonar models and agent tools with token plus request fees.

Cerebras

Wafer-scale inference with extreme tokens-per-second on open models.

AI21

Jamba hybrid models for long-context enterprise chat and document work.

Voyage AI

Specialized embedding and rerank models priced per million tokens.

DeepInfra

Low-cost serverless inference for open models with transparent per-token rates.

Moonshot AI

Kimi models with million-token context and first-party cache-aware pricing.

Z.AI

GLM flagship models from Z.AI with first-party cache-aware token pricing.

Novita AI

Open-model serverless API with competitive per-token rates across Llama, Qwen, and DeepSeek.

Nebius

European AI cloud Token Factory with transparent per-token open-model inference.