Catalog

Models

Every model routable through your Tokener endpoint, with context limits and public pricing per million tokens. Prices are what you pay, billed against prepaid credits. One balance across every provider.

Get an API key
ModelCategoryContextInput /1MCache /1MOutput /1MStatus
claude-opus-5AnthropicReasoning1M$5.00$1.00$25.00Available
claude-sonnet-5AnthropicReasoning1M$2.00$0.50$10.00Available
deepseek-v4-flashDeepseekReasoning1M$0.44$0.014$1.32Available
deepseek-v4-proDeepseekReasoning1M$1.32$0.044$3.96Available
gpt-5.6-lunaOpenAIReasoning1M$0.20$0.02$1.20Available
gpt-5.6-solOpenAIReasoning1M$4.00$0.40$20.00Available
gpt-5.6-terraOpenAIReasoning1M$2.00$0.20$12.00Available
kimi-k3KimiReasoning1M$3.00$0.30$15.00Available
8 models · pricing per 1M tokens · billed against prepaid credits

Cache prices are for reads of previously cached input; embedding models are priced on input only. Context is the largest input plus output window the model accepts.

Start with one endpoint

Create an account, add a key, send your first request in minutes.