Jotsu

Jotsu Pricing

Simple Usage-Based Pricing

No subscriptions, no hidden fees. Only pay for what you use.

Text Generation Costs
Per-million tokens
Model
InputOutput
claude-3-5-haiku-latest$1.60/M$8.00/M
claude-3-7-sonnet-latest$6.00/M$30.00/M
claude-3-opus-latest$30.00/M$150.00/M
deepseek-r1-distill-qwen-32b$0.994/M$9.762/M
gemma-3-12b-it$0.69/M$1.112/M
gpt-4.1$6.00/M$24.00/M
gpt-4.1-mini$1.60/M$6.40/M
gpt-4.1-nano$0.40/M$1.60/M
gpt-5$2.50/M$0.016/M
gpt-5-mini$0.50/M$4.00/M
gpt-5-nano$0.10/M$0.80/M
llama-2-7b-chat-fp16$1.112/M$13.334/M
llama-3-8b-instruct$0.564/M$1.654/M
llama-3-8b-instruct-awq$0.246/M$0.532/M
llama-3.1-70b-instruct-fp8-fast$0.586/M$4.506/M
llama-3.1-8b-instruct$0.564/M$1.654/M
llama-3.1-8b-instruct-awq$0.246/M$0.532/M
llama-3.1-8b-instruct-fp8$0.304/M$0.574/M
llama-3.1-8b-instruct-fp8-fast$0.09/M$0.768/M
llama-3.2-11b-vision-instruct$0.098/M$1.352/M
llama-3.2-1b-instruct$0.054/M$0.402/M
llama-3.2-3b-instruct$0.102/M$0.67/M
llama-3.3-70b-instruct-fp8-fast$0.586/M$4.506/M
llama-4-scout-17b-16e-instruct$0.54/M$1.70/M
llama-guard-3-8b$0.968/M$0.06/M
mistral-7b-instruct-v0.1$0.22/M$0.38/M
mistral-small-3.1-24b-instruct$0.702/M$1.11/M
qwen2.5-coder-32b-instruct$1.32/M$2.00/M
qwq-32b$1.32/M$2.00/M
Text Embedding Costs
Per-million tokens
Model
Price
bge-base-en-v1.5$0.134/M
bge-large-en-v1.5$0.408/M
bge-m3$0.024/M
bge-small-en-v1.5$0.04/M
Platform Costs
Name
Price
Workflow$0.005 / per run
Platform minimum$5.00 per month