LLM price calculator
Enter a typical request and daily volume to compare what each per-token model would cost. Prices are read from the live catalog and match the Models page.
| Model | Per request | Per month (30 days) |
|---|---|---|
gemini-3.8-flash-plus-free | $0.00 | $0.00 |
grok-4.7-plus-free | $0.00 | $0.00 |
muse-spark-plus-free | $0.00 | $0.00 |
jev | $0.000084 | $0.252 |
gemini-2.5-flash-lite | $0.0002 | $0.6 |
mimo-v2.5 | $0.00021 | $0.63 |
mimo-v2.5-plus | $0.00021 | $0.63 |
mimo-v2.6-flash | $0.00021 | $0.63 |
deepseek-v3.2 | $0.000213 | $0.639 |
deepseek-v3.2-thinking | $0.000213 | $0.639 |
mistral-nemo | $0.00022 | $0.66 |
gemma-4-31b-it | $0.00024 | $0.72 |
gemma-4-26b-a4b-it | $0.000263 | $0.788 |
glm-5.3-flash | $0.000275 | $0.825 |
muse-spark-1.2-contributor | $0.0003 | $0.9 |
muse-spark-1.3-contributor | $0.0003 | $0.9 |
minimax-m2.1 | $0.00036 | $1.08 |
minimax-m2.1-thinking | $0.00036 | $1.08 |
minimax-m2.5 | $0.00036 | $1.08 |
minimax-m2.5-thinking | $0.00036 | $1.08 |
qwen3.8-omni-flash | $0.000535 | $1.6 |
nemotron-3.5-super-vl | $0.00055 | $1.65 |
qwen3.8-flash | $0.000555 | $1.67 |
hy3 | $0.0006 | $1.8 |
minimax-m2.7 | $0.0006 | $1.8 |
How the estimate works
Cost per request is input tokens times the input price plus output tokens times the output price. A month is 30 days at your daily volume. Cached input discounts are not included, so chat workloads that reuse context often cost less. Free models, models billed per request and models with tiered pricing are not included; see the free AI API guide and the models page.