All 101 models, priced for your workload
Sorted by what each model would cost you per month. Tick up to four to compare them side by side, or click a model for its full cost breakdown.
| Compare | Cached /1M | ||||||||
|---|---|---|---|---|---|---|---|---|---|
 Qwen3.7 Flash | $0.030 | $0.006 | $0.130 | 1M | 144.1 | 79.6 | — | $31.74 | |
 GLM 5.3 FlashOpenVolatile | $0.005 | $0.005 | $0.199 | 1M | 153.1 | 90.5 | 69.3 | $32.85 | |
| Qwen3.5-Flash | $0.065 | $0.007 | $0.260 | 1M | — | 79.6 | — | $64.08 | |
 DeepSeek V4 Flash 0423OpenVolatile | $0.091 | $0.018 | $0.182 | 1M | — | — | — | $64.38 | |
| GLM 4.7 FlashOpen | $0.061 | $0.006 | $0.400 | 200K | — | — | 84.6 | $83.40 | |
 Gemma 4 26B A4B OpenVolatile | $0.090 | $0.050 | $0.300 | 262K | 141.9 | 67.0 | — | $89.40 | |
| Qwen3.5-9BOpen | $0.170 | $0.017 | $0.250 | 262K | 139.3 | 75.0 | 58.8 | $102.78 | |
 Claude Haiku 5.5 | $0.100 | $0.010 | $0.500 | 1M | 159.3 | 89.8 | 176.3 | $113.40 | |
 GPT-6 Luna | $0.100 | $0.010 | $0.500 | 1M | 156.8 | 90.9 | 91.5 | $113.40 | |
| GPT-6 Luna Pro | $0.100 | $0.010 | $0.500 | 1M | — | — | — | $113.40 | |
| Qwen3.8 FlashOpen | $0.150 | $0.016 | $0.470 | 1M | — | — | — | $128.34 | |
| Qwen3.8 Omni Flash | $0.150 | $0.016 | $0.470 | 1M | — | — | — | $128.34 | |
| Gemma 4 31BOpen | $0.200 | $0.020 | $0.400 | 262K | 143.0 | 70.5 | — | $136.80 | |
| DeepSeek V4.1 Flash 1017Open | $0.150 | $0.003 | $0.600 | 1M | — | — | — | $144.72 | |
 Mistral Small 4Open | $0.150 | $0.015 | $0.600 | 262K | — | — | 185.6 | $147.60 | |
| DeepSeek V4 Flash Vision ExpOpen | $0.216 | $0.007 | $0.647 | 1M | — | — | — | $176.49 | |
| Qwen3 Coder NextOpen | $0.120 | $0.070 | $0.800 | 262K | — | — | — | $180.00 | |
| Qwen3.6 35B A3BOpen | $0.100 | $0.050 | $0.950 | 262K | 143.7 | 83.1 | — | $190.50 | |
| Qwen3.5-35B-A3BOpenVolatile | $0.140 | $0.050 | $1.00 | 262K | 142.5 | 81.2 | — | $212.40 | |
| Qwen3.6 Flash | $0.188 | $0.019 | $1.13 | 1M | 142.9 | 81.0 | — | $240.99 | |
| GPT-5.6 Luna | $0.200 | $0.020 | $1.20 | 1M | 156.5 | 92.5 | 129.3 | $256.80 | |
| GPT-5.6 Luna Pro | $0.200 | $0.020 | $1.20 | 1M | — | — | — | $256.80 | |
| GLM 5.3OpenVolatile | $0.079 | $0.078 | $1.40 | 1M | 156.0 | 91.5 | — | $257.16 | |
| GPT-5.4 Nano | $0.200 | $0.020 | $1.25 | 400K | 146.0 | 74.3 | — | $264.30 | |
| DeepSeek V4.1 FlashOpenVolatile | $0.300 | $0.006 | $1.20 | 1M | 155.9 | 90.0 | — | $289.44 |
How the monthly cost is calculated
For each model we take your input tokens per request, split them into the share served from the prompt cache and the share billed at the full input rate, add your output tokens at the output rate, and multiply by your requests per day over a 30-day month. Batch pricing uses each provider's own batch rates, which most providers set at about half the standard price for work that can wait up to a day.
Prices come from OpenRouter and refresh daily. Models tagged volatile changed their listed price on five or more days in the last month, usually because the cheapest host changed, so check the provider's page before relying on them. See our methodology for sources and the guides for ways to bring the bill down.