Compare model prices
Input, output, cached and batch prices, every route and a month of tokens, side by side.
A month of tokens
DeepSeek V4 Flash 0731$8.45
100M input and 20M output tokens, list price. Use your own numbers.
Side by side
| DeepSeek V4 Flash 0731 | |
|---|---|
| Input per 1M | $0.053 |
| Output per 1M | $0.158 |
| Cached input | $0.0017 |
| Batch in / out | n/a |
| Blended (3:1) | $0.079 |
| Context | 1.31M |
| Routes | 29 |
| Released | Jul 31, 2026 |
| Leadersboard score | n/a |
On the price map
Size: context window, 8K to 2MEqual blended cost (3:1) 243 models, lower left is cheaper
Every route
DeepSeek V4 Flash 0731
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
| StreamLake fp8 · cached $0.0017 | $0.053 | $0.158 | $0.053 / $0.158Same as list | $0.0017 | Same as list |
fp8 · cached $0.015 | $0.06 | $0.18 | $0.06 / $0.18+14% vs list | $0.015 | +14% vs list |
| Relace fp4 · cached $0.016 | $0.04 | $0.32 | $0.04 / $0.32+39% vs list | $0.016 | +39% vs list |
| Makora Default region · cached $0.02 | $0.09 | $0.195 | $0.09 / $0.195+47% vs list | $0.02 | +47% vs list |
| Wafer fast · cached $0.02 | $0.08 | $0.35 | $0.08 / $0.35+86% vs list | $0.02 | +86% vs list |
Default region · cached $0.024 | $0.119 | $0.238 | $0.119 / $0.238+88% vs list | $0.024 | +88% vs list |
fp8 · cached $0.028 | $0.13 | $0.26 | $0.13 / $0.26+105% vs list | $0.028 | +105% vs list |
| Sail Research fp4 · cached $0.023 | $0.038 | $0.55 | $0.038 / $0.55+110% vs list | $0.023 | +110% vs list |
fp8 · cached $0.07 | $0.13 | $0.28 | $0.13 / $0.28+111% vs list | $0.07 | +111% vs list |
Default region · cached $0.07 | $0.14 | $0.28 | $0.14 / $0.28+121% vs list | $0.07 | +121% vs list |
fp8 | $0.14 | $0.28 | $0.14 / $0.28+121% vs list | n/a | +121% vs list |
fp8 · cached $0.05 | $0.14 | $0.28 | $0.14 / $0.28+121% vs list | $0.05 | +121% vs list |
Default region · cached $0.03 | $0.14 | $0.28 | $0.14 / $0.28+121% vs list | $0.03 | +121% vs list |
| Reka fp4 · cached $0.0056 | $0.088 | $0.528 | $0.088 / $0.528+150% vs list | $0.0056 | +150% vs list |
| Morph Default region · cached $0.036 | $0.142 | $0.4 | $0.142 / $0.4+161% vs list | $0.036 | +161% vs list |
Default region · cached $0.035 | $0.175 | $0.35 | $0.175 / $0.35+176% vs list | $0.035 | +176% vs list |
| Inceptron fp4 · cached $0.06 | $0.091 | $0.613 | $0.091 / $0.613+179% vs list | $0.06 | +179% vs list |
| OpenInference fp8 · cached $0.03 | $0.14 | $0.7 | $0.14 / $0.7+254% vs list | $0.03 | +254% vs list |
| Mancer 2 fp8 | $0.2 | $0.6 | $0.2 / $0.6+279% vs list | n/a | +279% vs list |
Default region · cached $0.007 | $0.22 | $0.66 | $0.22 / $0.66+317% vs list | $0.007 | +317% vs list |
fp8 · cached $0.028 | $0.22 | $0.66 | $0.22 / $0.66+317% vs list | $0.028 | +317% vs list |
| GMICloud fp8 · cached $0.0091 | $0.286 | $0.858 | $0.286 / $0.858+442% vs list | $0.0091 | +442% vs list |
| NextBit fp8 · cached $0.012 | $0.352 | $1.06 | $0.352 / $1.06+567% vs list | $0.012 | +567% vs list |
Default region · cached $0.035 | $0.352 | $1.06 | $0.352 / $1.06+567% vs list | $0.035 | +567% vs list |
fp8 · cached $0.026 | $0.409 | $1.23 | $0.409 / $1.23+675% vs list | $0.026 | +675% vs list |
| AtlasCloud fp4 · cached $0.028 | $0.44 | $1.32 | $0.44 / $1.32+733% vs list | $0.028 | +733% vs list |
| Baidu fp8 · cached $0.014 | $0.44 | $1.32 | $0.44 / $1.32+733% vs list | $0.014 | +733% vs list |
Default region · cached $0.014 | $0.44 | $1.32 | $0.44 / $1.32+733% vs list | $0.014 | +733% vs list |
| Phala Default region · cached $0.028 | $0.44 | $1.32 | $0.44 / $1.32+733% vs list | $0.028 | +733% vs list |
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.