Compare model prices
Input, output, cached and batch prices, every route and a month of tokens, side by side.
DeepSeek V4 Pro 0423DeepSeek V4.1 FlashA month of tokens
100M input and 20M output tokens, list price. Use your own numbers.
Side by side
| DeepSeek V4 Pro 0423 | DeepSeek V4.1 Flash | |
|---|---|---|
| Input per 1M | $0.801 | $0.15 |
| Output per 1M | $1.6 | $0.6 |
| Cached input | $0.067 | $0.003 |
| Batch in / out | n/a | $0.112 / $0.336 |
| Blended (3:1) | $1 | $0.262 |
| Context | 1M | 1M |
| Routes | 15 | 26 |
| Released | Apr 24, 2026 | Sep 10, 2026 |
| Leadersboard score | n/a | 3 (#33) |
On the price map
Size: context window, 8K to 2MEqual blended cost (3:1) 245 models, lower left is cheaper
Every route
DeepSeek V4 Pro 0423
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
| StreamLake fp8 · cached $0.067 | $0.801 | $1.6 | $0.801 / $1.6Same as list | $0.067 | Same as list |
| Baidu fp8 · cached $0.067 | $0.803 | $1.61 | $0.803 / $1.61Same as list | $0.067 | Same as list |
| GMICloud fp8 · cached $0.08 | $0.957 | $1.91 | $0.957 / $1.91+19% vs list | $0.08 | +19% vs list |
 DigitalOceanDefault region · cached $0.209 | $1.04 | $2.09 | $1.04 / $2.09+30% vs list | $0.209 | +30% vs list |
 Cloudflare Workers AIDefault region · cached $0.2 | $1.15 | $2.55 | $1.15 / $2.55+50% vs list | $0.2 | +50% vs list |
 DeepInfrafp8 · cached $0.1 | $1.3 | $2.6 | $1.3 / $2.6+62% vs list | $0.1 | +62% vs list |
 Qwen (Alibaba)fp8 · cached $0.118 | $1.42 | $2.83 | $1.42 / $2.83+77% vs list | $0.118 | +77% vs list |
 SiliconFlowfp8 · cached $0.135 | $1.5 | $3.14 | $1.5 / $3.14+91% vs list | $0.135 | +91% vs list |
 Novita AIfp8 · cached $0.135 | $1.6 | $3.2 | $1.6 / $3.2+100% vs list | $0.135 | +100% vs list |
 VeniceDefault region · cached $0.33 | $1.65 | $3.3 | $1.65 / $3.3+106% vs list | $0.33 | +106% vs list |
| AtlasCloud fp4 · cached $0.13 | $1.68 | $3.38 | $1.68 / $3.38+110% vs list | $0.13 | +110% vs list |
 Basetenfp4 · cached $0.145 | $1.74 | $3.48 | $1.74 / $3.48+117% vs list | $0.145 | +117% vs list |
| NextBit fp8 · cached $0.145 | $1.74 | $3.48 | $1.74 / $3.48+117% vs list | $0.145 | +117% vs list |
 Parasailfp8 · cached $0.1 | $1.74 | $3.48 | $1.74 / $3.48+117% vs list | $0.1 | +117% vs list |
 Azure AI Foundryus · cached $0.16 | $1.91 | $3.83 | $1.91 / $3.83+139% vs list | $0.16 | +139% vs list |
DeepSeek V4.1 Flash
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
| Morph Default region, cheapest · cached $0.0015 | $0.075 | $0.3 | $0.075 / $0.3-50% vs list | $0.0015 | -50% vs list |
| DekaLLM Default region · cached $0.01 | $0.04 | $0.49 | $0.04 / $0.49-42% vs list | $0.01 | -42% vs list |
| OpenInference fp4 · cached $0.01 | $0.1 | $0.5 | $0.1 / $0.5-24% vs list | $0.01 | -24% vs list |
| Relace Default region · cached $0.01 | $0.1 | $0.5 | $0.1 / $0.5-24% vs list | $0.01 | -24% vs list |
| DeepInfra fp8 · cached $0.0042 | $0.14 | $0.42 | $0.14 / $0.42-20% vs list | $0.0042 | -20% vs list |
| Wafer Default region · cached $0.06 | $0.099 | $0.6 | $0.099 / $0.6-15% vs list | $0.06 | -15% vs list |
| DeepSeek API The lab's own API · cached $0.003 | $0.15 | $0.6 | $0.15 / $0.6List price | $0.003 | List price |
| Sail Research fp4 · cached $0.01 | $0.13 | $0.75 | $0.13 / $0.75+9% vs list | $0.01 | +9% vs list |
| StreamLake fp8 · cached $0.0033 | $0.165 | $0.66 | $0.165 / $0.66+10% vs list | $0.0033 | +10% vs list |
 CoreWeavefp8 · cached $0.03 | $0.2 | $0.65 | $0.2 / $0.65+19% vs list | $0.03 | +19% vs list |
 Fireworks AIDefault region · cached $0.007 | $0.22 | $0.66 | $0.22 / $0.66+26% vs list | $0.007 | +26% vs list |
| GMICloud fp8 · cached $0.0045 | $0.225 | $0.9 | $0.225 / $0.9+50% vs list | $0.0045 | +50% vs list |
| Krea fp8 · cached $0.006 | $0.225 | $0.9 | $0.225 / $0.9+50% vs list | $0.006 | +50% vs list |
| Phala Default region · cached $0.0055 | $0.276 | $1.1 | $0.276 / $1.1+84% vs list | $0.0055 | +84% vs list |
| Novita AI fp8 · cached $0.0057 | $0.285 | $1.14 | $0.285 / $1.14+90% vs list | $0.0057 | +90% vs list |
| AtlasCloud fp8 · cached $0.03 | $0.3 | $1.2 | $0.3 / $1.2+100% vs list | $0.03 | +100% vs list |
| Baseten fp8 · cached $0.03 | $0.3 | $1.2 | $0.3 / $1.2+100% vs list | $0.03 | +100% vs list |
| DigitalOcean Default region · cached $0.006 | $0.3 | $1.2 | $0.3 / $1.2+100% vs list | $0.006 | +100% vs list |
| Makora fp8 · cached $0.006 | $0.3 | $1.2 | $0.3 / $1.2+100% vs list | $0.006 | +100% vs list |
 ModalDefault region · cached $0.03 | $0.3 | $1.2 | $0.3 / $1.2+100% vs list | $0.03 | +100% vs list |
| NextBit fp8 · cached $0.006 | $0.3 | $1.2 | $0.3 / $1.2+100% vs list | $0.006 | +100% vs list |
| Parasail fp8 · cached $0.006 | $0.3 | $1.2 | $0.3 / $1.2+100% vs list | $0.006 | +100% vs list |
| Qwen (Alibaba) Default region · cached $0.03 | $0.3 | $1.2 | $0.3 / $1.2+100% vs list | $0.03 | +100% vs list |
| SiliconFlow fp8 · cached $0.006 | $0.3 | $1.2 | $0.3 / $1.2+100% vs list | $0.006 | +100% vs list |
 Together AIDefault region · cached $0.006 | $0.3 | $1.2 | $0.3 / $1.2+100% vs list | $0.006 | +100% vs list |
| Venice fp8 · cached $0.0075 | $0.375 | $1.5 | $0.375 / $1.5+150% vs list | $0.0075 | +150% vs list |
Sources: OpenRouter's public model catalog and each provider's own pricing page, read every morning at 05:00 UTC; gateway fees re-read every Monday. List prices: your contract may differ. Logos via logo.dev; trademarks belong to their owners.