Ways to buy 8
| Way to buy | Input | Output | In / out per 1M | Cached | Vs cheapest |
|---|---|---|---|---|---|
 DeepInfrafp4 · cached $0.13 | $0.25 | $0.95 | $0.25 / $0.95Cheapest | $0.13 | Cheapest |
 Novita AIfp8 · cached $0.135 | $0.27 | $1 | $0.27 / $1+6% vs cheapest | $0.135 | +6% vs cheapest |
 SiliconFlowfp8 | $0.27 | $1 | $0.27 / $1+6% vs cheapest | n/a | +6% vs cheapest |
| AtlasCloud fp8 · cached $0.13 | $0.3 | $0.95 | $0.3 / $0.95+9% vs cheapest | $0.13 | +9% vs cheapest |
 CoreWeavefp8 · cached $0.55 | $0.55 | $1.65 | $0.55 / $1.65+94% vs cheapest | $0.55 | +94% vs cheapest |
 SambaNovafp8 | $0.65 | $1.5 | $0.65 / $1.5+103% vs cheapest | n/a | +103% vs cheapest |
 Google Vertex AIus-west2 | $0.6 | $1.7 | $0.6 / $1.7+106% vs cheapest | n/a | +106% vs cheapest |
| Mara Default region | $0.6 | $1.7 | $0.6 / $1.7+106% vs cheapest | n/a | +106% vs cheapest |
USD per 1M tokens. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $44.00 direct.
Helicone$44.00+0%
Kong AI Gateway$44.00+0%
LiteLLM$44.00+0%
Vercel AI Gateway$44.00+0%
Cloudflare AI Gateway$46.20+5%
Requesty$46.20+5%
Eden AI$46.42+5.5%
OpenRouter$46.42+5.5%
No published token fee: Martian Gateway, Portkey, TrueFoundry AI Gateway.
Related models
| In / out per 1M | Cheapest route | ||||||
|---|---|---|---|---|---|---|---|
 DeepSeek V4.1 FlashDeepSeek · 1MCheapest: $0.1 on Relace | $0.15 | $0.6 | $0.15 / $0.6 | $0.262 | 1M | $0.1 on Relace | · |
| DeepSeek V4 Flash Vision Exp DeepSeek · 1M | $0.216 | $0.647 | $0.216 / $0.647 | $0.323 | 1M | on DeepInfra (fp8) | · |
| DeepSeek V4 Pro 0813 DeepSeek · 1MCheapest: $0.693 on StreamLake | $0.66 | $1.98 | $0.66 / $1.98 | $0.99 | 1M | $0.693 on StreamLake | · |
| DeepSeek V4 Flash 0731 DeepSeek · 1.31M | $0.053 | $0.158 | $0.053 / $0.158 | $0.079 | 1.31M | on StreamLake (fp8) | · |
 GLM 4.6Z.ai · 205K | $0.43 | $1.75 | $0.43 / $1.75 | $0.76 | 205K | on Venice (fp4) | · |
 Kimi K2.5Moonshot AI · 262K | $0.45 | $2.25 | $0.45 / $2.25 | $0.9 | 262K | on SiliconFlow (int4) | · |
 Gemini 3.1 Flash LiteGoogle · 1MCheapest: $0.281 on Google Vertex AI (global-flex) | $0.25 | $1.5 | $0.25 / $1.5 | $0.563 | 1M | $0.281 on Google Vertex AI (global-flex) | · |
| Gemini 3.1 Flash Lite Preview Google · 1MCheapest: $0.281 on Google Gemini API (flex) | $0.25 | $1.5 | $0.25 / $1.5 | $0.563 | 1M | $0.281 on Google Gemini API (flex) | · |
About DeepSeek V3.1
DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates.
Takes text in and returns text. First listed Sep 23, 2026. Up to 33K output tokens. Blended price $0.425 per 1M tokens at 3 input to 1 output. Model id deepseek-chat-v3-1.
Price history
No list-price history: this model is sold by hosts rather than its lab.
Across fru.devCompany profile
Questions
How much does DeepSeek V3.1 cost?
$0.25 per million input tokens and $0.95 per million output tokens, with cached input at $0.13.
What is the context window of DeepSeek V3.1?
164K tokens, with up to 33K tokens of output.
Where is DeepSeek V3.1 cheapest?
Of 8 routes tracked, DeepInfra is cheapest at $0.25 input and $0.95 output per million tokens.
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.