token.app › DeepSeek › DeepSeek V3.1

DeepSeek V3.1 pricing & benchmarks

DeepSeek V3.1 is available from DeepSeek at $0.250 per million input tokens and $0.950 per million output tokens ($0.425 blended at 3:1). It accepts up to 163,840 tokens of context. DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...

Pricing
Per million tokens · OpenRouter
Input$0.250
Output$0.950
Blended (3:1)$0.425
Specification
deepseek/deepseek-chat-v3.1
Context window164K
Max output33K
ReleasedAug 2025
LicenceOpen weights
Modalitiesin:text, out:text
No independently-run benchmark scores are published for DeepSeek V3.1 yet. We show nothing rather than reprinting an unverified figure.
Where to run DeepSeek V3.1
8 hosts · 2.1× between cheapest and dearest. Blended at 3:1. ⚠ marks an option serving less context than the best available, or re-pricing above a prompt-length threshold. Bracketed labels are the provider's own service tier or region.
HostBlended $/1MIn / OutContextWeightsUptime 24h
DeepInfra $0.425 $0.250 / $0.950 164K fp4 99.9%
Novita
⚠ 131K context, not 164K
 $0.453 $0.270 / $1.00 131K fp8 100.0%
SiliconFlow $0.453 $0.270 / $1.00 164K fp8 97.5%
AtlasCloud
⚠ 131K context, not 164K
 $0.462 $0.300 / $0.950 131K fp8 99.9%
CoreWeave $0.825 $0.550 / $1.65 161K fp8 100.0%
SambaNova
⚠ 131K context, not 164K
 $0.863 $0.650 / $1.50 131K fp8 99.5%
Google (us-west2) $0.875 $0.600 / $1.70 164K — 97.4%
Mara
⚠ 131K context, not 164K
 $0.875 $0.600 / $1.70 131K — 76.9%
Host prices and uptime from OpenRouter, synced 2026-08-08. Lower-precision weights (fp4, fp8) can cost less and score worse than the same model at bf16 — the score above is not host-specific.
Compare DeepSeek V3.1
DeepSeek V3.1 vs Qwen3.8 Max DeepSeek V3.1 vs Claude Opus 5 DeepSeek V3.1 vs Gemini 3.6 Flash DeepSeek V3.1 vs Kimi K3 DeepSeek V3.1 vs GPT-5.6 Luna DeepSeek V3.1 vs GPT-5.6 Terra DeepSeek V3.1 vs GPT-5.6 Sol DeepSeek V3.1 vs Grok 4.5
FAQ
How much does DeepSeek V3.1 cost?
DeepSeek V3.1 costs $0.250 per million input tokens and $0.950 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $0.425 per million tokens.
What is DeepSeek V3.1's context window?
DeepSeek V3.1 accepts up to 163,840 tokens of context, and can generate up to 32,768 output tokens.