DeepSeek V3.1 Terminus

Released
2025-09-22
Last refreshed
2026-06-29
Status
Researched 132d ago
Open weightsCommercial use: permittedRAGLong contextClassificationJSON / Tool use
DeepSeek releases · 7 in the last 12 monthsChangelog →
Specifications
Family
DeepSeek
Released
2025-09-22
Context
164k
Parameters
671B total, 37B active (MoE)
Architecture
Decoder Only
Specialization
general
Openness
Open weights
License
DeepSeek LicenseCommercial use: permitted
Weights
Unknown
Code
Unknown
Created by
DeepSeek

Advancing artificial general intelligence (AGI).

Hangzhou, Zhejiang, China
Founded 2023
Website
Pricing
Output / 1M
$0.790
Input / 1M
$0.210

Cheapest of 4 routes · OpenRouter

Providers(4)
NVIDIA NIMOpenRouterVercel AI GatewayNovita AI
View 4 provider routes
Links
Website

About

DeepSeek: DeepSeek V3.1 Terminus available via OpenRouter. Pricing: $0.21/1M input, $0.79/1M output.

Provider price ladder

Compare all 4

Compare API pricing across 4 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MCacheRoute
OpenRouter$0.210$0.790-
Serverless
Novita AI$0.270$1.00-
Serverless
Vercel AI Gateway$0.270$1.00read $0.135
Serverless
NVIDIA NIM---
ServerlessPartial

Available via routers & gateways(1)

NVIDIA LLM Router Blueprint

Router

NVIDIA's open-source AI blueprint for LLM routing that selects the optimal model per prompt via intent classification or neural auto-routing; being deprecated 2026-06-20.

Free OSSNVIDIA NIM

Capabilities

Structured Outputs

Benchmark peer barsfor RAG

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.