Skip to main content
AI Choice Engine

DeepSeek

DeepSeek V3.1

DeepSeek V3.1 is a DeepSeek model with 128K context, Not verified in / Not verified out per million tokens, last verified October 25, 2026. Open weights: yes. Status: Legacy since September 22, 2025; the current pick is DeepSeek V4.1 Flash. Public-board scores are linked to the publisher; vendor-only figures stay in the watch-out, not on the board.

DeepSeek V3.1 is a legacy open-weight (MIT) 671B/37B MoE with a 128K context — superseded by V3.1-Terminus, V3.2 and then V4.

Recorded profile verification October 25, 2026Individual provider fields may change

AI model specification details
SpecificationDeepSeek V3.1
ProviderDeepSeek
TierBudget
Context window128K
Max outputNot verifiedUnverified
Input / 1M tokensNot verifiedUnverified
Output / 1M tokensNot verifiedUnverified
WeightsOpen
Parameters671B total / 37B active (MoE)
Reasoning levelsNot verifiedUnverified
Modalitiestext
LicenseMIT
ReleasedAugust 21, 2025

Pricing tiers: No current first-party API or verified third-party tariff. deepseek-chat moved to V3.1-Terminus on September 22, 2025; that alias later retired July 24, 2026. MIT weights remain for self-hosting or separately priced hosts. The original checkpoint's hard output cap and selectable hosted effort menu remain unverified. Current Flash/Pro API prices do not price the original V3.1 checkpoint.

Best for

  • Cost-sensitive hosted agents
  • High-volume coding assist
  • Open-weight deployments

Watch out

Legacy: DeepSeek's first-party alias moved to V3.1-Terminus on September 22, 2025. Pin the exact V3.1 checkpoint; current hosted rates depend on provider. The original card supports thinking/non-thinking templates, not a verified selectable low/high/max menu. Self-hosting memory depends on quantization, offloading and hardware. The current first-party pricing table lists Flash-1017 and Pro-0813 only; absence of a third-party tariff here means unknown, not free.

Source receipts

Catalog figures for this model were checked against the following sources.

Common questions

DeepSeek V3.1

Answered from the verified figures on this page rather than general guidance.

What is DeepSeek V3.1's context window?
DeepSeek V3.1 accepts about 128K tokens of context. That only matters if you routinely send very long documents, large codebases, or multi-turn histories that approach that limit.
What is DeepSeek V3.1 best for?
DeepSeek V3.1 is a budget tier from DeepSeek. It suits cost-sensitive hosted agents, high-volume coding assist, open-weight deployments. Legacy: DeepSeek's first-party alias moved to V3.1-Terminus on September 22, 2025. Pin the exact V3.1 checkpoint; current hosted rates depend on provider. The original card supports thinking/non-thinking templates, not a verified selectable low/high/max menu. Self-hosting memory depends on quantization, offloading and hardware. The current first-party pricing table lists Flash-1017 and Pro-0813 only; absence of a third-party tariff here means unknown, not free.
Can I self-host DeepSeek V3.1?
DeepSeek V3.1 publishes open weights, but self-hosting depends on the licence, hardware footprint, quantisation quality, and serving stack. A hosted API is often cheaper until you have measured throughput and concurrency on your own hardware.
Model comparison catalogBenchmark library