DeepSeek

DeepSeek R1

Name: DeepSeek R1
Author: DeepSeek

DeepSeek R1 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 May 28, 2025; the current pick is DeepSeek V4.1 Flash 1017. Public-board scores are linked to the publisher; vendor-only figures stay in the watch-out, not on the board.

DeepSeek R1 is the January 2025 open-weight (MIT) reasoning model — now open weights only, with no first-party API.

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

AI model specification details
Specification	DeepSeek R1
Provider	DeepSeek
Tier	Balanced
Context window	128K
Max output	Not verifiedUnverified
Input / 1M tokens	Not verifiedUnverified
Output / 1M tokens	Not verifiedUnverified
Weights	Open
Parameters	671B total / 37B active (MoE)
Reasoning levels	Not verifiedUnverified
Modalities	text
License	MIT
Released	January 20, 2025

Pricing tiers: No current first-party API. The original deepseek-reasoner alias moved to R1-0528 on May 28, 2025 and V3.1 on August 21, 2025, before the alias retired July 24, 2026 at 15:59 UTC. Historical launch tariffs are not verified here; hosts charge their own rates for the MIT weights.

Best for

Harder reasoning on a budget
Open-weight deployments
Agentic coding

Watch out

Original January R1 MIT weights remain available. The first-party alias moved to R1-0528 on May 28, 2025 and later to other models before its July 24, 2026 retirement. Pin the exact checkpoint; no current first-party tariff, hard native output cap or selectable hosted effort menu is established for this original profile. Distilled Qwen/Llama variants have additional base-model licence terms.

History

DeepSeek R1 timeline

Release and status events for this model that passed two-source verification — dated, sourced, and linked.

DeepSeek deepseek-chat / deepseek-reasoner retiredStatus updateJuly 24, 2026
DeepSeek fully retires the deepseek-chat and deepseek-reasoner aliases (15:59 UTC); R1 and V3.1 are no longer served by the first-party API.
DeepSeek — deepseek-chat / deepseek-reasoner retirement notice

Source receipts

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

Whole-record check: current publisher specifications, licence, access or tariff (accessed 2026-10-25)
Whole-record check: current publisher specifications, licence, access or tariff (accessed 2026-10-25)
Whole-record check: current publisher specifications, licence, access or tariff (accessed 2026-10-25)
Whole-record check: current publisher specifications, licence, access or tariff (accessed 2026-10-25)
AI/TLDR — DeepSeek R1 (accessed 2026-08-29)
PricePerToken — DeepSeek R1 (accessed 2026-08-29)

Common questions

DeepSeek R1

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

What is DeepSeek R1's context window?

DeepSeek R1 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 R1 best for?

DeepSeek R1 is a balanced tier from DeepSeek. It suits harder reasoning on a budget, open-weight deployments, agentic coding. Original January R1 MIT weights remain available. The first-party alias moved to R1-0528 on May 28, 2025 and later to other models before its July 24, 2026 retirement. Pin the exact checkpoint; no current first-party tariff, hard native output cap or selectable hosted effort menu is established for this original profile. Distilled Qwen/Llama variants have additional base-model licence terms.

Can I self-host DeepSeek R1?

DeepSeek R1 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 catalog Benchmark library