DeepSeek

DeepSeek-R1-0528

Generally availableOpen weights164K contextReasoning

Summary

DeepSeek-R1-0528 is an open-weight language model from DeepSeek, released on 28 May 2025. It accepts text and generates text, with a 164K-token context window and up to 33K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.50 per million input tokens and $2.15 per million output tokens (DeepInfra), across 5 providers we track.

DeepSeek reasoning model for multi-step analysis, math, coding, and tools

Last verified 18 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperDeepSeek
Release date28 May 2025 [models.dev]
StatusGenerally available [models.dev]
WeightsOpen weights [Hugging Face]
Licensemit [Hugging Face]
Parameters685B [Hugging Face]
Context window164K (163,840 tokens) [models.dev]
Max output33K tokens [models.dev]
Knowledge cutoffMay 2025 [models.dev]
InputText [models.dev]
OutputText [models.dev]
Reasoning modeYes [models.dev]
Tool callingYes [models.dev]
Structured outputYes [models.dev]
Hugging Facedeepseek-ai/DeepSeek-R1-0528 [Hugging Face]

DeepSeek-R1-0528 API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
DeepInfra
deepseek-ai/DeepSeek-R1-0528
$0.50$2.15$0.35164Kmodels.dev, 18 Nov 2026
SiliconFlow
deepseek-ai/DeepSeek-R1
$0.50$2.18–164Kmodels.dev, 18 Nov 2026
OpenRouter
deepseek/deepseek-r1-0528
$0.50$2.15$0.35128KOpenRouter, 18 Nov 2026
Novita AI
deepseek/deepseek-r1-0528
$0.70$2.50$0.35164Kmodels.dev, 18 Nov 2026
Hugging Face Inference Providers
deepseek-ai/DeepSeek-R1-0528
$3$5–164Kmodels.dev, 18 Nov 2026

Running DeepSeek-R1-0528 locally

Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.

QuantizationWeightsTotal, 8K contextTotal, 32K context
Q4_K_M (4-bit)415 GB416 GB418 GB
Q8_0 (8-bit)727 GB729 GB730 GB
FP16 / BF16 (16-bit)1369 GB1370 GB1372 GB

At 4-bit with an 8K conversation, DeepSeek-R1-0528 needs about 416 GB, more than any single consumer graphics card; it needs a unified-memory machine, a multi-GPU setup or a split between graphics card and system RAM. Check your own hardware, or see Best computer for local AI on our sister site AIPCs.

Frequently asked questions

What is the context window of DeepSeek-R1-0528?

DeepSeek-R1-0528 has a context window of 163,840 tokens (164K) and can generate up to 32,768 tokens in a single response, according to models.dev.

How much does the DeepSeek-R1-0528 API cost?

DeepSeek-R1-0528 is listed from $0.50 per million input tokens and $2.15 per million output tokens (DeepInfra). Prices last verified 18 Nov 2026.

Is DeepSeek-R1-0528 open source?

DeepSeek-R1-0528 is an open-weight model: its weights are published on Hugging Face as deepseek-ai/DeepSeek-R1-0528 under the mit license. Check the license terms before commercial use.

When was DeepSeek-R1-0528 released?

DeepSeek released DeepSeek-R1-0528 on 28 May 2025, according to models.dev.

Which providers offer DeepSeek-R1-0528?

We track DeepSeek-R1-0528 on 5 providers: DeepInfra, SiliconFlow, OpenRouter, Novita AI, Hugging Face Inference Providers.

How much VRAM does DeepSeek-R1-0528 need?

About 416 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 729 GB at 8-bit. That is more than any single consumer graphics card holds. These are estimates from the model's published parameter count and architecture.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
Kimi K2 InstructMoonshot AI11 Jul 2025131K$0.57$2.30Open
Kimi-K2-InstructMoonshot AI11 Jul 2025131K$0.57$2.30Open
GLM-4.5Zhipu AI (Z.ai)28 Jul 2025131K$0.60$2.20Open
GLM-4.6Zhipu AI (Z.ai)30 Sept 2025205K$0.50$2Open
Qwen3-235B-A22B-Thinking-2507Alibaba (Qwen)25 Jul 2025262K$0.30$3Open
Hermes-4-405BNousresearch26 Aug 2025131K$1$3Open

Change history

  • Max output changed from 64K to 33K
  • Knowledge cutoff changed from Jul 2024 to May 2025
  • Knowledge cutoff changed from May 2025 to Jul 2024
  • Max output changed from 33K to 64K
  • OpenRouter price changed: input $0.57 → $0.50, output $2.29 → $2.15 per 1M tokens
  • Knowledge cutoff changed from Jul 2024 to May 2025
  • Max output changed from 64K to 33K
  • Max output changed from 33K to 64K
  • Knowledge cutoff changed from May 2025 to Jul 2024
  • OpenRouter price changed: input $0.50 → $0.57, output $2.15 → $2.29 per 1M tokens
  • Knowledge cutoff changed from Jul 2024 to May 2025
  • Max output changed from 64K to 33K
  • Knowledge cutoff changed from May 2025 to Jul 2024
  • Max output changed from 33K to 64K
  • Knowledge cutoff changed from Jul 2024 to May 2025
  • Max output changed from 64K to 33K
  • Knowledge cutoff changed from May 2025 to Jul 2024
  • Max output changed from 33K to 64K
  • Max output changed from 64K to 33K
  • Knowledge cutoff changed from Jul 2024 to May 2025
  • Knowledge cutoff changed from May 2025 to Jul 2024
  • Max output changed from 33K to 64K
  • Knowledge cutoff changed from Jul 2024 to May 2025
  • Max output changed from 64K to 33K
  • Max output changed from 33K to 64K

Sources