LLM Reference

DeepSeek R1 0528

Released
2025-05-28
Last refreshed
2026-06-29
Status
Researched 42d ago
Open sourceCommercial use: permittedCodingRAGAgentsLong contextClassificationJSON / Tool use

DeepSeek R1 0528 is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.

Use it for

  • Teams evaluating coding, rag, and agents
  • Workloads that can use a 130k context window
  • Buyers comparing 4 tracked provider routes

Do not use it for

  • Vision or document-understanding workloads
Specifications
Released
2025-05-28
Context
130k
Parameters
685B total, 37B active (MoE)
Architecture
Decoder Only
Specialization
general
Openness
Open source
License
MITOSI-approvedCommercial use: permitted
Training
Pretrained
Created by

Advancing artificial general intelligence (AGI).

Hangzhou, Zhejiang, China
Founded 2023
Website
Pricing
Output / 1M
$1.68
Input / 1M
$0.560

Cheapest of 7 routes · Fireworks AI

About

DeepSeek R1 0528 is DeepSeek's DeepSeek R1 model with an optional reasoning mode. It offers a 130K-token context window with weights openly available for self-hosting and scores 81 on GPQA.

DeepSeek R1 0528 is an open-source model in the DeepSeek R1 family. The structured metadata tracks reasoning, structured outputs, and code execution. This page tracks provider routes through Together AI, Fireworks AI, GCP Vertex AI, and 4 more, with the cheapest tracked route listed at $0.5 input and $2.15 output per 1M tokens. Headline tracked benchmarks include Aider Polyglot 71.4, Google-Proof Q&A 81.0, and AIME 2024 91.4.

Top use-case fit: coding, agents, and build tasks

Coding

Q/$ C

3 relevant benchmarks in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

Q/$ C

1 relevant benchmark in the decision map.

Provider price ladder

Compare all 7

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

ProviderInput / 1MOutput / 1MCacheRoute
Fireworks AI$0.560$1.68-
Serverless
DeepInfra$0.500$2.15read $0.350
Serverless
OpenRouter$0.500$2.15-
Serverless
Novita AI$0.700$2.50read $0.350
Serverless

Available via routers & gateways(14)

Capabilities

ReasoningStructured OutputsCode Execution

Benchmark peer barsfor Coding

Benchmark scores(7)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionSource
Aider Polyglot71.42026-04https://aider.chat/docs/leaderboards
Google-Proof Q&A81.0https://github.com/deepseek-ai/DeepSeek-R1
AIME 202491.4https://github.com/deepseek-ai/DeepSeek-R1
AIME 202587.5https://github.com/deepseek-ai/DeepSeek-R1
LiveCodeBench73.3https://github.com/deepseek-ai/DeepSeek-R1
MMLU PRO85.0https://github.com/deepseek-ai/DeepSeek-R1
SWE-bench Verified57.6https://github.com/deepseek-ai/DeepSeek-R1

Migration checks

No linked migration route is available for this model yet.

Compare DeepSeek R1 0528 with other models

Show all 41 popular comparisonssorted by 7-day search impressions

Frequently asked questions

What is the context window of DeepSeek R1 0528?

DeepSeek R1 0528 has a context window of 130k tokens.

How much does DeepSeek R1 0528 cost?

DeepSeek R1 0528 pricing ranges from $0.5/1M to $3/1M input tokens depending on the provider.

When was DeepSeek R1 0528 released?

DeepSeek R1 0528 was released on 2025-05-28.

Which providers offer DeepSeek R1 0528?

DeepSeek R1 0528 is available from 7 providers: Together AI, Fireworks AI, GCP Vertex AI, Novita AI, OpenRouter, Microsoft Foundry, DeepInfra.

What benchmarks has DeepSeek R1 0528 been tested on?

DeepSeek R1 0528 has been evaluated on 7 benchmarks, including Aider Polyglot, Google-Proof Q&A, AIME 2024, AIME 2025, LiveCodeBench.