DeepSeekReasoningLIVE INDEX

R1 0528

Name: R1 0528
Brand: DeepSeek
Price: 0.500000 USD

text->text

May 2025 R1 refresh. Improves long-form reasoning consistency and reduces hallucinations vs original R1.

R1 0528 is a reasoning AI model from DeepSeek. It costs $0.500 per million input tokens and $2.150 per million output tokens (blended $0.995/M), with a 163,840-token context window.

Profile inherited from upstream DeepSeek-R1-0528 ↗ — this is a hosted variant of the same open-weights model.

Released May 2025Modalities textOfficial model page ↗Provider pricing ↗API docs ↗Pricing source ↗Compare with another model →Estimate monthly cost →

INPUT

$0.500/M

per million input tokens

OUTPUT

$2.150/M

per million output tokens

BLENDED 70/30

$0.995/M

unchanged since 3 May

default reference rate · how it is calculated →

CONTEXT

163,840

tokens

What it is good at

Open-weights reasoning
Improved over original R1
Cheap
Visible thinking

Typical use cases

Reasoning agents
Math/STEM tutoring
Migration from R1

Benchmarks

vs. best public score

Scores inherited from DeepSeek-R1-0528 — this is a hosted variant of the same open-weights model, so the underlying benchmark scores are identical.

MMLU90%

Multitask academic knowledge across 57 subjects.

GPQA Diamond73%

Graduate-level science questions, "Google-proof".

MATH95%

High-school competition math problems.

HumanEval90%

Python function synthesis from docstrings.

SWE-bench Verified51%

Real GitHub issues solved end-to-end.

LMArena Elo1370 Elo

Crowd-sourced head-to-head preference Elo rating.

Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources, treat as directional rather than authoritative.