LLM Pricing
PricingLeaderboardsToolsProvidersReleasesGuides

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

DeepSeek R1 0528

deepseek·deepseek/deepseek-r1-0528·GA·Open weights·deepseek-thinking series
DeepSeek reasoning model for multi-step analysis, math, coding, and tools

DeepSeek R1 0528 is offered by 13 providers on this page. Public prices are shown for 12 of them. Its reference price is $3.00 per 1M input tokens and $5.00 per 1M output tokens. The lowest paid channel is Deep Infra at $0.50 / $2.15 per 1M, about 6.0× below the reference price.

Artificial Analysis rates it 13.1 on the Intelligence Index. Against its lowest blended price of $0.912 per 1M, that is roughly 14 index points per dollar, which is the value ratio the leaderboards rank on.

The context window is 163,840 tokens at the reference host, but hosts report different limits, from 75,000 to 164,000, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2024-07.

Specs & pricing

Input / output per 1M tokens
Reference price·Hugging Face
$3.00 / $5.00
Blended $3.50 · Cache read —
Lowest paid·Deep InfraCloud
$0.50 / $2.15
Blended $0.91 · 6× spread
Context
163,840
Output limit
163,840
Knowledge cutoff
2024-07
Released / updated
2025-05-28 / 2026-01
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text

Quality & performanceArtificial Analysis · Intelligence Index v4.3

Intelligence13.1
Value14
Coding—
Agentic—
Output speed—
TTFT—
Value formulaIQ 13.1 ÷ min blended $0.912 = 14

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 13 providers12 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Deep Infra
deepseek-ai/DeepSeek-R1-0528
Cloud$0.50$2.15$0.35—163,84064,000
NanoGPT
deepseek-ai/DeepSeek-R1-0528
Gateway$0.50$2.15$0.35—163,84032,768
Meganova
deepseek-ai/DeepSeek-R1-0528
Gateway$0.50$2.15——163,84064,000
submodel
deepseek-ai/DeepSeek-R1-0528
Gateway$0.50$2.15——75,000 ⚠—
OpenRouterGateway$0.50$2.15$0.35—163,84032,768
Alibaba (China)First-party$0.50$2.18——163,84032,768
Alibaba (China)First-party$0.57$2.29——131,072 ⚠16,384
TensorXGateway$0.66$2.60$0.17$0.83164,000 ⚠8,192
Kilo GatewayGateway$0.70$2.50$0.35—163,84032,768
NovitaAIGateway$0.70$2.50$0.35—163,84032,768

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Reasoning control

effort = minimaleffort = loweffort = mediumeffort = higheffort = xhigheffort = max

Interleaved thinking (reasoning between tool calls) is declared by 2 of 13 providers.

11 / 13 providers expose no reasoning control (reasoning_options: []).

Your usage cost

1Deep Infra$189.50
2NanoGPT$189.50
3OpenRouter$189.50
4TensorX$202.60
5Meganova$207.50
6submodel$207.50
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$5.00$02026-08-052026-10-052026-08-05 · Input list $3.002026-08-06 · Input list $3.002026-08-07 · Input list $3.002026-08-08 · Input list $3.002026-08-09 · Input list $3.002026-08-10 · Input list $3.002026-08-11 · Input list $3.002026-08-12 · Input list $3.002026-08-13 · Input list $3.002026-10-05 · Input list $3.002026-08-05 · Output list $5.002026-08-06 · Output list $5.002026-08-07 · Output list $5.002026-08-08 · Output list $5.002026-08-09 · Output list $5.002026-08-10 · Output list $5.002026-08-11 · Output list $5.002026-08-12 · Output list $5.002026-08-13 · Output list $5.002026-10-05 · Output list $5.002026-08-05 · Min blended $0.732026-08-06 · Min blended $0.732026-08-07 · Min blended $0.732026-08-08 · Min blended $0.732026-08-09 · Min blended $0.732026-08-10 · Min blended $0.732026-08-11 · Min blended $0.732026-08-12 · Min blended $0.732026-08-13 · Min blended $0.732026-10-05 · Min blended $0.91

Artificial Analysis evaluations11 items

GPQA Diamond81.3%
Humanity's Last Exam15.8%
MMLU-Pro84.9%
LiveCodeBench77.0%
Terminal-Bench Hard15.9%
AIME 202576.0%
AIME89.3%
MATH-50098.3%
τ²-Bench Telecom36.5%
AA-LCR55.7%
IFBench39.6%

Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and harness, so rows are not comparable with one another. The Intelligence Index above draws on a different, newer set of evaluations.

Related models

DeepSeek V4 Pro 0813 (Databricks)same series$1.32 / $3.96DeepSeek V4 Pro 0813 (EU)same series$1.75 / $3.50DeepSeek V4 Pro 0813 Thinkingsame series$1.10 / $2.50GLM-5.3-Flashcheaper alternative$0.15 / $0.50DeepSeek V4.1 Flashcheaper alternative$0.15 / $0.60DeepSeek V4 Flash 0731cheaper alternative$0.45 / $1.34Qwen3.8 27Bcheaper alternative$0.80 / $4.00
Data partly from models.dev (MIT) · Hugging Face official docs ↗