LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

DeepSeek R1 0528

deepseek·deepseek/deepseek-r1-0528·GA·Open weights·deepseek-thinking series
May 2025 DeepSeek R1 update with improved mathematics, coding, and reasoning

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·submodelGateway
$0.20 / $0.80
Blended $0.35 · 15× spread
Context
163,840
Output limit
32,768
Knowledge cutoff
2024-07
Released / updated
2025-05-28 / 2025-05-28
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text
License
MIT
Weights
Hugging Face

DeepSeek R1 0528 is offered by 20 providers on this page. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is submodel at $0.20 / $0.80 per 1M. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. Prices vary about 15× across the providers that host it.

Median output speed is 31 tokens per second, with 1.51s to the first token.

The context window is 163,840 tokens at the reference host, but hosts report different limits, from 65,536 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.

Quality & performanceArtificial Analysis · Intelligence Index v5

Intelligence—
Value—
Output speed31 tok/s
TTFT1.51 s

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

Available at 20 providers20 with public prices

  • ProviderInput / Output
  • submodelGateway
    deepseek-ai/DeepSeek-R1-0528
    $0.20 / $0.80
    Context 75,000 ⚠Output limit 75,000
  • NanoGPTGateway
    deepseek-ai/DeepSeek-R1-0528
    $0.50 / $2.15
    Cache read $0.35Context 163,840Output limit 32,768
  • MeganovaGateway
    deepseek-ai/DeepSeek-R1-0528
    $0.50 / $2.15
    Cache read $0.40Context 163,840Output limit 64,000
  • Eden AIGateway
    deepinfra/deepseek-ai/DeepSeek-R1-0528
    $0.50 / $2.15
    Cache read $0.35Context 163,840Output limit 32,768
  • Deep InfraCloud
    deepseek-ai/DeepSeek-R1-0528
    $0.50 / $2.15
    Cache read $0.35Context 163,840Output limit 64,000
  • SiliconFlowCloud
    deepseek-ai/DeepSeek-R1
    $0.50 / $2.18
    Context 164,000 ⚠Output limit 164,000
  • Alibaba (China)First-party
    $0.50 / $2.18
    Context 163,840Output limit 32,768
  • IO.NETCloud
    deepseek-ai/DeepSeek-R1-0528
    $0.52 / $2.21
    Cache read $0.26Context 128,000 ⚠Output limit 4,096
  • OpenRouterGateway
    $0.57 / $2.29
    Context 163,840Output limit 32,000
  • Kilo GatewayGateway
    $0.57 / $2.29
    Context 128,000 ⚠Output limit 32,000
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
submodel
deepseek-ai/DeepSeek-R1-0528
Gateway$0.20$0.80——75,000 ⚠75,000
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$0.40—163,84064,000
Eden AI
deepinfra/deepseek-ai/DeepSeek-R1-0528
Gateway$0.50$2.15$0.35—163,84032,768
Deep Infra
deepseek-ai/DeepSeek-R1-0528
Cloud$0.50$2.15$0.35—163,84064,000
SiliconFlow
deepseek-ai/DeepSeek-R1
Cloud$0.50$2.18——164,000 ⚠164,000
Alibaba (China)First-party$0.50$2.18——163,84032,768
IO.NET
deepseek-ai/DeepSeek-R1-0528
Cloud$0.52$2.21$0.26—128,000 ⚠4,096
OpenRouterGateway$0.57$2.29——163,84032,000
Kilo GatewayGateway$0.57$2.29——128,000 ⚠32,000

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

budget_tokens ≥ 128 ≤ 32,768effort = higheffort = minimaleffort = loweffort = mediumeffort = xhigheffort = max

Interleaved thinking (reasoning between tool calls) is declared by 2 of 20 providers.

15 / 20 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1submodel$80.00
2SiliconFlow (China)$174.55
3SiliconFlow (China)$174.55
4IO.NET$183.58
5NanoGPT$189.50
6Eden AI$189.50
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.91$02026-08-052026-10-22
2026-10-22Input list —Output list —Min blended $0.35

Related models

DeepSeek V4 Pro 0813same series$0.66 / $1.98DeepSeek V4 Prosame series—DeepSeek V4 Pro 0423same series—DeepSeek-R1same lab—DeepSeek Reasonersame lab—
Data partly from models.dev (MIT)