DeepseekDeepSeek R1Tool use

R1 0528 pricing

May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass. Fully open-source model. Live index: 7 priced offers. Best input $0.200 per million tokens from Lambda. Best output $0.250 per million tokens from Hyperbolic.

164K context·7 providers·verified Apr 12, 2026
Best input$0.200per 1M tokens · Lambda
Best output$0.250per 1M tokens · Hyperbolic

Pricing across providers

All figures are list prices per million tokens unless a column says otherwise. 7 offers are listed for R1 0528. Best input in this view: Lambda.

O
Openrouter
Input / 1M
$0.500
Output / 1M
$2.15
L
Lambda
Input / 1M
$0.200
Output / 1M
$0.600
N
Nebius
Input / 1M
$0.800
Output / 1M
$2.40
H
Hyperbolic
Input / 1M
$0.250
Output / 1M
$0.250
N
Novita
Input / 1M
$0.700
Output / 1M
$2.50
Cached in: $0.350
D
DeepInfra
Input / 1M
$0.500
Output / 1M
$2.15
Cached in: $0.400
FA
Fireworks AI
Input / 1M
$3.00
Output / 1M
$8.00

Input vs output · per provider

Cost calculator

Use this block to stress test R1 0528 cost without a spreadsheet. All estimates come from public list rates in this page.

Provider

In: $0.500/M·Out: $2.15/M

0.050000¢ / req

0.107500¢ / req

Daily
$16
Monthly
$473
Annual
$5.7K

Model specifications

These fields describe R1 0528 as we store it (Family: DeepSeek R1. source: Deepseek). They sit next to price so buyers can check limits and tools in one place.

Context window
163,840 tokens
Max output
163,840 tokens
Vision (images)
No
Tool / function calling
Yes
Streaming
No
Released
May 2025
Primary provider
Deepseek
Model family
DeepSeek R1

Compare R1 0528

These links open full side by side pages for R1 0528. We picked pairs that people often shop together. 6 ready to open.

Frequently asked questions

Read these after the table if you want plain language around R1 0528 rates. The short model note from our index: May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active i...

Yes. R1 0528 is available on Openrouter, Lambda, Nebius, Hyperbolic, Novita, DeepInfra, Fireworks AI.

Also from Deepseek

Other models by Deepseek with live pricing in our catalog.