deepseek

DeepSeek: R1

DeepSeek R1 is a text-focused AI model with an extensive context length of 163,840 tokens and supports both reasoning and tools integration. It can generate detailed structured outputs when needed, making it suitable for complex tasks that require logical processing and external tool usage. For users seeking a reliable model within their budget, DeepSeek R1 stands out with its benchmark blended score of 63.8 across three independent evaluations. Given its pricing at $0.7 per million input tokens and $2.5 per million output tokens, it offers a cost-effective solution for those looking to perform sophisticated reasoning tasks without breaking the bank.

Quality Score
93/100
price + capability + benchmarks
Input Price
$0.70
per 1M tokens
Output Price
$2.50
per 1M tokens
Context Window
163,840
tokens

Benchmark results

Independent, published benchmarks. Blended score 63.8 across 3 benchmarks, last refreshed 2026-08-13. How scoring works →

BenchmarkMeasuresScore
Aider Polyglot code editing across languages 71.4
AI Index broad capability composite 33.6
EQ-Bench emotional understanding in dialogue 65.8
Model ID
deepseek/deepseek-r1
Vendor
deepseek
Released
January 2025
Tokenizer
DeepSeek
Input Modalities
text
Output Modalities
text
Max Output
16,000 tokens
Tool Calling
✓ supported
Structured Output
✓ supported
Reasoning Mode
✓ supported
Vision
text only
Audio
no
Moderated
no

What it costs in practice

Computed from the current $0.70/M input and $2.50/M output rates. Run your own numbers →

JobTokensCost
Summarize a 50-page report 30k in / 1.5k out $0.02
Classify 1,000 customer emails 500k in / 50k out $0.47
A month of a busy support chatbot 5M in / 2M out $8.50

Similar models

Quick answers

How much does DeepSeek: R1 cost?
$0.70 per million input tokens and $2.50 per million output tokens.
What is DeepSeek: R1's context window?
163,840 tokens, roughly 245 pages of text in a single request.
Does DeepSeek: R1 support tool calling?
It supports tool calling, structured output, a reasoning mode.
Can DeepSeek: R1 process images?
No, it is text-only on the input side.