R1 Model Specs, Costs & Benchmarks (March 2026)

R1, developed by DeepSeek, features a context window of 64K tokens. The model costs $0.70 per million tokens for input and $2.50 per million tokens for output. It was released on January 20, 2025, and has achieved impressive scores in various benchmarks.

Access R1 & 210+ other AI models all in one platformTry Galaxy.ai for free

Overview

	R1
Model Provider The organization behind this AI's development	DeepSeek
Input Context Window Maximum input tokens this model can process at once	64K tokens
Output Token Limit Maximum output tokens this model can generate at once	16K tokens
Release Date When this model first became publicly available	January 20, 2025 1 year ago January 20th, 2025

Pricing

	R1
Input Token Cost Cost per million input tokens	$0.70 per million tokens
Output Token Cost Cost per million output tokens	$2.50 per million tokens

Capabilities & Features

	R1
Input Types Supported input formats	text
Output Types Supported output formats	text
Tokenizer Text encoding system	DeepSeek
Key Features Advanced capabilities	✓ Function Calling✓ Reasoning Mode
Open Source Model availability	Available on HuggingFace →

Benchmarks

	R1
MMLU Measures knowledge across 57 subjects like law, math, history, and science	Not available
MMMU Measures understanding of combined text and images across various domains	Not available
HellaSwag Measures common sense reasoning by having models complete sentences about everyday situations	Not available

Compare This Model

See how R1 compares with other top models

Compare R1 with top models in each category:

🚀Programming

Best models for coding and development

R1 Model Specs, Costs & Benchmarks (March 2026)

Overview

Pricing

Capabilities & Features

Benchmarks

Compare This Model

Compare R1 with top models in each category:

🚀Programming

🎨Creative & Roleplay

📢Marketing

💻Technology

🔬Science

🌐Translation

Popular Head-to-Head Comparisons