How much does DeepSeek R1 cost?

DeepSeek R1 costs $0.70 per million input tokens and $2.50 per million output tokens on standard pricing. A workload of 20M input and 5M output tokens a month is about $27.

What is the context length of DeepSeek R1?

DeepSeek R1 accepts up to 64,000 tokens (64K) of input and can return up to 16,000 tokens in one response.

Does DeepSeek R1 support tool calling and structured outputs?

Yes, DeepSeek R1 supports function/tool calling and structured (JSON) outputs. Supported tools: Function calling, JSON mode, Reasoning, Deterministic seed.

What inputs and outputs does DeepSeek R1 support?

DeepSeek R1 accepts Text as input and produces Text as output.

Which providers serve DeepSeek R1?

DeepSeek R1 is available from 1 API provider: Novita. Prices can differ by provider.

When was DeepSeek R1 released?

DeepSeek R1 was released by DeepSeek in 2025-01.

DeepSeek R1

deepseek-r1

API Provider site

Open reasoning model rivalling o1 at a fraction of the price. Built by DeepSeek.

Prices updated recently

Input price

$0.70

per 1M tokens · Standard

Output price

$2.50

per 1M tokens · Standard

Input limit

64K

tokens

Output limit

16K

tokens

Input formats

TextImageVideoAudioPDF

Output formats

TextImageVideoAudioPDF

Compare

DeepSeek R1 price history

14 price records since 4/1/2026 · 12 changes

DeepSeek R1 cost calculator

Input20M tokens

Output5M tokens

$27/month

Standard pricing

Gemini 2.5 Pro$75

Overview

What is DeepSeek R1?

DeepSeek R1 is a text & reasoning and code & slms model from DeepSeek. Open reasoning model rivalling o1 at a fraction of the price. Its 64K context window and $0.70 input price make it a candidate for quality-focused production applications.

Code generationAgent workflowsContent workflowsClassification

Benchmarks

DeepSeek R1 benchmarks & speed

How DeepSeek R1 scores on standardized evaluations, and where it lands among every model we track.

13.1

Intelligence Index

Better than 34% of 153 models

Reasoning

GPQA Diamond

81.3%

Graduate-level scientific reasoning · top 52%

HLE

15.8%

Humanity's Last Exam · top 56%

Independent scores from Artificial Analysis and DesignArena · updated 10/5/2026. Higher is better; ranks compare against every model we track with that score.

Rates

DeepSeek R1 pricing

Pricing is based on token usage. Provider-specific caching, batch, regional, and tool charges may affect the final cost.

Input · Standard

$0.70

Per 1M tokens

Cached input · Standard

Not available

No listed cached-input rate

Capabilities

DeepSeek R1 Tools

Tools available when using DeepSeek R1 through supported provider APIs.

Function calling

Supported

Structured outputs

Not supported

JSON mode

Supported

Reasoning

Supported

Built-in web search

Not supported

Log probabilities

Not supported

Deterministic seed

Supported

Parallel tool calls

Not supported

Prompt caching

Not supported

Strengths and limitations

Strengths

Measured results (AA Intelligence 13.1 · Arena Elo 1239 · MMLU-Pro 80%) position it for demanding production work.
A 64K context window covers most focused application workflows.
Supports text & reasoning and code & slms workloads in one model.

Limitations

Generated tokens cost 4× more than input tokens, which matters for verbose responses.
The 64K context window is smaller than several long-context alternatives.
Arena Elo and MMLU-Pro are directional; test accuracy, latency and reliability on your own workload before committing.

Arena Elo, MMLU-Pro and pricing figures are illustrative; validate current vendor terms before purchase.

Same provider