L LLM Cloud Hub
Model

R1

DeepSeek R1 — pricing, 64k context window, API cost calculator and alternatives.

By DeepSeek

🔧 Tools Function calling — the model can structure responses as tool calls with typed arguments. Reliability differs between providers. Glossary →
Context window Maximum tokens (input + output) the model can process in a single request. Glossary →
64,000
tokens
Input price What the model charges for tokens you send (prompt + context). Glossary →
$0.7000
per 1M tokens
Output price What the model charges for tokens it generates. Usually 3–5× pricier than input. Glossary →
$2.5000
per 1M tokens

Specs

Provider
DeepSeek
Slug
deepseek/deepseek-r1
Capabilities
tools

Pricing freshness

Tier
standard
Currency
USD
As of
2026-05-08 17:08 UTC
Estimate monthly cost → See alternatives to R1 →

Pricing history

Tracking R1 pricing since 2026-05-08. We'll plot the chart here once it changes.

Quickstart — call R1 from your app

curl https://api.deepseek.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $DEEPSEEK_API_KEY" \
  -d '{
    "model": "deepseek-r1",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Official docs: https://api-docs.deepseek.com/

Related models

Similar capabilities, context window, and price tier — drawn from across the catalog so you can compare alternatives in one click.

Frequently asked questions

What is R1?

R1 is a large language model API from DeepSeek with a 64k-token context window. It costs $0.7 per 1M input tokens and $2.5 per 1M output tokens.

How much does R1 cost?

R1 is priced at $0.7 per 1M input tokens and $2.5 per 1M output tokens via the DeepSeek API. A 50/50 input/output workload of 1M total tokens costs about $1.6.

What is the context window of R1?

R1 supports up to 64k tokens of context per request — roughly 128 pages of English text or 8000 lines of code at a typical density.

Does R1 support vision, tool use, or JSON mode?

R1 supports tool/function calling. It does not support image input (vision) and structured JSON mode.

Who makes R1?

R1 is built and operated by DeepSeek. Pricing, context window, and capabilities on this page are refreshed nightly from DeepSeek's public catalog.

Can I self-host R1?

R1 is API-only — its weights are not publicly distributed by DeepSeek, so it cannot be self-hosted today.

Keyboard shortcuts

?
Show this overlay
/
Focus the first form field
g h
Go to / (home)
g b
Go to /best-llm-for
g c
Go to /cost
g s
Go to /self-hosted
g x
Go to /compliance
Esc
Close any overlay

Inspired by Linear and GitHub conventions. The two-key sequences (g then h) work within ~1 second.