DeepSeek-R1

DeepSeekOpen weights

DeepSeek-R1 by DeepSeek costs — per 1M input tokens and — per 1M output tokens, with a —-token context window.

Pricing

Input (per 1M tokens)

—

Output (per 1M tokens)

—

Cached input (per 1M)

—

Specifications

Provider: DeepSeek
Context window: —
Parameters: 671B
Released: Jan 2025
Open weights: Yes
Frontier model: No

Benchmarks

Epoch Capabilities Index: 141.3
GPQA Diamond: 76.3
LMArena (Chatbot Arena) Elo: 1427.7

Speed & latency

Time to first token

0.25s

Output speed

165 tok/s

Fastest host: bedrock (via vercel-ai-gateway).

Compare DeepSeek-R1 with…

DeepSeek-R1 vs DeepSeek: R1 Distill Llama 70B$0.80/1M DeepSeek-R1 vs DeepSeek Reasoner$0.28/1M DeepSeek-R1 vs DeepSeek: DeepSeek Pro Latest$8.00/1M DeepSeek-R1 vs DeepSeek: DeepSeek Flash Latest$0.89/1M DeepSeek-R1 vs DeepSeek: DeepSeek V4 Flash Latest$0.58/1M DeepSeek-R1 vs DeepSeek: DeepSeek V4.1 Flash$0.89/1M

FAQ

How much does DeepSeek-R1 cost?

DeepSeek-R1 is priced at — per 1M input tokens and — per 1M output tokens. Output tokens cost more than input.

What is DeepSeek-R1's context window?

DeepSeek-R1 supports a context window of — tokens — the maximum prompt plus response length it can handle in a single request.

Is DeepSeek-R1 open weight?

Yes — DeepSeek-R1 has openly available weights.

Data as of 2026-10-14. Source: Epoch AI, Data on AI Models (CC BY 4.0), epoch.ai. Pricing is per 1M tokens (USD); confirm with the provider before production use.