Log in
← All models

DeepSeek R1 (0528)

Balanced

The open-weight reasoning model that put long chain-of-thought in everyone's hands.

DeepSeek
Maker
75/100
Overall
63
Value score
$0.99
Blended /1M
164K
Context
Open
Weights
Pricing: $0.50 in · $2.15 out / 1M tokens · synced from OpenRouter · updated 2026-06-22

Scorecard

Output Quality7.5/10 · 70% community
Agentic Ability7.0/10 · 68% community
Speed6.8/10 · 66% community
Value for $8.6/10 · 75% community
Reliability8.6/10 · 75% community

DeepSeek R1 is the open-weight reasoning model that popularized accessible long chain-of-thought. It trades speed for deliberate, step-by-step problem solving and remains a favourite for math, logic, and planning-heavy agent tasks at low cost.

Strengths
  • Strong reasoning at low cost
  • Open weights
  • Transparent thinking traces
Trade-offs
  • Slow due to long reasoning
  • Weaker at fast tool loops

Agents that run DeepSeek R1 well

Reasoning-heavy planning where cost matters.

Best model for ClineBest model for AiderBest model for OpenClawBest model for HermesBest model for OpenCode

DeepSeek R1 (0528) FAQ

Is DeepSeek R1 (0528) good for AI agents?
Reasoning-heavy planning where cost matters. On our editorial scoring it rates 7.0/10 for agentic ability and 7.5/10 for output quality. Strong reasoning at low cost.
How much does DeepSeek R1 (0528) cost?
Via OpenRouter, DeepSeek R1 (0528) is priced at $0.50 in · $2.15 out / 1M tokens — a blended rate of about $0.99 per 1M tokens for typical input-heavy agent use.
What is DeepSeek R1 (0528)'s context window?
DeepSeek R1 (0528) has a 164K-token context window. DeepSeek is the maker.
Is DeepSeek R1 (0528) open source?
Yes — DeepSeek R1 (0528) ships with open weights, so you can self-host it for privacy or run it through a hosted provider like OpenRouter. That openness is a big reason it's popular in open agent stacks.
What are the downsides of DeepSeek R1 (0528)?
The main trade-offs: slow due to long reasoning; weaker at fast tool loops. It's strongest for reasoning-heavy planning where cost matters.

DeepSeek R1 compared

DeepSeek R1 vs Sonnet 4.6DeepSeek R1 vs GPT-5.4DeepSeek R1 vs Gemini 3.5 FlashDeepSeek R1 vs GPT-5.3-CodexDeepSeek R1 vs Kimi K2.7 CodeDeepSeek R1 vs MiniMax M3DeepSeek R1 vs Qwen3.7 PlusDeepSeek R1 vs Devstral 2

The model is half the story — the agent is the other half

The model picks the moves; the agent runs the loop, the tools, and the guardrails. Once you've chosen a model, see which agent gets the most out of it.

Compare AI agents →