Reasoning

DeepSeek R1

Reasoning-first MoE model optimized for multi-step logic, math, and complex planning.

Overview
R1 focuses on deliberate reasoning and multi-step problem solving. It is a strong choice for math, verification, and complex logic tasks that require deeper chains of thought.
Best for: Multi-step reasoning, Math and proofs, Complex planning
  • Reasoning-optimized training and evaluation.
  • Reported strength on math and coding benchmarks.
  • Open-source availability with multiple distilled sizes.
Pricing
Transparent pricing for legacy models. V4 pricing will be announced at launch.
Tokens$1.50 / 1M tokens
Full pricing
Research summary
Compiled from public research notes and internal summaries. Specifications may evolve ahead of official releases.

DeepSeek R1 is a reasoning-first MoE model designed for multi-step logic, math, and planning. Public reports describe ~671B parameters with sparse activation (~37B per token), pairing scale with practical inference cost.

R1 is open-source under MIT and ships alongside distilled variants (1.5B-70B class), enabling everything from research clusters to smaller deployments. Reported context windows range from 64K to 128K depending on variant and release notes.

Use R1 when correctness and reasoning chains matter: verification, proof-style tasks, algorithmic planning, and complex decision support. For smaller infrastructure, start with distilled models and scale up when evaluation demands it.

Focus areas
The traits to evaluate when choosing this model.
  • Multi-step reasoning and verification.
  • Distilled family for smaller deployments.
  • Sparse MoE efficiency at large scale.
  • Large-context variants for deep reasoning.
  • Planning and structured decision workflows.
Validate benchmarks and latency on your own prompts before committing a production rollout.