DeepSeek
DeepSeek R1
deepseek-r1Context
128K
Input / 1M tokens
$0.5500
Output / 1M tokens
$2.19
Weighted tokens formula
1× provider × 4× tier
About this model
DeepSeek R1
DeepSeek R1 is the reasoning-specialist sibling of V3 — trained with reinforcement learning to think step-by-step before answering. It matches or beats OpenAI o1 on math and competitive programming while costing ~80% less.
Released
2025-01
Training cutoff
2024-07
Parameters
MoE 671B (37B active)
Best for
Use cases
- ✓Competition-grade mathematics (AIME, MATH)
- ✓Algorithmic coding and competitive programming
- ✓Multi-step logical inference
- ✓Scientific reasoning + research summarization
- ✓Any workload where you'd otherwise reach for o1
Strengths
What it does well
- ●AIME 2024: 79.8% (matches o1)
- ●MATH-500: 97.3% — near-saturating the benchmark
- ●Codeforces Elo: 2029 (96.3 percentile)
- ●Emits explicit chain-of-thought you can inspect or hide
- ●Open weights (MIT license) for self-host fallback
Limitations
Know the trade-offs
- !Output token count is high — chain-of-thought adds 2–5× the tokens vs a normal chat model
- !Slower TTFT — minimum ~3 s latency on first token while it thinks
- !Less suited to conversational UX — pair with V3 for chat, R1 for hard problems
Benchmarks
Published scores
Scores from official model cards and public leaderboards. Higher is better unless noted.
| Benchmark | Score | Measures |
|---|---|---|
| AIME 2024 | 79.8 | Competition math, high-school olympiad |
| MATH-500 | 97.3 | Mathematics, competition + textbook |
| HumanEval | 96.3 | Python code generation, pass@1 |
| MMLU | 90.8 | General knowledge across 57 subjects |
| Codeforces | 96.3 | Percentile rank vs human competitive programmers |
Code example
Chat completion with DeepSeek R1
from openai import OpenAI
client = OpenAI(
base_url="https://api.anoman.io/v1",
api_key="anm-sk-..."
)
response = client.chat.completions.create(
model="deepseek-r1",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)Weighted tokens
weighted_tokens = raw_tokens × 1 (provider) × 4 (tier)
Pro plan: 20M weighted tokens/month. Combined multiplier 4×: 5,000,000 raw tokens available.
Alternatives
Similar models in our catalog
Workloads that fit DeepSeek R1 often fit these too. Compare benchmarks and pricing before locking in a default.