AI 模型情报

DeepSeek-R1

deepseek/r1

出品方： DeepSeek · 系列: deepseek-thinking · 发布 2025-01-20 · 知识截止: 2024-07

$0.400
输入 / 1M token
$1.70
输出 / 1M token
128K
上下文长度
33K
最大输出

Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.

能力清单

✓ 工具调用✓ 推理? 结构化输出✗ 附件✗ 开放权重✓ 温度可调
支持模态: 输入 text · 输出 text

Model fit scores

0–100 · higher is better

These scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.

Coding62
  • Tool calling40/40
  • Structured output0/20
  • Reasoning10/10
  • Context window (100K → 1M)2/20
  • Provider availability10/10
Agents75
  • Tool calling35/35
  • Structured output0/25
  • Reasoning15/15
  • Output token limit15/15
  • Provider availability10/10
JSON / structured output46
  • Structured output / JSON mode0/50
  • Tool calling20/20
  • Temperature control10/10
  • Price-friendly for high-volume16/20
Cost efficiency54
  • Headline price (log-scaled)54/95
  • Has prompt-cache pricing0/5
Long context45
  • Context window (100K → 2M)35/90
  • Has published price for full window10/10
Production-readiness96
  • Number of independent providers40/40
  • Has published per-token price20/20
  • Context window ≥ 8K15/15
  • No data inconsistencies across providers6/10
  • Official model (not derivative)15/15

Cost Efficiency Index

Open full calculator →

Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.

ScenarioCostAssumption
RAG answer
per 1,000 RAG answers
$2.85
< $0.01 per request
5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot.
Support ticket triage
per 10,000 tickets
$5.70
< $0.01 per request
1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support.
Data extraction
per 1,000 documents
$1.65
< $0.01 per request
2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines.
Code review
per 1,000 PRs
$4.90
< $0.01 per request
8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads.
Agent step
per 1,000 steps
$5.82
< $0.01 per request
12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step.

定价详情

推荐定价来自 nano-gpt · deepseek-r1

$0.400
输入
$1.70
输出

最便宜的渠道： iflowcn · Unknown 输入 + Unknown 输出

在 18 家渠道可用

服务商服务商模型 ID输入 / 1M输出 / 1M上下文发布日期
Amazon Bedrock
amazon-bedrock
deepseek.r1-v1:0$1.35$5.40128K2025-01-20
Azure
azure
deepseek-r1$1.35$5.40164K2025-01-20
OpenRouter
openrouter
deepseek/deepseek-r1$0.700$2.5064K2025-01-20
Vercel AI Gateway
vercel
deepseek/deepseek-r1$1.35$5.40128K2025-01-20
Together AI
togetherai
deepseek-ai/DeepSeek-R1$3.00$7.00164K2024-12-26
NanoGPT
nano-gpt
deepseek-r1$0.400$1.70128K2025-01-20
Abacus
abacus
deepseek-ai/DeepSeek-R1$3.00$7.00128K2025-01-20
SiliconFlow (China)
siliconflow-cn
Pro/deepseek-ai/DeepSeek-R1$0.500$2.18164K2025-05-28
SiliconFlow (China)
siliconflow-cn
deepseek-ai/DeepSeek-R1$0.500$2.18164K2025-05-28
Alibaba (China)
alibaba-cn
deepseek-r1$0.574$2.29131K2025-01-01
iFlow
iflowcn
deepseek-r1UnknownUnknown128K2025-01-20
Qiniu
qiniu-ai
deepseek-r1UnknownUnknown128K2025-08-05
Kilo Gateway
kilo
deepseek/deepseek-r1$0.700$2.5064K2025-01-20
Azure Cognitive Services
azure-cognitive-services
deepseek-r1$1.35$5.40164K2025-01-20
Synthetic
synthetic
hf:deepseek-ai/DeepSeek-R1$0.550$2.19128K2025-01-20
SiliconFlow
siliconflow
deepseek-ai/DeepSeek-R1$0.500$2.18164K2025-05-28
D.Run (China)
drun
public/deepseek-r1$0.550$2.20131K2025-01-20
GitHub Models
github-models
deepseek/deepseek-r1UnknownUnknown66K2025-01-20

各渠道数据存在不一致

  • context_window varies: 128000, 131072, 163839, 163840, 164000, 64000, 65536
  • release_date varies (span 222d): 2024-12-26, 2025-01-01, 2025-01-20, 2025-05-28, 2025-08-05

各服务商对此模型的报告值存在差异。上方「核心数据」使用代表性服务商的值；逐项请以下表为准。

Frequently asked questions

How much does DeepSeek-R1 cost?

DeepSeek-R1 costs $0.400 per 1M input tokens and $1.70 per 1M output tokens, sourced from nano-gpt. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.

What is the context window of DeepSeek-R1?

DeepSeek-R1 has a context window of 128K tokens, with a max output of 33K tokens per reply. This is the total combined size of prompt + completion.

Does DeepSeek-R1 support tool calling?

Yes. DeepSeek-R1 supports tool calling (function calling). This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.

Does DeepSeek-R1 support structured output / JSON mode?

Support for structured output / JSON-schema-constrained decoding is not reported for DeepSeek-R1 in our data source. Verify with DeepSeek's official documentation before relying on it in production.

Can DeepSeek-R1 accept image input?

No. DeepSeek-R1 only accepts text as input. If you need image input, see our /capabilities/vision list for current vision-capable models.

Is DeepSeek-R1 open-weight?

No. DeepSeek-R1 is a proprietary model — only DeepSeek (and any approved hosting partners) can serve it. The pricing above reflects the cheapest API access.

What are the best alternatives to DeepSeek-R1?

If DeepSeek-R1 doesn't fit, consider DeepSeek-V3.2, DeepSeek V4 Pro, DeepSeek-R1-0528. Each one targets the same use case — see the Related links below for direct head-to-head pages.

Where does this data come from?

All numbers come from the public models.dev API and are normalised into a single canonical model record. We re-pull daily and write any changes (price, context, capability) to the /changelog page.

Explore more

Direct comparisons

More DeepSeek models

Capability lists this model is in

See also

最近更新：

Data is sourced from models.dev and normalized for comparison. Prices and capabilities may change. Always verify critical production decisions with the provider's official documentation.