DeepSeek-R1
Toolsdeepseek/deepseek-r164K context · Jul 2026 · 5 upstreamsupstream上游
DeepSeek's flagship reasoning model with chain-of-thought. Strong math, coding, and complex problem solving.
Bring your own keyAnyRouter has no platform route for DeepSeek-R1. Requests use your key and bill your provider account. AnyRouter adds no fee.
- contextngữ cảnh上下文
- 64K
- inputđầu vào输入 / 1M (list)
- $0.70
- outputđầu ra输出 / 1M (list)
- $2.50
- routestuyến路由
- 5
- speed, 24htốc độ, 24h速度,24h
- —
Upstreams
5- 1SiliconFlowYour key · not addedyour planTPS —TTFT ——
- 2ClineYour key · not addedyour planTPS —TTFT ——
- 3Vercel AI GatewayYour key · not addedyour planTPS —TTFT ——
- 4OpenRouterYour key · not addedyour planTPS —TTFT ——
- 5Hugging FaceYour key · not addedyour planTPS —TTFT ——
- Up
- No traffic
- Down
Try itDùng thử试用
Send a promptGửi một prompt发送提示词
Details
- Owner
- DeepSeek
- Kind
- Chat
- Released
- Jul 2026
- Context
- 64K
- Data policy
- Provider retention
- Endpoint
/api/v1/chat/completions
Quick start
curl https://anyrouter.dev/api/v1/chat/completions \ -H "Authorization: Bearer $ANYROUTER_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "deepseek/deepseek-r1", "messages": [ { "role": "user", "content": "Say hi in 3 words." } ] }'
- Math, code and logic reasoning
- Distilling reasoning into smaller models
Architecture and licenseKiến trúc và giấy phép架构与许可
- TypeLoại类型
- Mixture of experts[1]
- Native contextNgữ cảnh gốc原生上下文
- 131,072[1]
- LicenseGiấy phép许可
- MIT · Open weightsTrọng số mở开放权重[1]
StrengthsĐiểm mạnh优势[1]
- Comparable to OpenAI o1 on math, code and reasoning
- Reasoning trained with large-scale reinforcement learning
- Distilled into dense models from 1.5B to 70B
Known limitsGiới hạn đã biết已知局限[2]
- Weak structured output; cannot call tools such as search
- Mixes languages outside Chinese and English
- Sensitive to prompts; few-shot prompting lowers quality
API notesGhi chú APIAPI 说明[1]
- Model card advises no system prompt; put instructions in the user turn
- Model card recommends temperature 0.6 (range 0.5 to 0.7)
Links and versionsLiên kết và phiên bản链接与版本
- Model cardThẻ mô hình模型卡
- huggingface.co
- PaperBài báo论文
- arxiv.org
SourcesNguồn来源
- [1]deepseek-ai/DeepSeek-R1 model cardaccessedtruy cập访问于 2026-10-14
- [2]DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningaccessedtruy cập访问于 2026-10-14
Upstreams and pricingUpstream và giá上游与价格
Share cards6 images






AliasesBí danh别名 (2)
deepseek/DeepSeek-R1deepseek-ai/DeepSeek-R1
Uptime + latency
—recent checks · all routes
No health checks recorded for this model yet.
24h
No traffic in the last 24h.