🇨🇳 Chinese model
DeepSeek R1 Distill Llama 70B
Text Function calling Reasoning
Pricing & specs
Input / 1M tokens $0.29
Output / 1M tokens $0.86
Cache / 1M tokens —
Context window 33K tokens
Max output 16K tokens
Updated 2025-01-01
Docs Official docs ↗
Price source View source ↗
Providers
USD / 1M tokens · input / output
DeepSeek Official $0.29 / $0.86 FastRouter lowest $0.03 / $0.14 Helicone $0.03 / $0.13 Alibaba (China) $0.29 / $0.86 OpenRouter $0.80 / $0.80 NovitaAI $0.80 / $0.80 Kilo Gateway $0.80 / $0.80 1 more at higher prices
Similar models · Top 5
QwQ 32B 🇨🇳 131K In $0.29 · Out $0.86 · Cache — Qwen2.5-Coder 32B Instruct 🇨🇳 131K In $0.29 · Out $0.86 · Cache — Qwen2.5 32B Instruct 🇨🇳 131K In $0.29 · Out $0.86 · Cache — GLM-4.6V 🇨🇳 128K In $0.30 · Out $0.90 · Cache — Qwen Math Turbo 🇨🇳 4K In $0.29 · Out $0.86 · Cache —
Want to go deeper on AI and cloud cost management?
Explore more on AI infrastructure, model API cost and resource optimization at mofcloud.