AI Rate CardBase model
DeepSeek R1 Distill Llama 8B
from $0.01 at 2 providers
deepseek/deepseek-r1-distill-llama-8b · 8B parameters · 2 providers · Text models ·
Price alerts
Found 2
Simple Full
Ranges in one field: "from-to" - "0.5-3", "-3" (up to), "128k-" (from); a colon works too. Several ticked values of one column are ORed, columns are ANDed.
Input price history, $/1M
Latest: minimum $0.01, median $0.01 (Nov 4, 2026)
The DEEPSEEK family - base models: 101
- deepseek
- DeepSeek Chat 9
- DeepSeek V3 0324 3
- DeepSeek V3.1 4
- deepseek-coder-6-7b 1
- deepseek-coder-33b-instruct 1
- deepseek-coder-v2-instruct 1
- deepseek-flash(1) 3
- DeepSeek Flash v4 0731 1
- deepseek-llm-67b-chat 2
- deepseek-mai-ds-r1 1
- DeepSeek OCR 7
- DeepSeek OCR 2 4
- DeepSeek: DeepSeek Pro Latest 3
- DeepSeek-Prover-V2-7B 1
- Deepseek Prover V2 671B 3
- deepseek-r1-32b 1
- deepseek-r1-di 1
- deepseek-r1-distill-qianfan-llama-8b 1
- deepseek-r1-n 1
- deepseek-r1-turbo-di 1
- DeepSeek-R1-Zero 1
- DeepSeek-R1T-Chimera 1
- DeepSeek Reasoner V3.1 1
- DeepSeek-V2-Chat 1
- deepseek-v2-5 1
- DeepSeek-V3 17
- DeepSeek-V3.1 Release 1
- deepseek-v3.2-el 1
- DeepSeek-V3.2-Exp Non-Thinking 1
- deepseek-v3.2-sp 1
- DeepSeek V3 0324 9
- DeepSeek-V3-0324-Turbo 1
- deepseek-v3-di 1
- DeepSeek V3 (Turbo) 2
- deepseek-v3-turbo-di 1
- DeepSeek-V3.1 20
- DeepSeek V3.1 Terminus 15
- DeepSeek V3.2 35
- Deepseek/DeepSeek-V3.2 1
- DeepSeek: DeepSeek V3.2 Exp 13
- DeepSeek-V3.2-Speciale 2
- deepseek-v4.1-1017 1
- DeepSeek V4.1 1017 Marathon 1
- DeepSeek V4.1 Flash 1017 Free cached input until Oct 31, 2026, 11:59 PM UTC 1
- umans-deepseek-v4.1-flash-1017-lab 2
- deepseek-v4p1-flash-1017-spot 1
- DeepSeek V4.1 Flash 1017 Uncensored 1
- deepseek-v4-1-flash-abliterated 1
- deepseek-v4.1-flash-dst 1
- deepseek-v4-1-flash-economy 1
- DeepSeek V4.1 Flash Free cached input until Oct 31, 2026, 11:59 PM UTC 1
- deepseek-v4.1-flash-marathon 1
- DeepSeek V4.1 Flash MarathonMultimodal & high-throughput 1
- deepseek-v4.1-flash-p 1
- deepseek-v4p1-flash-spot 1
- DeepSeek: DeepSeek V4.1 Flash Ultrafast 1
- DeepSeek V4.1 Flash Uncensored 1
- deepseek-v4-1-flash-us 1
- DeepSeek V4.1 Pro 1
- deepseek-v4-0731 1
- deepseek-v4-flash-0731-p 1
- DeepSeek V4 Flash 0731 · 🇺🇸 US 1
- DeepSeek V4 Flash 0731Legacy alias · Same pricing as V4.1 Flash 1
- DeepSeek V4 Flash 0731Legacy compatibility alias 1
- deepseek-v4-flash-202605 1
- deepseek-v4-flash-e 1
- DeepSeek-V4-Flash-EL 1
- DeepSeek V4 Flash Featured 1
- DeepSeek V4 Flash · 🇺🇸 US 1
- DeepSeek V4 Flash Vision (Exp) 2
- deepseek-v4-pro-0813-ds 1
- deepseek-v4-pro-0813-el 1
- deepseek-v4-pro-0813-p 1
- DeepSeek V4 Pro 0813 · 🇺🇸 US 1
- deepseek-v4-pro-202606 1
- deepseek-v4-pro-ch 1
- deepseek-v4-pro-e 1
- DeepSeek-V4-Pro-EL 1
- deepseek-v4-pro-t 1
- DeepSeek V4 Pro · 🇺🇸 US 1
- deepseek-vision-exp 1
- deepseek-vl2 1
- deepseek-flash
- deepseek-thinking
About the model: cost of your workload, questions, comparisons, citation
Cost of my workload → in the Tools tab: every provider of this model, cheapest first
Frequently asked questions
How much does DeepSeek R1 Distill Llama 8B API cost?
From $0.01 input and $0.01 output per 1M tokens, at aihubmix.
Which provider offers DeepSeek R1 Distill Llama 8B cheapest?
aihubmix offers the lowest price, $0.01 per 1M tokens, among 2 providers.
What is the context window of DeepSeek R1 Distill Llama 8B?
131K tokens.
Compare
vs Qwen2.5-Coder 7B Instruct vs Qwen2.5-VL 72B Instruct vs Qwen 2.5 72B Instruct
Source: AI Rate Card, https://airatecard.com/en/model/deepseek/deepseek-r1-distill-llama-8b, prices checked 2026-11-04