Baidu DeepSeek V3.2
DeepSeek · text → text
Input$0.274 /M
Output$0.411 /M
← ModelsBaidu DeepSeek V3.2DeepSeek R1 Distill Llama 70B
Baidu DeepSeek V3.2 vs DeepSeek R1 Distill Llama 70B
Compare Baidu DeepSeek V3.2 from DeepSeek and DeepSeek R1 Distill Llama 70B from DeepSeek on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the AIHubMix API.
Baidu DeepSeek V3.2DeepSeek R1 Distill Llama 70B+ Add model · 2/4
DeepSeek R1 Distill Llama 70B
DeepSeek · text → text
Provided by Groq, the DeepSeek-R1-Distill model is fine-tuned based on an open-source model, using samples generated by DeepSeek-R1. We have made slight modifications to their configurations and tokenizers. Please use our settings to run these models.
Input$0.8 /M
Output$1.6 /M
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
Baidu DeepSeek V3.2
DeepSeek R1 Distill Llama 70B
Input /M
$0.274
$0.8
Output /M
$0.411
$1.6
Cache read /M
-
-
Context length
0
NaN
Max output
0
0
Time to First Token
0.7 s
1.2 s
Throughput
54.0 tok/s
101.4 tok/s
Modalities
text
text
Supported Parameters
toolsfunction callingstructured outputs
thinking
API Formats
Released
-
January 23, 2025
Promotional prices show the discounted rate; see each model page for promotion windows.
Activity Past 30 Days
Daily traffic served through AIHubMix — how demand for each model is trending.
baidu-deepseek-v3.2deepseek-r1-distill-llama-70b
Tokens / day
-
Requests / day
-
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
baidu-deepseek-v3.2deepseek-r1-distill-llama-70b
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
Cost calculator
Estimate your monthly bill for the same workload on each model.
Baidu DeepSeek V3.2
$22.61 /mo
DeepSeek R1 Distill Llama 70B
$72.00 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: Baidu DeepSeek V3.2, DeepSeek R1 Distill Llama 70B?
Baidu DeepSeek V3.2: $0.411/M output tokens; DeepSeek R1 Distill Llama 70B: $1.6/M. Use the cost calculator above to estimate your own workload.
Which responds faster?
Baidu DeepSeek V3.2: 0.7s time to first token measured on AIHubMix; see the live performance charts above for how each model behaves across the day.
Which one generates tokens faster?
DeepSeek R1 Distill Llama 70B at 101.4 tok/s and Baidu DeepSeek V3.2 at 54.0 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.
What inputs and capabilities does each model support?
Baidu DeepSeek V3.2 accepts text input and supports tool calling, function calling and structured outputs; DeepSeek R1 Distill Llama 70B accepts text input and supports thinking.
Can I call Baidu DeepSeek V3.2 and DeepSeek R1 Distill Llama 70B with the same API key?
Yes. AIHubMix serves every model on this page behind one OpenAI-compatible endpoint, so switching between them is a one-line change to the model field — no second account, key or SDK.
Popular comparisons
Related model match-ups readers also look at.
