DeepSeek

DeepSeek R1 Distill Qwen 32B

AI model by DeepSeek. Real-time pricing and benchmark data.

Pricing (per 1M tokens)

Input$0.27
Output$0.27
Blended (3:1)$0.27

Source: Artificial Analysis

Performance

Output Speed59 tok/s
Time to First Token492ms

Median values from Artificial Analysis

Compare with similar models

ModelInputOutputSpeed
DeepSeek R1 Distill Qwen 32BCurrent
$0.27$0.2759 tok/s
Granite 4.0 H Small
$0.06$0.25524 tok/s
Llama 2 Chat 7B
$0.05$0.25120 tok/s
Mistral 7B Instruct
$0.25$0.25188 tok/s
Granite 3.3 8B (Non-reasoning)
$0.03$0.25386 tok/s
Step 3.5 Flash
$0.10$0.3093 tok/s

Example Costs

Single Request
$0.0004
1.0K in / 500 out
1K Requests/day
$0.4050
1.0M in / 500.0K out
10K Requests/day
$4.05
10.0M in / 5.0M out