Skip to main content
Glama

deepseek-r1 vs deepseek-r1-distill-qwen-32b

Pricing, Performance & Features Comparison

Price unit:
deepseek-r1
Authordeepseek
Context Length64K
Reasoning
-
Providers2
ReleasedJan 2015
Knowledge CutoffJul 2024
License-
Input$0.55
Output$2.2
Latency (p50)6.9s
Output Limit8K
Function Calling
-
JSON Mode
-
InputText
OutputText
deepseek
Cheapest
in$0.55out$2.2cache$0.14write$0.55
avian
in$6.9out$6.9--
Latency (24h)
Success Rate (24h)
deepseek-r1-distill-qwen-32b
Authordeepseek
Context Length128K
Reasoning
-
Providers3
ReleasedJan 2015
Knowledge CutoffJul 2024
License-

DeepSeek-R1-Distill-Qwen-32B outperforms OpenAI-o1-mini across various benchmarks, achieving new state-of-the-art results for dense models.

Input$0.45
Output$0.7
Latency (p50)6.9s
Output Limit8K
Function Calling
-
JSON Mode
-
InputText
OutputText
glama
Cheapest
in$0.45out$1.6--
cloudflare
in$0.5out$4.9--
fireworks
in$0.7out$0.7--
Latency (24h)
Success Rate (24h)