Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.cogito.decart.ai/llms.txt

Use this file to discover all available pages before exploring further.

The proven workhorse. DeepSeek V3.2’s reasoning is more than enough for 90% of production workloads, at one of the lowest prices in the catalog.
Slugdeepseek-v3.2
Parameters671B MoE (~37B active)
Context131,072 tokens (128k)
Throughput70 tokens/sec
TTFT260ms
LicenseDeepSeek License
HardwareAWS Trainium
Input price$0.252 / 1M tokens
Output price$0.378 / 1M tokens

​
Best for

  • Production chat applications
  • Coding assistance
  • Cost-sensitive RAG and analysis pipelines
  • Default fallback when newer models are too expensive for the use case
client.chat.completions.create(
    model="deepseek-v3.2",
    messages=[...],
)