Back to models
DeepSeek V3.2
DeepSeek's iteration balancing reasoning capability and cost.
Context
128,000
≈ 128K
Max output
64K
64,000
Price ($/1M tokens)
—
Specs
Input
Text
Output
Text
Reasoning
Yes
Tool call
Yes
Structured
Yes
Weights
Open
Released
2025-12-01
Free on relays
0
Free on relays (0)
This model is not currently offered by an indexed relay with free quota.