DeepSeek: DeepSeek V3.2 Exp

deepseek/deepseek-v3.2-exp

Modalities: text->text
In / out price: $0.27 / $0.41
Context: 164K
Released: Sep 29, 2025
Knowledge cutoff: 2025-07-31

DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...

ToolsReasoningStructured outputLong context

Supported parameters

frequency_penalty
Frequency penalty
Lowers the chance of a token in proportion to how often it already appeared.
include_reasoning
Include reasoning
Include a reasoning summary in the response.
max_tokens
Max tokens
Upper bound on generated tokens. Output stops at the limit.
reasoning
Reasoning
Enable or configure reasoning. The fields differ by model.
response_format
Response format
For example json_object or json_schema, to constrain the shape.
structured_outputs
Structured outputs
Generate a parseable structure that follows a JSON Schema.
temperature
Temperature
Sampling temperature. Lower is steadier, higher is more varied. Often 0 to 2.Default 0.6
tool_choice
Tool choice
Whether to call a tool: auto, none, or a named function.
tools
Tools
Function definitions the model may call via tool_calls.
top_k
Top-K
Sample only from the K most likely tokens.
top_p
Top-p
Sample only from tokens whose cumulative probability reaches top_p.Default 0.95

Models DeepSeek

DeepSeek: DeepSeek V3.2 Exp

deepseek/deepseek-v3.2-exp

Try this model

Modalities: text->text
In / out price: $0.27 / $0.41
Context: 164K
Released: Sep 29, 2025
Knowledge cutoff: 2025-07-31

ToolsReasoningStructured outputLong context

Supported parameters

frequency_penalty
Frequency penalty
Lowers the chance of a token in proportion to how often it already appeared.
include_reasoning
Include reasoning
Include a reasoning summary in the response.
max_tokens
Max tokens
Upper bound on generated tokens. Output stops at the limit.
reasoning
Reasoning
Enable or configure reasoning. The fields differ by model.
response_format
Response format
For example json_object or json_schema, to constrain the shape.
structured_outputs
Structured outputs
Generate a parseable structure that follows a JSON Schema.
temperature
Temperature
Sampling temperature. Lower is steadier, higher is more varied. Often 0 to 2.Default 0.6
tool_choice
Tool choice
Whether to call a tool: auto, none, or a named function.
tools
Tools
Function definitions the model may call via tool_calls.
top_k
Top-K
Sample only from the K most likely tokens.
top_p
Top-p
Sample only from tokens whose cumulative probability reaches top_p.Default 0.95