← All models
DeepSeek · Language model
DeepSeek V3.2 Exp
deepseek/deepseek-v3.2-exp- Language
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...
Specifications
- Context window
- 163,840 tokens
- Max output
- 65,536 tokens
- Input
- text
- Output
- text
- Reasoning
- supported
- Tokenizer
- DeepSeek
- Knowledge cutoff
- 2025-07-31
Supported parameters
Accepted by the model and forwarded as-is by the gateway.
- frequency_penalty
- logit_bias
- logprobs
- max_tokens
- min_p
- presence_penalty
- reasoning
- repetition_penalty
- response_format
- seed
- stop
- structured_outputs
- temperature
- tool_choice
- tools
- top_k
- top_logprobs
- top_p
Use it
POST /api/v1/chat/completions · MCP chat · full reference
curl https://omnirail.org/api/v1/chat/completions \
-H "Authorization: Bearer $OMNIRAIL_KEY" -H "Content-Type: application/json" \
-d '{"model":"deepseek/deepseek-v3.2-exp","messages":[{"role":"user","content":"Hello"}],"max_tokens":300}'