DeepSeek V3.2 Exp API Pricing
As of October 10, 2026, DeepSeek V3.2 Exp costs $0.27 per 1M input tokens and $0.41 per 1M output tokens on Novita AI. It has a 163,840-token context window and returns up to 65,536 tokens per response.
- Input
- $0.27 / 1M tokens
- Output
- $0.41 / 1M tokens
- Context window
- 163,840 tokens
- Max output
- 65,536 tokens
- Providers
- 1
- Added to LiteLLM
- November 2025
DeepSeek V3.2 Exp pricing by provider
1 listing across 1 provider. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.
| Provider | Model name in LiteLLM | Input | Output | Context |
|---|---|---|---|---|
| Novita AI | novita/deepseek/deepseek-v3.2-exp | $0.27 | $0.41 | 160K |
What DeepSeek V3.2 Exp costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| Novita AI | $0.745 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| Novita AI | $2.782 |
DeepSeek V3.2 Exp features
- Function calling
- Parallel tool calls
- Structured output
- Reasoning
Use DeepSeek V3.2 Exp with LiteLLM
Call DeepSeek V3.2 Exp through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.
from litellm import completion
response = completion(
model="novita/deepseek/deepseek-v3.2-exp",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: deepseek-v3.2-exp
litellm_params:
model: novita/deepseek/deepseek-v3.2-exp
# credentials: see the provider's LiteLLM docs pagecurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "deepseek-v3.2-exp",
"messages": [{"role": "user", "content": "Hello!"}]
}'DeepSeek V3.2 Exp FAQ
How much does DeepSeek V3.2 Exp cost?
DeepSeek V3.2 Exp costs $0.27 per 1M input tokens and $0.41 per 1M output tokens on Novita AI.
What is the context window of DeepSeek V3.2 Exp?
DeepSeek V3.2 Exp has a 163,840-token context window and returns up to 65,536 tokens per response.
Which providers offer DeepSeek V3.2 Exp?
DeepSeek V3.2 Exp is available from Novita AI through LiteLLM, using the model name novita/deepseek/deepseek-v3.2-exp.
How do I call DeepSeek V3.2 Exp with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="novita/deepseek/deepseek-v3.2-exp", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.
What features does DeepSeek V3.2 Exp support?
DeepSeek V3.2 Exp supports function calling, parallel tool calls, structured output and reasoning.
When did LiteLLM add DeepSeek V3.2 Exp?
DeepSeek V3.2 Exp was added to LiteLLM's model price file in November 2025.
Sources
Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request.
Provider pages: Novita AI.
