DeepSeek: DeepSeek V3.2 Exp
deepseek-v3.2-exp
DeepSeek V3.2 Exp costs $0.364 per million input tokens and $0.546 per million output tokens, supports 164K context, and is available through the OpenAI-compatible API.
DeepSeek V3.2 Exp is an experimental V3-series model with improved long-context efficiency compared with earlier V3 releases. FP8.
Modalities
Text → Text
Input / output price
$0.364 / $0.546 per 1M
Context
164K · max output 66K
Capabilities
Pricing
Billed per token actually used and deducted from your credits.
| Item | USD per 1M tokens |
|---|---|
| Input | $0.364 |
| Output | $0.546 |
| Cached input | $0.182 |
Calculator
Drag the sliders to estimate what this model will cost.
- Per request
- $0.00153
- Per day
- $0.7644
- Per month (30 days)
- $22.93
DeepSeek V3.2 Exp: input $0.364/M · output $0.546/M · cached input $0.182/M
curl https://api.geniusrelaygpt.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "deepseek-v3.2-exp", "max_tokens": 800,
"messages": [{"role": "user", "content": "…"}]}'Code samples
OpenAI-compatible. Set the base URL to https://api.geniusrelaygpt.com/v1 and the model to deepseek-v3.2-exp.
curl https://api.geniusrelaygpt.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v3.2-exp",
"stream": true,
"messages": [{"role": "user", "content": "Hello"}]
}'Use it in a client: Cursor · Cline · SillyTavern · Codex
Parameters
Common OpenAI parameters can be passed as-is.
temperaturetop_pmax_tokensstreamstoppresence_penaltyfrequency_penaltyseedFAQ
- How is DeepSeek V3.2 Exp billed?
- Input is $0.364 and output is $0.546 per million tokens; cached input is $0.182. The charge for every request is listed in Usage Logs in the console.
- How long is the context window?
- 164K tokens. In a long conversation every turn is billed for the full input, so keep the history under control.
- Does it support streaming?
- Yes. Add "stream": true to the request to receive server-sent events in the OpenAI format.