DeepSeek V3.2 Speciale
$1.42
estimated usage cost
1,000 requests × (1,000 uncached input × $0.58 + 500 output × $1.68) / 1,000,000 = $1.42
base rates; no context pricing tiers are published.
the model directory
DeepSeek V3.2 Speciale vs GPT-5.1 Codex mini
compare api pricing, context windows, and capabilities side by side.
use the same workload to understand the cost before choosing a model.
prices are published impossibl api usage rates in usd. compare the billing units and context tiers alongside each price. unpublished capabilities are marked explicitly.
| specification | DeepSeek V3.2 Speciale deepseek/deepseek-v3-2-speciale | GPT-5.1 Codex mini openai/gpt-5.1-codex-mini |
|---|---|---|
| creator | DeepSeek | OpenAI |
| model type | Text generation | Text generation |
| input modalities | text | text, image |
| output modalities | text | text |
| base input price | $0.58 / 1m tokens | $0.25 / 1m tokens |
| base output price | $1.68 / 1m tokens | $2.00 / 1m tokens |
| cached input price | not published | $0.025 / 1m tokens |
| context window | 163.84k tokens | 400k tokens |
| tool calling | not published | not published |
| context pricing tiers | none published | none published |
| endpoints |
|
|
| retirement | not announced | not announced |
estimate your api cost
estimate text token usage across the same workload. all amounts are in usd.
GPT-5.1 Codex mini
$1.25
estimated usage cost
1,000 requests × (1,000 uncached input × $0.25 + 500 output × $2.00) / 1,000,000 = $1.25
base rates; no context pricing tiers are published.
estimates use published impossibl api usage rates. configured billing adjustments, funding fees, taxes, and custom workspace rates are excluded and may change the final amount.
image and audio usage, cache creation, and additional tool charges are excluded. reasoning tokens count as billable output, even when they are not visible in the response.
DeepSeek V3.2 Speciale vs GPT-5.1 Codex mini: side-by-side summary
DeepSeek V3.2 Speciale and GPT-5.1 Codex mini are available through the Impossibl API. They share the /v1/chat/completions endpoint. Set the model identifier to select the model for a supported request.
DeepSeek V3.2 Speciale is created by DeepSeek. It has a 163,840-token context window. Base API pricing (USD): $0.58 per million input tokens; $1.68 per million output tokens.
GPT-5.1 Codex mini is created by OpenAI. It has a 400,000-token context window. Base API pricing (USD): $0.25 per million input tokens; $2.00 per million output tokens.
context window
- DeepSeek V3.2 Speciale: 163,840 tokens
- GPT-5.1 Codex mini: 400,000 tokens
price
- DeepSeek V3.2 Speciale: Base API pricing (USD): $0.58 per million input tokens; $1.68 per million output tokens.
- GPT-5.1 Codex mini: Base API pricing (USD): $0.25 per million input tokens; $2.00 per million output tokens.
created by
- DeepSeek V3.2 Speciale: DeepSeek
- GPT-5.1 Codex mini: OpenAI