Type
Spec
Rate
Input
per 1M prompt tokens
$1.32
Output
per 1M generated tokens
$3.96
Web Search (Linkup)
per call when invoked
$0.013
DeepSeek V4 Pro 0813 and DeepSeek V4 Flash 0731 side by side: specs, capabilities, parameters, and live pricing from the EmpirioLabs catalog.
DeepSeek Text GenerationDeepSeek V4 Pro 0813 and DeepSeek V4 Flash 0731 are both DeepSeek models in the Text Generation category, available through the EmpirioLabs API.
| Spec | DeepSeek V4 Pro 0813 | DeepSeek V4 Flash 0731 |
|---|---|---|
| Model ID | deepseek-v4-pro-0813 | deepseek-v4-flash-0731 |
| Author | DeepSeek | DeepSeek |
| Released | Aug 13, 2026 | Jul 31, 2026 |
| Context window | 1M tokens | 1M tokens |
| Max output | 393,216 tokens | 393,216 tokens |
| Input | Text | Text |
| Output | Text | Text |
| Structured output | JSON Schema | JSON Mode |
| Region | Singapore | Germany |
| Endpoints | POST /v1/chat/completions POST /v1/responses POST /v1/messages POST /v1beta/models/deepseek-v4-pro-0813:generateContent | POST /v1/chat/completions POST /v1/responses POST /v1/messages POST /v1beta/models/deepseek-v4-flash-0731:generateContent |
| Capabilities |
Live rates from the EmpirioLabs catalog for both models. Each rate card always matches what the API charges.
Request parameters each model lists on EmpirioLabs, with the allowed values or range where one applies. A dash marks a parameter the model does not list.
| Parameter | DeepSeek V4 Pro 0813 | DeepSeek V4 Flash 0731 |
|---|---|---|
| temperature | 0 to 2 Default: 0.7 | 0 to 2 Default: 0.7 |
| top_p | 0 to 1 Default: 0.9 | 0 to 1 Default: 0.9 |
| max_tokens | 1 to 393216 | 1 to 393216 |
| stop | string | string |
| enable_thinking | boolean Default: true | boolean Default: true |
| reasoning_effort | none, low, medium, high, max Default: medium | none, low, medium, high, max Default: medium |
| thinking_budget | 1 to 393216 Default: 32768 | 1 to 393216 Default: 32768 |
| response_format | enum | enum |
| web_search_linkup | boolean Default: false | boolean Default: false |
| disable_formatting | boolean Default: false | boolean Default: false |
Thinking is enabled by default and can be disabled. Reasoning tokens are billed as output tokens. Optional Linkup web search is billed only when invoked.
Thinking is enabled by default and can be disabled. Reasoning tokens are billed as output tokens. Optional Linkup web search is billed only when invoked.
DeepSeek V4 Pro 0813 serves the OpenAI-compatible Chat Completions API. Point any OpenAI SDK at https://api.empiriolabs.ai/v1 with your EmpirioLabs API key and use the model id deepseek-v4-pro-0813. Both models are called through the same endpoint. Set model to deepseek-v4-pro-0813 or deepseek-v4-flash-0731. Get an API key from the EmpirioLabs dashboard.
curl https://api.empiriolabs.ai/v1/chat/completions \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-pro-0813",
"messages": [
{"role": "user", "content": "Write a haiku about the ocean."}
]
}'DeepSeek V4 Pro 0813 is the newer release (Aug 13, 2026); DeepSeek V4 Flash 0731 was released on Jul 31, 2026. Both models have a context window of 1M tokens. DeepSeek V4 Flash 0731 lists the lower rate for Input (per 1M prompt tokens) and Output (per 1M generated tokens). The specs, rate cards, and parameters on this page come from the live EmpirioLabs catalog.
DeepSeek V4 Pro 0813 is the newer release (Aug 13, 2026); DeepSeek V4 Flash 0731 was released on Jul 31, 2026.
DeepSeek V4 Flash 0731 lists the lower rate for Input (per 1M prompt tokens) and Output (per 1M generated tokens). Both live rate cards are on this page and always match what the API charges.
Yes. Both models use POST /v1/chat/completions with the same EmpirioLabs API key, so most integrations switch by changing the model value. Check the parameters table on this page first if you rely on a model-specific parameter.
Yes. Open each model in the EmpirioLabs playground and run the same prompt on both, with the parameters the API exposes.
Check out our pricing or reach out if you want your own model deployed on our stack.