DeepSeek V4 Pro (0813)
StableDeepSeek · Released 2026-08 · deepseek/deepseek-v4-pro-0813
Overview
High-efficiency open model from DeepSeek delivering frontier-class reasoning and coding ability at a fraction of typical frontier pricing. DeepSeek V4 Pro (0813) supports up to 1.0M tokens of context, and an extended reasoning mode. Served through the FirmLink unified API with OpenAI-compatible endpoints.
Function CallingJSON ModeStreamingReasoningText
API example
Fully OpenAI-compatible — just change the model field.
curl https://api.firmlinktech.com/v1/chat/completions \
-H "Authorization: Bearer $FIRMLINK_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek/deepseek-v4-pro-0813",
"messages": [{"role": "user", "content": "Hello!"}]
}'Related models
DeepSeek
DeepSeek V4.1 Flash
Function CallingJSON ModeStreaming
1.0M context
$0.30 / $1.20per 1M tok in / out
View details
DeepSeek
DeepSeek V4 Flash Vision (Exp)
Function CallingJSON ModeStreamingVision
1.0M context
$0.22 / $0.66per 1M tok in / out
View details
DeepSeek
DeepSeek V4 Flash (0731)
Function CallingJSON ModeStreaming
1.3M context
$0.060 / $0.12per 1M tok in / out
View details
DeepSeek
DeepSeek V4 Pro
Function CallingJSON ModeStreaming
1.0M context
$1.60 / $3.20per 1M tok in / out
View details
DeepSeek V4 Pro (0813) is provided by DeepSeek and served through the FirmLink gateway. Availability and limits follow the provider's terms.