DeepSeek V4 Pro
deepseek/deepseek-v4-proDeepSeek V4 Pro is the large tier of DeepSeek's V4 family, a 1.6T-parameter mixture-of-experts model with 49B active parameters, introduced as an open-weight preview in April 2026 with a 1M-token context. It combines token-wise compression with DeepSeek Sparse Attention and supports thinking and non-thinking modes, aimed at agentic coding, advanced reasoning and knowledge-heavy work. On DeepSeek's API this name now serves the August 2026 GA revision; use the 0813 entry to pin that version.
- Input price
- $0.99
$1.32USD / 1M tokens - Output price
- $2.97
$3.96USD / 1M tokens - Cache read
- $0.03
$0.04USD / 1M tokens - Context window
- 1M
- Max output
- 384K
Specifications
- Input
- Text
- Output
- Text
Independent evaluations
Benchmarks
Scores on standardized evaluations, compared with other models on SandBase.
Metrics sourced from Artificial Analysis · Intelligence Index v5 · Updated 2026-10-29
Try the model
Playground
Write a prompt to try this model. Usage is billed at the prices shown.
Try a prompt
Your response will appear here
Choose an example or write a prompt, then click Run.
Start building
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/chat/completions" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "deepseek/deepseek-v4-pro",
"messages": [
{
"role": "user",
"content": "Hello"
}
],
"max_tokens": 2048
}
SANDBASE_JSON
)
printf '%s\n' "$result"Questions
FAQ
How do I call DeepSeek V4 Pro through SandBase?
Create a SandBase API key, then send requests with the model ID "deepseek/deepseek-v4-pro" to Chat Completions API (/v1/chat/completions) at https://api.sandbase.ai. The request examples on this page show the exact payload.
How much does DeepSeek V4 Pro cost?
$0.99 per 1M input tokens and $2.97 per 1M output tokens with the current 25% discount (list price $1.32 / $3.96), billed per request from your SandBase balance.
What is the context window of DeepSeek V4 Pro?
1M tokens of context, with up to 384K output tokens per response.
How does DeepSeek V4 Pro score on benchmarks?
DeepSeek V4 Pro scores 23.1 on the Artificial Analysis Intelligence Index (v5), ranking #18 of 21 models on SandBase. Source: Artificial Analysis, measured as DeepSeek V4 Pro 0813 (Max).
Which features does DeepSeek V4 Pro support?
DeepSeek V4 Pro supports reasoning, function calling, structured output. See Specifications above for the full list.
Do I need a separate DeepSeek account?
No. One SandBase API key and balance gives you access to DeepSeek V4 Pro and the other models in the catalog; you do not need to sign up with DeepSeek separately.