DeepSeek V4 Pro 0813
deepseek/deepseek-v4-pro-0813DeepSeek V4 Pro 0813 is the pinned GA release of DeepSeek V4 Pro from August 2026, for workloads that need a fixed version. It keeps V4 Pro's 1.6T-parameter mixture-of-experts design and 1M-token context, with thinking and non-thinking modes, tool calls and JSON output, and DeepSeek reports much stronger agent performance than the April preview, especially in production. DeepSeek has said it will keep serving V4 Pro alongside V4.1 Flash.
- Input price
- $0.99
$1.32USD / 1M tokens - Output price
- $2.97
$3.96USD / 1M tokens - Context window
- 1M
- Max output
- 384K
Try the model
Playground
Try a prompt
Your response will appear here
Choose an example or write a prompt, then click Run.
Model card
Specifications
Pricing
- Input
- $0.99 / 1M tokens
- Output
- $2.97 / 1M tokens
- Cache read
- $0.03 / 1M tokens
Context & modalities
- Context window
- 1,048,576 tokens
- Max output
- 384,000 tokens
- Input
- Text
- Output
- Text
Capabilities
- Chat
- Supported
- Vision
- Not supported
- Reasoning
- Supported
- Structured output
- Supported
- Function calling
- Supported
- Audio input
- Not supported
Access
- Provider
- DeepSeek
- Model ID
- deepseek/deepseek-v4-pro-0813
- Execution
- sync
- Base URL
- https://api.sandbase.ai
- API
- Chat Completions API
- Endpoint
- /v1/chat/completions
Independent evaluations
Benchmarks
Scores on standardized evaluations, compared with other models on SandBase.
Metrics sourced from Artificial Analysis · Intelligence Index v4.3
Start building
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/chat/completions" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "deepseek/deepseek-v4-pro-0813",
"messages": [
{
"role": "user",
"content": "Hello"
}
],
"max_tokens": 2048
}
SANDBASE_JSON
)
printf '%s\n' "$result"Choose your model
Compare models
| Model | Context | Input / 1M | Output / 1M | Released |
|---|---|---|---|---|
DeepSeek V4 Pro 0813This model DeepSeek | 1M | $0.99 | $2.97 | Aug 12, 2026 |
DeepSeek | 1M | $0.30 | $1.20 | Sep 10, 2026 |
DeepSeek | 1M | $0.30 | $1.20 | Aug 21, 2026 |
DeepSeek | 1M | $0.30 | $1.20 | Jul 31, 2026 |
DeepSeek | 1M | $1.32 | $3.96 | Apr 24, 2026 |
DeepSeek | 1M | $0.30 | $1.20 | Apr 24, 2026 |
Questions
FAQ
How do I call DeepSeek V4 Pro 0813 through SandBase?
Create a SandBase API key, then send requests with the model ID "deepseek/deepseek-v4-pro-0813" 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 0813 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 0813?
1M tokens of context, with up to 384K output tokens per response.
How does DeepSeek V4 Pro 0813 score on benchmarks?
DeepSeek V4 Pro 0813 scores 36.0 on the Artificial Analysis Intelligence Index (v4.3), ranking #31 of 84 models on SandBase; Coding Index 68.8, Agentic Index 41.3. Source: Artificial Analysis, measured as DeepSeek V4 Pro 0813 (Max).
Which features does DeepSeek V4 Pro 0813 support?
DeepSeek V4 Pro 0813 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 0813 and the other models in the catalog; you do not need to sign up with DeepSeek separately.