VENICE ATLAS · MODEL DOSSIER · DEEPSEEK V4 PRO 0813

Model overview

DeepSeek V4 Pro 0813

Name: DeepSeek V4 Pro 0813
Brand: venice.ai
Price: 1.6500 USD
Availability: InStock

DeepSeek V4 Pro is a 1.6T-parameter Mixture-of-Experts model with 49B active parameters and a 1M-token context window. Built for advanced reasoning, coding, and long-horizon agentic workflows with a hybrid attention system for efficient long-context processing.

deepseek-v4-pro-0813 · venice.ai

Text · Venice catalog$1.65 per 1M tokensPrice on Venice AI

ModalityTextOn Venice AI

Primary price$1.65 per 1M tokensper 1M tokens

Context window1MMax tokens

Benchmarks12Benchmark results

Benchmark results

See the tests behind each score. They use the benchmark’s original scoring scale.

Agents#1735.25 rating Coding#1638.15 rating Vision#2032.81 rating General intelligence#1450.26 rating Math#1638.80 rating Reasoning#1648.54 rating Safety#717.79 rating Tool Calling#1528.00 rating

Agents3 results

Agents' Last Examagents-last-exam · agents

25.7%

ReportedOct 2026

AutomationBenchautomationbench · agents

31.8%

ReportedOct 2026

Toolathlontoolathlon · agents

74.1%

ReportedOct 2026

Coding5 results

CyberGymcybergym · code

83.3%

ReportedOct 2026

DeepSWEdeepswe · code

62.7%

ReportedOct 2026

DSBench-FullStackdsbench-fullstack · code

71.1%

ReportedOct 2026

DSBench-Harddsbench-hard · code

67.2%

ReportedOct 2026

NL2Reponl2repo · code

61.5%

ReportedOct 2026

Reasoning4 results

Humanity's Last Examhumanity's-last-exam · reasoning

60.0%

ReportedAug 2026

Humanity's Last Exam (no tools, text-only)humanity's-last-exam-(no-tools,-text-only) · reasoning

42.7%

ReportedOct 2026

Humanity's Last Exam (with tools, text-only)humanity's-last-exam-(with-tools,-text-only) · reasoning

60.0%

ReportedOct 2026

Terminal-Bench 2.1terminal-bench-2.1 · reasoning

87.9%

ReportedOct 2026

Learn what each benchmark measures ↗

Pricing detail

Input price per 1M tokens: $1.65
Output price per 1M tokens: $4.95
Cache read price per 1M tokens: $0.17
Blended price per 1M tokens (50/50): $3.30

Prices are published by Venice AI. Venice model page ↗

Capabilities

ReasoningFunction callingWeb search

Endpoint metadata

Privacy: private
Quantization: not-available
Maximum completion tokens: 33K
Uncensored: No
Beta: No
Mapping confidence: 100.0%

View model source ↗

All capabilities

Quantization: not-available
Supports E2 E E: No
Supports Vision: No
Supports X Search: No
Optimized For Code: Yes
Supports Log Probs: No
Supports Reasoning: Yes
Supports Web Search: Yes
Supports Audio Input: No
Supports Video Input: No
Default Reasoning Effort: high
Reasoning Effort Options: none, low, high, max
Supports Multiple Images: No
Supports Response Schema: Yes
Supports Tee Attestation: No
Supports Function Calling: Yes
Supports Reasoning Effort: Yes

Traits

default_code

Related models

More from deepseek

deepseek-v4-1-flash-1017DeepSeek v4.1 Flash (1017)$0.30 input per 1M tokens ↗deepseek-v3.2DeepSeek V3.2$0.33 input per 1M tokens ↗deepseek-v4-1-flashDeepSeek V4.1 Flash$0.30 input per 1M tokens ↗