VENICE ATLAS · MODEL DOSSIER · DEEPSEEK V4 FLASH 0423

Model overview

DeepSeek V4 Flash 0423

Name: DeepSeek V4 Flash 0423
Brand: venice.ai
Price: 0.1380 USD
Availability: InStock

DeepSeek V4 Flash is an efficiency-optimized 284B-parameter Mixture-of-Experts model with 13B active parameters and a 1M-token context window. Tuned for fast inference and high-throughput workloads while maintaining strong reasoning and coding performance.

deepseek-v4-flash · venice.ai

Text · Venice catalog$0.14 per 1M tokensPrice on Venice AI

ModalityTextOn Venice AI

Primary price$0.14 per 1M tokensper 1M tokens

Context window1MMax tokens

Benchmarks19Benchmark results

Benchmark results

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

Factuality#511.70 rating Finance#1529.11 rating Frontend Development#1524.95 rating Healthcare#2129.11 rating Legal#1229.11 rating Math#2536.79 rating

Agents1 result

Toolathlontoolathlon · agents

43.5%

ReportedOct 2026

Factuality1 result

SimpleQAsimpleqa · factuality

28.9%

ReportedOct 2026

General intelligence1 result

CSimpleQAcsimpleqa · general

73.2%

ReportedOct 2026

Language1 result

MMLU-Prommlu-pro · language

86.4%

ReportedOct 2026

Long Context2 results

CorpusQA 1Mcorpusqa-1m · long_context

59.3%

ReportedOct 2026

MRCR 1Mmrcr-1m · long_context

76.9%

ReportedOct 2026

Math4 results

CodeForcescodeforces · math

93.9%

ReportedOct 2026

HMMT Feb 26hmmt-feb-26 · math

91.9%

ReportedOct 2026

IMO-AnswerBenchimo-answerbench · math

85.1%

ReportedOct 2026

MathArena Apexmatharena-apex · math

72.1%

ReportedOct 2026

Reasoning9 results

BrowseCompbrowsecomp · reasoning

53.5%

ReportedOct 2026

GPQAgpqa · reasoning

87.4%

ReportedOct 2026

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

40.3%

ReportedOct 2026

LiveCodeBenchlivecodebench · reasoning

88.4%

ReportedOct 2026

MCP Atlasmcp-atlas · reasoning

67.4%

ReportedOct 2026

SWE-bench Multilingualswe-bench-multilingual · reasoning

70.2%

ReportedOct 2026

SWE-Bench Proswe-bench-pro · reasoning

52.3%

ReportedOct 2026

SWE-Bench Verifiedswe-bench-verified · reasoning

78.6%

ReportedOct 2026

Terminal-Bench 2.0terminal-bench-2 · reasoning

56.6%

ReportedOct 2026

Learn what each benchmark measures ↗

Pricing detail

Input price per 1M tokens: $0.14
Output price per 1M tokens: $0.28
Cache read price per 1M tokens: $0.0280
Blended price per 1M tokens (50/50): $0.21

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: low
Reasoning Effort Options: none, low, medium, high
Supports Multiple Images: No
Supports Response Schema: Yes
Supports Tee Attestation: No
Supports Function Calling: Yes
Supports Reasoning Effort: Yes

Related models

More from deepseek

deepseek-v4-1-flash-1017DeepSeek v4.1 Flash (1017)$0.30 input per 1M tokens ↗deepseek-v4-pro-0813DeepSeek V4 Pro 0813$1.65 input per 1M tokens ↗deepseek-v3.2DeepSeek V3.2$0.33 input per 1M tokens ↗