VENICE ATLAS · MODEL DOSSIER · DEEPSEEK V4.1 FLASH

Model overview

DeepSeek V4.1 Flash

Name: DeepSeek V4.1 Flash
Brand: venice.ai
Price: 0.3000 USD
Availability: InStock

DeepSeek V4.1 Flash is a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window. It natively processes images and text, with strong reasoning, coding, and agentic performance.

deepseek-v4-1-flash · venice.ai

Text · Venice catalog$0.30 per 1M tokensPrice on Venice AI

ModalityTextOn Venice AI

Primary price$0.30 per 1M tokensper 1M tokens

Context window1MMax tokens

Benchmarks20Benchmark results

Benchmark results

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

Agents#1038.16 rating Biology#2132.97 rating Chemistry#2532.97 rating Coding#740.30 rating Vision#3030.49 rating General intelligence#1649.77 rating Math#3135.19 rating Multimodal#2032.26 rating Physics#2632.97 rating Reasoning#2047.73 rating Safety#324.47 rating Tool Calling#531.75 rating

Agents5 results

Agents' Last Examagents-last-exam · agents

31.8%

ReportedOct 2026

AutomationBenchautomationbench · agents

54.8%

ReportedOct 2026

ExploitGymexploitgym · agents

15.3%

ReportedOct 2026

Program Benchprogram-bench · agents

20.3%

ReportedOct 2026

SEC-bench Prosec-bench-pro · agents

62.8%

ReportedOct 2026

Coding3 results

CyberGymcybergym · code

88.1%

ReportedOct 2026

DeepSWE 1.1deepswe-1.1 · code

74.2%

ReportedOct 2026

NL2Reponl2repo · code

64.0%

ReportedOct 2026

Math2 results

CodeForcescodeforces · math

100.0%

ReportedOct 2026

MathArena Apexmatharena-apex · math

65.6%

ReportedOct 2026

Reasoning7 results

GPQAgpqa · reasoning

90.9%

ReportedOct 2026

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

36.8%

ReportedOct 2026

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

39.1%

ReportedOct 2026

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

63.9%

ReportedOct 2026

Terminal-Bench 2.1terminal-bench-2.1 · reasoning

90.6%

ReportedOct 2026

Terminal-Bench 3.0terminal-bench-3.0 · reasoning

30.0%

ReportedOct 2026

Terminal-Bench 4.0terminal-bench-4.0 · reasoning

31.2%

ReportedOct 2026

Vision3 results

BabyVisionbabyvision · vision

89.6%

ReportedOct 2026

Chartographychartography · vision

78.9%

ReportedOct 2026

ZEROBenchzerobench · vision

49.0%

ReportedOct 2026

Learn what each benchmark measures ↗

Pricing detail

Input price per 1M tokens: $0.30
Output price per 1M tokens: $1.20
Cache read price per 1M tokens: $0.0075
Blended price per 1M tokens (50/50): $0.75

Prices are published by Venice AI. Venice model page ↗

Capabilities

ReasoningFunction callingVisionWeb search

Endpoint metadata

Privacy: private
Quantization: fp8
Maximum completion tokens: 131K
Uncensored: No
Beta: No
Mapping confidence: 100.0%

View model source ↗

All capabilities

Max Images: 10
Quantization: fp8
Supports E2 E E: No
Supports Vision: Yes
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: Yes
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 ↗