VENICE ATLAS · MODEL DOSSIER · DEEPSEEK V4.1 FLASH (1017)

Model overview

DeepSeek v4.1 Flash (1017)

Name: DeepSeek v4.1 Flash (1017)
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-1017 · 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

Benchmarks11Benchmark results

Benchmark results

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

Agents#738.56 rating Coding#1139.13 rating Vision#2232.24 rating General intelligence#1151.04 rating Multimodal#1134.96 rating Reasoning#1548.62 rating Tool Calling#730.89 rating

Agents3 results

Agents' Last Examagents-last-exam · agents

35.4%

ReportedOct 2026

AutomationBenchautomationbench · agents

60.5%

ReportedOct 2026

Program Benchprogram-bench · agents

29.1%

ReportedOct 2026

Coding2 results

DeepSWE 1.1deepswe-1.1 · code

77.0%

ReportedOct 2026

NL2Reponl2repo · code

68.2%

ReportedOct 2026

Reasoning3 results

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

42.6%

ReportedOct 2026

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

44.0%

ReportedOct 2026

Terminal-Bench 4.0terminal-bench-4.0 · reasoning

42.3%

ReportedOct 2026

Vision3 results

BabyVisionbabyvision · vision

92.5%

ReportedOct 2026

Chartographychartography · vision

83.0%

ReportedOct 2026

ZEROBenchzerobench · vision

51.0%

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-pro-0813DeepSeek V4 Pro 0813$1.65 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 ↗