EvalLedger
LeaderboardCompareToken CalculatorModel ReleasesVersion seriesChangelog
DeepSeek·flash·v4.1-flash-0910

DeepSeek V4.1-Flash 0910

Released: 2026-09-10Updated: 2026-10-19
Run your usage →

Benchmark scores

GPQA Diamond90.9%
HLE(39.1 on text-only subset)36.8%
Codeforces (Rating)3471
MathArena Apex65.6%
Terminal-Bench 2.190.6%
Terminal-Bench 3.030%
Terminal-Bench 4.031.2%
DeepSWE v1.174.2%
ProgramBench20.3%
NL2Repo-Bench65.4%
CyberGym88.1%
SEC-Bench Pro62.8%
ExploitGym15.3%
HLE (w/tools)63.9%
Automation-Bench54.8%
Agents' Last Exam31.8%
Chartography (w/tools)78.9%
BabyVision (w/tools)89.6%
ZeroBench-main (w/tools)49%

Pricing

Input$0.300
Output$1.20
Cached input$0.0060
Source · verified 2026-10-20
Run your usage →

Comparisons

Claude Opus 5 vs DeepSeek V4.1-Flash 0910GPT 5.6-Sol vs DeepSeek V4.1-Flash 0910Gemini 3.1 Pro vs DeepSeek V4.1-Flash 0910Grok 4.7 vs DeepSeek V4.1-Flash 0910DeepSeek V4.1-Flash 0910 vs GLM 5.3DeepSeek V4.1-Flash 0910 vs Kimi K3

Model series

DeepSeek V4

4 versions

2026-09-10

DeepSeek V4.1-Flash 0910: $0.30 / $1.20 at peak, and a cache read at 2% of input

DeepSeek V4.1-Flash 0910 — the 2026-09-10 launch checkpoint — costs $0.30 per 1M input and $1.20 per 1M output at peak, $0.15 / $0.60 off-peak, and reads cached input at $0.006, with 19 verified benchmark scores. The API now serves the newer 1017 checkpoint, tracked separately.

EvalLedger

Pricing, benchmarks, and version history for every major LLM.

Product

LeaderboardCompareToken Calculator

Resources

X (Twitter)Model ReleasesChangelog

Legal

TermsPrivacyContact

© 2026 EvalLedger. © 2026 EvalLedger. All rights reserved.