Home  /  Models  /  DeepSeek V4.1 Flash
DeepSeek · DeepSeek V4

DeepSeek V4.1 Flash

DeepSeek V4.1 Flash by DeepSeek: League Score, pricing, context window and sourced benchmarks — the full tracked record.

75 Open weights $0.30 / $1.20 per 1M 1M context

League positions: #10 overall · #11 Reasoning Division · #3 Value Division · #1 Open-Weight Division. Score coverage: 55% of components measured. Count tokens & cost for DeepSeek V4.1 Flash · Estimate a workload cost

Specifications & pricing

MakerDeepSeek — lab profile
FamilyDeepSeek V4
ReleasedSep 10, 2026
StatusCurrent
WeightsOpen weights
LicenseMIT
Knowledge cutoffNot published
Context window1,000,000 tokens
Max output384,000 tokens
Modalities intext, image
Modalities outtext
API price (input)$0.30 per 1M tokens
API price (output)$1.20 per 1M tokens
Cached input$0.006 per 1M
Blended (3:1 in:out)$0.52 per 1M
Pricing sourceOfficial pricing page (checked Oct 14, 2026)
Output speed213 tokens/sec — Artificial Analysis, Oct 14, 2026
API accessDeepSeek API

Benchmark results

BenchmarkScoreSourceDateLink
GPQA Diamond90.9 / 100BenchLM GPQA leaderboardOct 14, 2026Source
LiveBench overall77.3 / 100LiveBenchOct 14, 2026Source

How its League Score is built

ComponentRawNormalisedWeightDateLink
LiveBench overall77.374.540%Oct 14, 2026Source
GPQA Diamond90.977.815%Oct 14, 2026Source

Normalised 0–100 against the tracked field; missing components redistribute their weight. Full rules on the methodology page.

Closest rivals

FAQ

How much does DeepSeek V4.1 Flash cost?

DeepSeek V4.1 Flash costs $0.30 per 1M input tokens and $1.20 per 1M output tokens on the first-party API (checked Oct 14, 2026).

What is the context window of DeepSeek V4.1 Flash?

DeepSeek V4.1 Flash accepts up to 1,000,000 tokens of context.

Is DeepSeek V4.1 Flash open source?

Yes — its weights are publicly downloadable (license: MIT).

Data verified Oct 14, 2026. Spotted an error? Every figure above links to its source.