ModelsCompareBest forBenchmarksStatusPricingAPI

DeepSeek V4.1 Flash

DeepSeek·Operational·Released 2026-09-10textvision
Context1,000k
Max output384k
Input / 1M$0.14 ↗
Output / 1M$0.28 ↗
Cached in$0.0028
Benchmarks3

Benchmarks

Cited public sources · rank is exact-benchmark, apples-to-apples

DeepSWE v1.1#1/1374.2% ↗
GPQA Diamond#19/7090.9% ↗
Terminal-Bench 2.1#1/1790.6% ↗

Compare

vs GPT-6 Astravs GPT-5.6 Solvs GPT-5.6 Terravs GPT-5.6 Lunavs Claude Fable 5.1vs Claude Opus 5vs Claude Sonnet 5vs Claude Haiku 4.5

More from DeepSeek

DeepSeek V4 ProDeepSeek V3.2DeepSeek R1DeepSeek V3

Access DeepSeek V4.1 Flash and every other model through one endpoint with automatic failover: Respan gateway.