MMODELYST
Models/DeepSeek V4 Flash
MDL

DeepSeek V4 Flash

DeepSeek

Verified against Artificial Analysis · Jul 13, 2026
Capability
90
percentile index
Price /M
$0.14 / $0.28
in / out
Context
1M
tokens
Avg score
62.7
7 benchmarks
AA Intelligence
40.3
index
Speed
106 tok/s
TTFT 0.8s
Released
Apr 24, 2026
About

DeepSeek V4 Flash is a open-weights model in the DeepSeek family from DeepSeek. Benchmarked on 7 evals, averaging 62.7.

Benchmark scores · 7
avg 62.7 — higher is better
τ²-bench
95
GPQA Diamond
89.4
IFBench
79.2
AA Long-Context Reasoning
63
SciCode
44.9
Terminal-Bench Hard
35.6
Humanity's Last Exam
32.1
Details
PublisherDeepSeek
FamilyDeepSeek
Parameters
License
WeightsOpen
ReleasedApr 24, 2026
Performance & price
Output speed106 tok/s
Latency (TTFT)0.8s
First answer54s
Price in / out$0.14 / $0.28 per 1M
Blended price$0.175 / 1M
Coding index56.2

Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →

Capability over time

Append-only ledger — every observed change to this model's numbers.

API providers
Artificial Analysis$0.28/M