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 betterThe research behind this model
all papers mentioning it →Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent▲ 98 on HF · Jun 29, 2026FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention▲ 61 on HF · Jun 8, 2026K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts▲ 55 on HF · Jun 1, 2026DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation▲ 31 on HF · Jul 6, 2026AutoTrainess: Teaching Language Models to Improve Language Models Autonomously▲ 23 on HF · Jun 30, 2026
Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.
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 →
History
full ledger →Capability over time
Append-only ledger — every observed change to this model's numbers.
API providers
Artificial Analysis$0.28/M