DeepSeek V4 Flash 0423
deepseek-v4-flashDeepSeek-V4-Flashdeepseek-v4-flash-0423- 🆕 Efficiency-optimized member of DeepSeek's V4 preview series, released April 2026.
- 🧠 284B-parameter Mixture-of-Experts with only 13B active per token.
- 📏 One-million-token context window, now DeepSeek's default standard.
- 🔧 Hybrid attention pairs Compressed Sparse and Heavily Compressed Attention.
- ⚡ Tuned for fast, high-throughput, cost-efficient inference.
- 💬 Dual Thinking and Non-Thinking modes via one model.
- 🎯 Capable in reasoning, coding, function-calling, and agentic tool use.
- 🔒 Released under the permissive MIT license.
DeepSeek is a Chinese artificial intelligence company specializing in large language model development, founded in July 2023 by Liang Wenfeng. Based in Hangzhou, Zhejiang, the company is backed by High-Flyer, a prominent Chinese hedge fund also co-founded by Liang. DeepSeek…
Explore 7 more models by DeepSeek →DeepSeek V4 Flash is the lightweight half of DeepSeek's V4 preview series, launched alongside DeepSeek V4 Pro on April 24, 2026. Where the Pro model carries 1.6 trillion total parameters with 49 billion active, Flash uses a much smaller 284-billion-parameter Mixture-of-Experts design activating just 13 billion parameters per token — positioning it as DeepSeek's economical, high-throughput option. Both models share a one-million-token context window, which the company states is now the default across its services.
The V4 family introduces a new hybrid attention mechanism combining Compressed Sparse Attention and Heavily Compressed Attention, plus DeepSeek Sparse Attention, to cut long-context compute and memory cost. DeepSeek reports that, at the 1M-token setting, the Pro variant needs only 27% of single-token inference FLOPs and 10% of the KV cache compared with the prior-generation DeepSeek V3.2, illustrating the architectural efficiency gains this generation targets.
Both V4 models support Thinking and Non-Thinking modes and an OpenAI- and Anthropic-compatible API. DeepSeek notes that Flash's maximum-effort mode can reach reasoning quality comparable to Pro when given a larger thinking budget, though its smaller scale leaves it slightly behind on pure-knowledge tasks and the most complex agentic workflows.
The model targets advanced reasoning, software engineering, tool use, and enterprise assistants, and ships under the MIT license.
This About section is AI-generated from public sources via VeniceStats + Venice inference, with no human editing. It may contain inaccuracies.
| Seller | Reputation↓ | Routing | Input $/M | Cached $/M | Output $/M | Categories | API |
|---|---|---|---|---|---|---|---|
| ▲ Apex Ant 0x73b4…e736 | 71.90 | #1 | $0.00 | $0.00 | $0.00 | chat,fast,open-source,cheap,coding,privacy,reasoning,long-context,agents,free | openai-chat-completions |
| Venice.ai Proxy 0x1f22…18c9 | 70.55 | #4 | $0.069 | $0.014 | $0.1375 | chat,reasoning,coding,web-search | openai-chat-completions |
| D5V1N2 0xd5e7…7be0 | 67.45 | #2 | $0.04 | $0.04 | $0.12 | chat,reasoning,coding,fast,cheap,router,fallback,deepseek | openai-chat-completions |
| DeepArc 0xfc36…8842 | 65.84 | gated | $1.20 | $1.20 | $3.00 | — | — |
| Super Seeder 0xd19f…41f3 | 63.77 | #3 | $0.0683 | $0.0139 | $0.1361 | chat,coding,reasoning,tools,long-context,cheap | openai-chat-completions |
| Open Forge 0x1d90…b0aa | 58.60 | gated | $0.00 | $0.00 | $0.00 | chat,reasoning,coding,fast,free | openai-chat-completions |
| bartly.eth64.de 0x666e…4666 | 53.43 | gated | $0.0062 | $0.0012 | $0.0125 | chat,coding,reasoning,fast | openai-chat-completions |
| NovaRoute AI 0xc50d…ed7b | 50.00 | gated | $0.198 | $0.198 | $0.4455 | chat,coding,code,reasoning,tasks,deepseek,fast,value,surplus,openai-compatible,low-cost,verified,github,response-auth,base-usdc,monitored | openai-chat-completions |
| Open Ant 0xe4f6…5bc4 | 50.00 | gated | $0.138 | $0.028 | $0.275 | chat,coding,reasoning,tools,long-context,cheap | openai-chat-completions |
| Fire Ant 🔥🐜 0xbe05…bc5d | 50.00 | gated | $0.1189 | $0.0241 | $0.237 | chat,coding,fast,tools | — |
| Open Bird 0xc0f1…8183 | 50.00 | gated | $0.049 | $0.0098 | $0.098 | chat,coding | openai-chat-completions |
| Best 0x472f…69fd | 49.76 | gated | $0.0062 | $0.0012 | $0.0124 | chat,coding | openai-chat-completions |
| Hana Gateway ✅ 0x4ae1…117b | 45.41 | gated | $0.02 | $0.005 | $0.04 | chat,coding,fast,tools | openai-chat-completions |
| Meridian AI 0x8c8c…06f5 | 44.01 | gated | $0.0191 | $0.0191 | $0.0383 | chat,coding | openai-chat-completions |
| AntFeed 0xddb6…1442 | 36.49 | gated | $0.1232 | $0.1232 | $0.2464 | chat,fast | openai-chat-completions |
| antseed-neon-puma-944e 0x6650…944e | 35.09 | gated | $0.058 | $0.028 | $0.1194 | chat,coding,math | openai-chat-completions |
| uomi.ai 0x87df…48e3 | 34.47 | gated | $0.103 | $0.103 | $0.206 | chat,math,coding | openai-chat-completions |
| Leftermute 0x388b…5389 | 28.39 | gated | $0.0429 | $0.0429 | $0.0884 | chat,coding,json,tools | openai-chat-completions |
| Deep Node 0x668e…6cd0 | 27.64 | gated | $0.14 | $0.0028 | $0.28 | chat,coding,fast,tasks | openai-chat-completions |
| Jarvis 0x5beb…a1c9 | 27.49 | gated | $0.10 | $0.10 | $0.50 | chat,coding,research,fast | openai-chat-completions |
| Colony Router 0x8aa0…5d3f | 23.52 | gated | $0.50 | $0.50 | $1.50 | — | openai-chat-completions |
| minion0x 0x215e…e2e3 | 20.44 | gated | $0.08 | $0.02 | $0.31 | chat,coding,math,fast | openai-chat-completions |
| Xerxes Inference 0xdc73…65ce | 18.10 | gated | $0.05 | $0.02 | $0.10 | chat,code,reasoning | openai-responses |
| Apex TEE Test 0xe672…7955 | 15.22 | gated | $0.00 | $0.00 | $0.00 | chat,fast,open-source,cheap,coding,privacy,reasoning,long-context,agents | openai-chat-completions |
| deepseek 0x47f9…ccd7 | 12.58 | gated | $0.07 | $0.003 | $0.28 | chat,fast | openai-chat-completions |
| antseed-opal-marten-4af3 0x17f5…4af3 | 12.50 | gated | $10.00 | $10.00 | $10.00 | chat | openai-chat-completions |
| Skeffo Inference 0x1af8…e2b5 | 10.65 | gated | $0.15 | $0.15 | $0.30 | chat,reasoning,agent,function-calling | openai-chat-completions |
"Best price" and the seller table are live AntSeed catalog data (advertised $/1M tokens — or $ per generated image for unit-billed image models — not settled amounts). Reputation = buyer trust score (0-100, the AntSeed SDK's own formula). "Routing" = the SDK's default buyer routing (what the VPR desktop app ships with): a trust ≥ 60 gate on the effective reputation, then cheapest-first among routable sellers; live failover state (per-peer cooldowns) is buyer-side runtime and not included. Model knowledge (TLDR, provider, About) via the VeniceStats enrichment layer. Advertised catalog, not the model used in any specific purchase. "Usage on AntSeed" counts only settlements whose buyers share the per-model split on-chain (metadata v2/v3, opt-in), so every usage figure is a lower bound.