DeepSeek V4 Flash
Efficiency-optimized variant of DeepSeek V4. 284B MoE / 13B active, 1M context, ultra-low pricing for high-throughput workloads.
DeepSeek V4 Flash is text & chat AI model from DeepSeek, priced at €0.000 per 1M input tokens with a 1.0M tokens context window.
About this model
0.7
Pricing
API Integration
Use our OpenAI-compatible API to integrate DeepSeek V4 Flash into your application.
npm install railwailimport railwail from "railwail";
const rw = railwail("YOUR_API_KEY");
// Simple — just pass a string
const reply = await rw.run("deepseek-v4-flash", "Hello! What can you do?");
console.log(reply);
// With message history
const reply2 = await rw.run("deepseek-v4-flash", [
{ role: "system", content: "You are a helpful assistant." },
{ role: "user", content: "Explain quantum computing simply." },
]);
console.log(reply2);
// Full response with usage info
const res = await rw.chat("deepseek-v4-flash", [
{ role: "user", content: "Hello!" },
], { temperature: 0.7, max_tokens: 500 });
console.log(res.choices[0].message.content);
console.log(res.usage);Deep dive — DeepSeek AI's DeepSeek V4 Flash
DeepSeek AI is a Chinese AI research lab founded in 2023 by Liang Wenfeng, founder of the High-Flyer quantitative hedge fund. The lab is funded primarily by High-Flyer's profits. Its mission is open frontier AI, with all flagship models released with open weights. Major releases include DeepSeek LLM (2023), DeepSeek-V2 (May 2024), DeepSeek-V3 (December 2024), DeepSeek-R1 (January 2026), DeepSeek V3.1 (early 2026) and the DeepSeek V4 family (April 24, 2026), comprising V4-Pro and V4-Flash. DeepSeek is credited with popularising large-scale Reinforcement Learning from Verifiable Rewards and consistently tops open-weights leaderboards.
Visit DeepSeek AI →DeepSeek-V4-Flash was released April 24, 2026 as the efficiency-optimized sibling of V4-Pro. It is a Sparse MoE Transformer with 284B total parameters and 13B activated per token, retaining the full 1M-token native context window and 384K-token max output of the Pro variant at significantly lower inference cost. The model uses the same DeepSeek architectural stack: Multi-head Latent Attention (MLA), DeepSeekMoE with fine-grained expert specialization and shared experts, and FP8 mixed-precision training. Post-training combined supervised fine-tuning, RLVR on math/code/tool-use trajectories, and heavy distillation from the V4-Pro teacher model. V4 Flash is published with open weights under a permissive license and is designed for production-scale RAG, agentic loops and high-throughput workloads. At $0.112 input / $0.224 output per million tokens it undercuts every Western frontier model by an order of magnitude.
- Parameters
- 284B total / 13B active per token
- Context
- 1.0M tokens
- 1M token native context window with 384K max output
- 284B MoE / 13B active parameters
- Ultra-low pricing ($0.112 / $0.224 per million tokens)
- Distilled from DeepSeek V4-Pro teacher model
- FP8-trained for compute efficiency
- Multi-head Latent Attention for memory-efficient long context
- Function calling and structured JSON output
- Strong on math, STEM and coding for its size
- Available via DeepSeek API, OpenRouter, Together and self-hosted with vLLM/SGLang
- Open weights under a permissive license
- Best for: production agents, RAG pipelines, high-throughput data extraction, on-premise inference under tight cost budgets.
Pretrained on the same multi-trillion-token mixture as V4-Pro. Post-training combines supervised fine-tuning, RLVR and distillation from the V4-Pro teacher model. Knowledge cutoff approximately early 2026.
License: Open weights under a permissive license that allows commercial use. Hosted API access via deepseek.com.
Known limitations
- Below V4-Pro on the hardest reasoning and coding benchmarks
- Light built-in safety alignment relative to Western frontier models
- No native vision or audio input (text-only)
- Older deepseek-chat / deepseek-reasoner endpoints will be deprecated July 24, 2026
- Some Chinese-language safety constraints apply
Frequently asked questions
Related Models
View all Text & ChatBio_ClinicalBERT
The original Bio_ClinicalBERT from Alsentzer et al., a BERT model initialized from BioBERT and further pretrained on all MIMIC-III clinical notes. Served as a fill-mask endpoint it predicts masked tokens in clinical text and produces clinical embeddings. It is the standard encoder backbone behind many downstream clinical NLP fine-tunes.
Biomedical NER (all entities)
Token-classification model from d4data that tags 84 biomedical entity types in clinical and medical text, including disease, sign, symptom, medication, dosage, lab value, body part and procedure. Trained on the Maccrobat clinical case corpus on a DistilBERT base, so it runs cheaply for high-volume tagging.
Claude Opus 4
Anthropic's most powerful model. Exceptional at complex analysis, agentic tasks, and extended reasoning.
Claude Opus 4.8
Anthropic's most capable Opus-tier model. State of the art on long-horizon agentic work, coding and knowledge tasks, with a 1M-token context window at standard pricing.
Start using DeepSeek V4 Flash today
Get started with free credits. No credit card required. Access DeepSeek V4 Flash and 100+ other models through a single API.