DeepSeek-V4.1-Flash is a multimodal Mixture-of-Experts model with a 552B-parameter backbone, activating just 8B parameters per token during prefill and 16B during decoding. It natively processes images and text, supports a 1M-token context window, and introduces a Causal Encoder-Decoder architecture with Compressed Sparse Attention 2 to make long-context inference more efficient. Configurable reasoning-effort levels let developers trade latency and cost for deeper deliberation. Compared with DeepSeek-V4-Flash-0731, it reduces the global KV-cache footprint by roughly 4x while delivering stronger coding, reasoning, and agentic performance.
5 providers serve this model. FastRouter routes each request to the best available one, and you can bring your own key for any of them.
deepinfra
togethertelnyx
alibaba
basetenRequest parameters you can send with this model.
Median throughput and time to first token per provider over the last week.
OpenAI-compatible. Point your SDK at FastRouter, or call the API directly.
<FASTROUTER_API_KEY> with your key · Get your key →Installdeepseek/deepseek-v4-flashDeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts large language model from DeepSeek with a 1M-token context window and strong general, coding, and reasoning performance. It is designed as a fast, low-cost frontier model suitable for long-context chat, agents, and tools. The Flash variant emphasizes high throughput and low latency while maintaining competitive reasoning quality.
deepseek/deepseek-v4-proDeepSeek-V4-Pro is a 1.6 trillion parameter Mixture-of-Experts (MoE) language model from DeepSeek AI, with 49 billion parameters activated per token and support for a 1 million token context window. It features a hybrid attention architecture combining Compressed Sparse Attention (CSA) and Heavily Compressed Attention (HCA), which reduces inference FLOPs to 27% and KV cache to 10% of DeepSeek-V3.2 at 1M context, enabling 83.5% MRCR comprehension. The model was pre-trained on over 32 trillion tokens using the Muon optimizer and a two-stage post-training process involving SFT, RL with GRPO, and on-policy distillation for domain-specific expertise.
deepseek/deepseek-v3.2DeepSeek-V3.2 is positioned as a next-generation “general-purpose + reasoning” model intended to be a daily driver at roughly frontier (GPT‑5-class) performance on broad tasks like coding, math, agents, and general chat. It is released in several variants (such as V3.2, V3.2-Exp, and V3.2-Speciale), sharing the same core architecture but targeting different trade‑offs between efficiency and maximum reasoning power.
deepseek-ai/DeepSeek-R1A frontier-level reasoning model with 671B total parameters (37B activated per token) that delivers performance comparable to OpenAI's o1 across mathematics, coding, and reasoning tasks. Licensed under MIT for free commercial use, it pioneered cold-start data techniques before reinforcement learning to achieve breakthrough capabilities.
deepseek/deepseek-v3.1DeepSeek V3.1 is an advanced open-source hybrid AI model designed to balance powerful reasoning with high-speed efficiency. It uniquely supports two inference modes—"Think" for deep reasoning and "Non-Think" for direct, lightweight tasks—making it versatile across use cases. Built with a mixture-of-experts architecture, it scales to 685B parameters while activating only 37B per token, enabling cost-effective performance. With a 128K context window, it can handle large documents, codebases, and complex multi-step workflows. DeepSeek V3.1 is optimized for tool use, agent-based applications, and enterprise deployment through open weights and developer-friendly APIs.
Side by side: price per provider, context window, benchmarks and speed.
Model scores sourced from ArtificialAnalysis