skip to content
gigarouter gigarouter
models / text generation · coming soon

DeepSeek V4 Pro DSpark

deepseek-ai/DeepSeek-V4-Pro-DSpark

published Jun 2026 · updated Jun 2026

DeepSeek V4 Pro DSpark is a text-generation model that is a Mixture-of-Experts language model with speculative decoding for efficient inference, supporting million-token contexts.

status
coming soon
API providers
0
downloads / mo
9.4K
license
mit

specs

TaskText Generation
ArchitectureMixture-of-Experts (MoE) with Hybrid Attention (CSA + HCA), Manifold-Constrained Hyper-Connections
Parameters (Total)1.6T
Parameters (Activated)49B
Context Length1M tokens
LicenseMIT

best for

FAQ

What is DeepSeek V4 Pro DSpark best used for?

It excels at long-context tasks (up to 1M tokens), coding, complex reasoning, and agentic applications, with speculative decoding for faster inference.

How does the speculative decoding (DSpark) improve performance?

DSpark is a speculative decoding module that increases throughput by generating multiple candidate tokens per step, reducing latency for the same checkpoint.

What are the license terms for DeepSeek V4 Pro DSpark?

The model is released under the MIT License, allowing free use, modification, and distribution.

What input/output format does the model use?

It uses an OpenAI-compatible chat format; see the model's encoding folder for message-to-token conversion and parsing.

How can I call this model via the gigarouter API?

Use the gigarouter OpenAI-compatible endpoint with your API key, setting the model name to deepseek-ai/DeepSeek-V4-Pro-DSpark.

not yet live

We're benchmarking and onboarding DeepSeek V4 Pro DSpark as a hosted, OpenAI-compatible API. Sign in for free credit and be ready when it lands, or tell us you want it and we'll prioritize it.

related text generation models

compare all →