DeepSeek V4 Pro is an open-source chat model created by DeepSeek. It is a Mixture-of-Experts language model that takes text inputs and returns text outputs, designed for tasks such as coding, reasoning, and general conversation.
Input
Output
Context
1M
Max Output
384K
Parameters
1598.8B
Input Modalities
Output Modalities
Some values come from web research and may be incorrect. Report incorrect data
Bands compare this model with every model the same suite measured in our catalog.
Download 865 GB · Runs on vLLM v0.32.0 · 5 GGUF builds
| Precision | Weights | One request at 33K tokens | Smallest GPU that fits |
|---|---|---|---|
| FP16 / BF16 | 2978 GB | 3156 GB | 16x AMD Instinct MI325X (4096 GB) |
| INT8 | 1489 GB | 1591 GB | 8x AMD Instinct MI325X (2048 GB) |
| INT4 | 745 GB | 809 GB | 4x AMD Instinct MI325X (1024 GB) |
Computed by Inferbase from the 1,598,839,674,782 parameters in the creator's Hugging Face repository; one request adds its KV cache, activations and framework overhead, with the layer layout estimated from the parameter count.
Request deepseek-v4-pro and routing picks a build. Use a build's model ID to pin it.
| Build | What it is | Model ID |
|---|---|---|
| FP8 | 8-bit floating-point weights | deepseek-v4-pro:fp8 |
Public resources
Specification sources
As of Nov 14, 2026.
Answered from the facts on this page, with their sources.
DeepSeek V4 Pro has a context window of 1,048,576 tokens and a maximum output of 384,000 tokens (source: Creator or provider API). A provider may serve less; Inferbase routes on what each provider serves.
Yes. DeepSeek V4 Pro is an open-weight model under the MIT license. You can download and self-host it within the license terms.
DeepSeek V4 Pro has 1,598,839,674,782 parameters (1598.8B), as stated in the creator's Hugging Face repository.
Strengths: Open weights under a permissive license (mit); 1,048K token context window; In the top 25% on graduate-level science (GPQA) among measured models. Limitations: Below average on coding among measured models. Each is computed from the model's stated facts and benchmark results.
DeepSeek V4 Pro accepts Text and produces Text. The Capabilities card lists the API features it supports, such as function calling and structured output.
DeepSeek V4 Pro has published results from Artificial Analysis and Epoch AI. The Benchmarks card shows each score as reported, with its band among the models the same source measured. Scores are never combined across sources.
Yes. DeepSeek V4 Pro is available on Inferbase Managed through the OpenAI-compatible API as deepseek-v4-pro. Request it by name, or request auto and routing picks it when it fits the request best.
The weights take 2.98 TB at FP16 / BF16, 1.49 TB at INT8, 744.5 GB at INT4, computed from the 1,598,839,674,782 parameters its creator publishes. Each request adds its KV cache and the framework's overhead. The hardware section shows one request and the smallest GPU that fits; the GPU planner sizes it for your context length and traffic.
Start on the free plan with 5,000 requests a month, no card required.