# DeepSeek: DeepSeek V4 Pro (Free)  Free    Rate Limit

deepseek/deepseek-v4-pro-free

[Chat](/content/platform/chat?model=deepseek/deepseek-v4-pro-free/index.html)

DeepSeek-V4-Pro is the flagship model of the DeepSeek V4 series, released as a preview and open-sourced alongside its efficiency-tier sibling V4-Flash. It is positioned as the performance-first tier in the V4 lineup, designed to push agentic capability, world knowledge, and reasoning performance to levels competitive with leading closed-source models.

The model introduces a new attention mechanism that performs compression along the token dimension, combined with DeepSeek Sparse Attention (DSA). The design makes a 1M context window the default across all official DeepSeek services while substantially reducing compute and memory overhead compared with prior approaches.

DeepSeek-V4-Pro has been specifically adapted and optimized for mainstream agent products such as Claude Code, OpenClaw, OpenCode, and CodeBuddy. According to DeepSeek, V4-Pro reaches the top tier among open-source models on Agentic Coding benchmarks, and is currently used internally at DeepSeek as the default Agentic Coding model—with internal evaluation reports describing a usage experience above Sonnet 4.5 and delivery quality close to Opus 4.6 in non-thinking mode, while still trailing Opus 4.6 in thinking mode. On world knowledge, it leads open-source models and trails only Gemini-Pro-3.1; on math, STEM, and competitive coding, it delivers results on par with top closed-source models.

The model supports both thinking and non-thinking modes, with the thinking mode exposing a reasoning_effort parameter (high / max) for complex agent workflows. It is available via App, Web, and API through the OpenAI ChatCompletions and Anthropic interfaces, with weights open-sourced on Hugging Face and ModelScope._

by [DeepSeek](/content/deepseek/index.html)Input typeOutput typePublish time2026-04-24

## Recent activity on DeepSeek V4 Pro (Free)

Tokens processed per day

## Throughput

(tokens/s)

| Providers | Min (tokens/s) | Max (tokens/s) | Avg (tokens/s) |
| --- | --- | --- | --- |
| DeepSeek | 29.91 | 32.31 | 31.37 |

## First Token Latency

(ms)

| Providers | Min (ms) | Max (ms) | Avg (ms) |
| --- | --- | --- | --- |
| DeepSeek | 2379 | 2477 | 2422.00 |

## Uptime stats for DeepSeek V4 Pro (Free)

Uptime stats for DeepSeek V4 Pro (Free) across all providers

Uptime

DeepSeek

( Percent )

Providers for DeepSeek V4 Pro (Free)

ZenMux Provider to the best providers that are able to handle your prompt size and parameters, with fallbacks to maximize uptime.

[**DeepSeek**](/content/provider/deepseek/index.html)

Latency

2.49

s

Throughput

31.01
tps

Uptime

100.00
%

Recent uptime

Apr 29, 2026 4:00 PM100.00%

Price

Input

$ 1.74$ 0/ M tokens

Output

$ 3.48$ 0/ M tokens

Cache read

$ 0.0145$ 0/ M tokens

Cache write 5m

-

Cache write 1h

-

Cache write

-

Web search

-

Image

-

Image input

-

Image output

-

Image cache

-

reasoning

-

Video

-

Audio

-

Audio cache read

-

Audio input

-

Audio & Video

-

Image search

-

Web search image

-

Model limitation

Context

1000.00K

Max output

384.00K

Supported Parameters

max_completion_tokens

-

temperature

-

top_p

-

frequency_penalty

-

presence_penalty

-

seed

-

logit_bias

-

logprobs

-

top_logprobs

-

response_format

-

stop

-

tools

tool_choice

-

parallel_tool_calls

-

Model Protocol Compatibility

OpenAI Chat Completions

OpenAI Responses

OpenAI Embeddings

-

Anthropic Messages

Google Gemini

-

Google Imagen

-

Google Video

-

Status Page

status page

## Sample code and API for DeepSeek V4 Pro (Free)

ZenMux normalizes requests and responses across providers for you.

[Create API Key](/content/platform/pay-as-you-go/index.html)

OpenAI: Python-SDK

OpenAI: cURL

Anthropic: Python-SDK

Anthropic: cURL

```python
from openai import OpenAI

client = OpenAI(
  base_url="https://zenmux.ai/api/v1",
  api_key="<ZENMUX_API_KEY>",
)

# Chat Completion
completion = client.chat.completions.create(
  model="deepseek/deepseek-v4-pro-free",
  messages=[\
    {\
      "role": "user",\
      "content": "What is the meaning of life?"\
    }\
  ]
)
print(completion.choices[0].message.content)

# Responses API
responses = client.responses.create(
  model="deepseek/deepseek-v4-pro-free",
  input="What is the meaning of life?"
)
print(responses)
```