GLM-5.3 is live, the strongest open coding model in the world. Try it now
Sign Up
deepseek

deepseek-v4-pro-0813

Efficient 1.6T reasoning model with a lossless 1M-token context window.

deepseek 1M context
Get API Key View Pricing

Value rank

#12 of 18

intelligence per dollar in our catalogue

Context rank

#1 tied

1M token window

Benchmarks

Independent scores by Artificial Analysis, compared with the strongest models in our catalogue.

Intelligence index

glm-5.3
44.9
kimi-k3
43.8
glm-5.3-flash
41.9
qwen3.8-2.4t-a95b
40.3
deepseek-v4-pro-0813
36.3

Coding index

kimi-k3
76.2
glm-5.3
74.8
qwen3.8-2.4t-a95b
71.8
glm-5.3-flash
71.5
deepseek-v4-pro-0813
68.8

Best for

Where this model earns its keep.

Long-document analysis Coding and engineering Prompt-cached workloads

The numbers

Pricing is live from our platform. Prices per 1M tokens, zero data retention on every request.

Input price$2.00
Cache read price$0.50
Output price$4.00
Context window1M tokens
Intelligence / coding index36.3 / 68.8
GPQA / MMLU-Pro93% / -

Or consider

Close alternatives in the catalogue.

deepseek-v4-pro

Intelligence 36.3 · agentic -

deepseek-v4-flash-0731

Intelligence 34.5 · agentic -

glm-5.2

Intelligence 34 · agentic 99%

Quick start

OpenAI-compatible. Switch in one line.

# pip install openai
client = OpenAI(base_url="https://api.tensorx.ai/v1", api_key="tsx-...")
r = client.chat.completions.create(
    model="deepseek/deepseek-v4-pro-0813",
    messages=[{"role": "user", "content": "Hello"}],
)

Benchmark data from the Artificial Analysis Intelligence Index, measured independently. Pricing live from the TensorX platform. All inference on EU-sovereign infrastructure with zero data retention.