GLM-5.2, MiniMax-M3 and Kimi K2.7 are now live. Try them now
Sign Up
deepseek

deepseek-v3.2

Well-rounded DeepSeek model for everyday reasoning, coding, and chat.

deepseek 160K context
Get API Key View Pricing

Value rank

#6 of 23

intelligence per dollar in our catalogue

Context rank

#6 of 24

160K token window

Agentic strength

79%

tau2-bench tool-use success

Benchmarks

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

Intelligence index

glm-5.2
51.1
minimax-m3
44.4
deepseek-v4-pro
44.3
kimi-k2.6
42.8
deepseek-v3.2
24.7

Coding index

glm-5.2
50.7
deepseek-v4-pro
47.5
kimi-k2.6
47.1
minimax-m3
43.4
deepseek-v3.2
34.6

Agentic (tau2-bench)

deepseek-v4-pro
96.2%
kimi-k2.6
95.9%
minimax-m3
88.9%
deepseek-v3.2
78.9%

Best for

Where this model earns its keep.

Prompt-cached workloads

The numbers

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

Input price$0.30
Cache read price$0.08
Output price$0.50
Context window160K tokens
Intelligence / coding index24.7 / 34.6
Agentic: tau2 / terminal-bench79% / 33%
GPQA / MMLU-Pro75% / 84%

Or consider

Close alternatives in the catalogue.

qwen3.5-9b

Intelligence 25 · agentic 87%

nemotron-3-super-120b-a12b

Intelligence 25.4 · agentic 68%

gpt-oss-120b

Intelligence 23.8 · agentic 66%

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-v3.2",
    messages=[{"role": "user", "content": "Hello"}],
)

Benchmark data from the Artificial Analysis Intelligence Index v4.1, measured independently. Pricing live from the TensorX platform. All inference on EU-sovereign infrastructure with zero data retention.