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

qwen3-coder-30b-a3b-instruct

Optimized for programming and software development tasks

qwen 262K context
Get API Key View Pricing

Value rank

#4 of 23

intelligence per dollar in our catalogue

Context rank

#3 of 24

262K token window

Agentic strength

35%

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
qwen3-coder-30b-a3b-instruct
13.6

Coding index

glm-5.2
50.7
deepseek-v4-pro
47.5
kimi-k2.6
47.1
minimax-m3
43.4
qwen3-coder-30b-a3b-instruct
19.4

Agentic (tau2-bench)

deepseek-v4-pro
96.2%
kimi-k2.6
95.9%
minimax-m3
88.9%
qwen3-coder-30b-a3b-instruct
34.5%

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$0.06
Cache read price$0.02
Output price$0.25
Context window262K tokens
Intelligence / coding index13.6 / 19.4
Agentic: tau2 / terminal-bench35% / 15%
GPQA / MMLU-Pro52% / 71%

Or consider

Close alternatives in the catalogue.

qwen3-vl-235b-a22b-instruct

Intelligence 14.3 · agentic 35%

qwen3-235b-a22b-2507

Intelligence 18.2 · agentic 33%

deepseek-r1-0528

Intelligence 20.1 · agentic 37%

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="qwen/qwen3-coder-30b-a3b-instruct",
    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.