WWhichAITry via Vercel AI Gateway
Models/Alibaba
Alibaba · released 2025-10open

Qwen 3 Coder

Open-weights coding specialist.

Try via Vercel AI GatewayTry at AlibabaDocs
context
128K
output max
16K
input /M
$0.50
output /M
$1.50
modalities
T
Verdict

What it's actually good at

Strengths

  • +Coding-tuned
  • +Open weights
  • +Affordable

Weaknesses

  • −Narrower general-purpose strength

Our scores

reasoning
7.0
coding
9.0
writing
6.0
speed
8.0
value
10.0
Open-weights model fine-tuned for code. Competitive with closed-weights coding leaders on many benchmarks.
best for:codingCheapest AI models for bulk workloads
Pricing

Cost at common volumes

Monthly volumeInputOutputEst. monthly
Side project1M tok0.3M tok$0.95
Growing app50M tok15M tok$47.50
Production500M tok150M tok$475.00
Scale5000M tok1500M tok$4750.00

Estimates assume uncached input. Prompt caching and batch APIs can cut this by 50–90% for many workloads. Use the calculator →

Head-to-head

Compare Qwen 3 Coder

vs OpenAI
GPT-5 Mini
200K context · $0.40 / $1.60
vs Meta
Llama 4 70B
128K context · $0.60 / $0.60
vs DeepSeek
DeepSeek V3
128K context · $0.27 / $1.10
vs OpenAI
GPT-OSS 20B
128K context · $0.15 / $0.60