Pricing per million tokens, context window, capabilities — pulled from each provider's public docs. All 2 are available via the same AIgateway OpenAI-compatible endpoint; flip the model string to switch.
Alibaba's Qwen 3.5 is a 397B-parameter mixture-of-experts model with 17B active parameters, offering strong reasoning capabilities with efficient inference.
Claude Sonnet 4.6 is Anthropic's latest balanced model offering strong coding, reasoning, and agentic capabilities with improved instruction following.
Source: each provider's published benchmarks. Higher is better. Run an eval to compare on your own data.
from openai import OpenAI
client = OpenAI(
base_url="https://api.aigateway.sh/v1",
api_key="sk-aig-...",
)
# Qwen 3.5 397B A17B
client.chat.completions.create(
model="alibaba/qwen3.5-397b-a17b",
messages=[{"role":"user","content":"hello"}],
)
# Claude Sonnet 4.6
client.chat.completions.create(
model="anthropic/claude-sonnet-4.6",
messages=[{"role":"user","content":"hello"}],
)