Pricing, context window, capabilities, and release date — pulled from each provider's public docs. Both are available via the same AIgateway OpenAI-compatible endpoint; flip the model string to switch.
Both models stream in parallel through your own AIgateway key. Tokens, latency, and cost update as they arrive.
| Qwen 3.5 397B A17B alibaba/qwen3.5-397b-a17b | Qwen3-30b-A3b-Fp8 qwen/qwen3-30b-a3b-fp8 | |
|---|---|---|
| Provider | Alibaba | Alibaba Qwen |
| Family | Qwen | Qwen |
| Modality | text | text |
| Context window | 262,144 tok | 131,072 tok |
| Max output | 4,096 tok | 4,096 tok |
| Released | 2026-05-22 | 2025-04-30 |
| Input price | $0.600 /1M | $0.250 /1M |
| Output price | $3.60 /1M | $0.500 /1M |
| Cache read | — | — |
| Tools | yes | — |
| Streaming | yes | yes |
| Vision | — | — |
| JSON mode | yes | — |
| Reasoning | yes | — |
| Prompt caching | — | — |
Alibaba's Qwen 3.5 is a 397B-parameter mixture-of-experts model with 17B active parameters, offering strong reasoning capabilities with efficient inference.
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support.
# pip install aigateway-py openai
# aigateway-py: sub-accounts, evals, replays, jobs, webhook verify.
# openai SDK: chat/embeddings/images/audio — drop-in compat per our SDK's own guidance.
from openai import OpenAI
client = OpenAI(
base_url="https://api.aigateway.sh/v1",
api_key="sk-aig-...",
)
# Try Qwen 3.5 397B A17B
client.chat.completions.create(
model="alibaba/qwen3.5-397b-a17b",
messages=[{"role":"user","content":"hello"}],
)
# Try Qwen3-30b-A3b-Fp8 — same client, same key
client.chat.completions.create(
model="qwen/qwen3-30b-a3b-fp8",
messages=[{"role":"user","content":"hello"}],
)