OpenAI compatible API. Attested gateway. Public status.
Qwen: Qwen3.5 397B A17B vs Z.ai: GLM 4.6
Compare Qwen: Qwen3.5 397B A17B and Z.ai: GLM 4.6 by providers, context, price, and TrustedRouter route support.
1 URLbase_url migration
100smodels and routes
0prompt logs by default
Compare routesProviders, price, context, and policy posture in one view.
Use auto when uptime mattersKeep a primary model and let fallback handle provider failures.
Same API shapeUse the OpenAI client and set the model you want.
Practical read
Z.ai: GLM 4.6 has the lower cheapest prompt+completion route on TrustedRouter. Qwen: Qwen3.5 397B A17B has more provider fallback routes, while Qwen: Qwen3.5 397B A17B has the larger context window. Current TrustedRouter probes show Qwen: Qwen3.5 397B A17B with the lower p50 TTFT.
$3.795/1MQwen: Qwen3.5 397B A17B cheapest route
$2.398/1MZ.ai: GLM 4.6 cheapest route
3885 msQwen: Qwen3.5 397B A17B measured p50 TTFT
4910 msZ.ai: GLM 4.6 measured p50 TTFT
Qwen: Qwen3.5 397B A17BZ.ai: GLM 4.6
Model id
qwen/qwen3.5-397b-a17bz-ai/glm-4.6
PublisherDeepInfraZ.AI
AI IQ
—
—
Context262,144 tokens204,800 tokens
Provider routes1410
Cheapest route$3.795/1M$2.398/1M
Privacy posturehas provider E2EE routehas provider E2EE route
Modes
chat
chat
Qwen: Qwen3.5 397B A17B routes
- Overview14 endpoints
- PricingPrompt and completion rates
- BenchmarksTrustedRouter and external sources
- ProvidersAll serving providers
Z.ai: GLM 4.6 routes
- Overview10 endpoints
- PricingPrompt and completion rates
- BenchmarksTrustedRouter and external sources
- ProvidersAll serving providers
Production choice
Pick a default model. Keep fallback enabled.
TrustedRouter is useful when you know the model you want, but still need provider rollover, budget limits, usage records, and a prompt path you can verify.
OpenAI clientPython
client = OpenAI(
base_url="https://api.trustedrouter.com/v1",
api_key="sk-tr-v1-..."
)
response = client.chat.completions.create(
model="qwen/qwen3.5-397b-a17b",
messages=messages,
)