OpenAI compatible API · Attested · Public status
Qwen: Qwen3.5 397B A17B vs Thinking Machines: Inkling
Compare Qwen: Qwen3.5 397B A17B and Thinking Machines: Inkling by providers, context, price, and TrustedRouter route support.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
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
Qwen: Qwen3.5 397B A17B has the lower cheapest prompt+completion route on TrustedRouter. Qwen: Qwen3.5 397B A17B has more provider fallback routes, while Thinking Machines: Inkling has the larger context window. Probe-backed speed data is shown when enough recent samples exist.
$2.97675/1MQwen: Qwen3.5 397B A17B cheapest route
$5.3025/1MThinking Machines: Inkling cheapest route
not enough dataQwen: Qwen3.5 397B A17B measured p50 TTFT
not enough dataThinking Machines: Inkling measured p50 TTFT
Qwen: Qwen3.5 397B A17BThinking Machines: Inkling
Model id
qwen/qwen3.5-397b-a17bthinkingmachines/inkling
PublisherDeepInfraDeepInfra
Context262,144 tokens1,048,576 tokens
Provider routes166
Cheapest route$2.97675/1M$5.3025/1M
Privacy posturehas confidential-compute routehas ZDR route
Modes
chat
chat
Qwen: Qwen3.5 397B A17B routes
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://gchircrcif.eu-west-3.awsapprunner.com/v1",
api_key="sk-tr-v1-..."
)
response = client.chat.completions.create(
model="qwen/qwen3.5-397b-a17b",
messages=messages,
)