OpenAI compatible API · Attested · Public status
Google: Gemini 3.1 Pro Preview vs Thinking Machines: Inkling
Compare Google: Gemini 3.1 Pro Preview and Thinking Machines: Inkling by providers, context, price, and TrustedRouter route support.
Onebase URL to migrate
100sof models and routes
Noneprompt 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
Thinking Machines: Inkling has the lower cheapest prompt+completion route on TrustedRouter. Google: Gemini 3.1 Pro Preview has more provider fallback routes, while Google: Gemini 3.1 Pro Preview has the larger context window. Current TrustedRouter probes show Thinking Machines: Inkling with the lower p50 TTFT.
$14.7/1MGoogle: Gemini 3.1 Pro Preview cheapest route
$5.3025/1MThinking Machines: Inkling cheapest route
6470 msGoogle: Gemini 3.1 Pro Preview measured p50 TTFT
4815 msThinking Machines: Inkling measured p50 TTFT
Google: Gemini 3.1 Pro PreviewThinking Machines: Inkling
Model id
google/gemini-3.1-pro-previewthinkingmachines/inkling
PublisherGoogle AI StudioTogether
Context1,048,576 tokens524,288 tokens
Provider routes75
Cheapest route$14.7/1M$5.3025/1M
Privacy postureprovider posture varieshas ZDR route
Modes
chat
chat
Google: Gemini 3.1 Pro Preview routes
- Overview7 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="google/gemini-3.1-pro-preview",
messages=messages,
)