OpenAI compatible API · Attested · Public status
Thinking Machines: Inkling vs nvidia/NVIDIA-Nemotron-3-Ultra-550B
Compare Thinking Machines: Inkling and nvidia/NVIDIA-Nemotron-3-Ultra-550B 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
nvidia/NVIDIA-Nemotron-3-Ultra-550B has the lower cheapest prompt+completion route on TrustedRouter. Thinking Machines: Inkling has more provider fallback routes, while Thinking Machines: Inkling has the larger context window. Current TrustedRouter probes show nvidia/NVIDIA-Nemotron-3-Ultra-550B with the lower p50 TTFT.
$5.3025/1MThinking Machines: Inkling cheapest route
$2.73/1Mnvidia/NVIDIA-Nemotron-3-Ultra-550B cheapest route
5994 msThinking Machines: Inkling measured p50 TTFT
2157 msnvidia/NVIDIA-Nemotron-3-Ultra-550B measured p50 TTFT
Thinking Machines: Inklingnvidia/NVIDIA-Nemotron-3-Ultra-550B
Model id
thinkingmachines/inklingnvidia/nemotron-3-ultra-550b
PublisherTogetherCrusoe
Context524,288 tokens262,144 tokens
Provider routes54
Cheapest route$5.3025/1M$2.73/1M
Privacy posturehas ZDR routeprovider posture varies
Modes
chat
chat
Thinking Machines: Inkling 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://api.trustedrouter.com/v1",
api_key="sk-tr-v1-..."
)
response = client.chat.completions.create(
model="thinkingmachines/inkling",
messages=messages,
)