Which is cheaper, Nemotron 3 Ultra 550B A55B and Inkling Small?

Inkling Small has the lowest input price. Per 1M input tokens: Nemotron 3 Ultra 550B A55B from $0.50 and Inkling Small from $0.45.

Which has the larger context window, Nemotron 3 Ultra 550B A55B and Inkling Small?

Inkling Small has the largest context window: Nemotron 3 Ultra 550B A55B 262,144 tokens and Inkling Small 524,288 tokens.

Which is smarter, Nemotron 3 Ultra 550B A55B and Inkling Small?

Inkling Small scores highest on the Artificial Analysis Intelligence Index: Nemotron 3 Ultra 550B A55B 11.8 and Inkling Small 12.9.

Can I switch between Nemotron 3 Ultra 550B A55B and Inkling Small without changing my code?

Yes. All of them are served through FastRouter's OpenAI-compatible API, so switching is a change of the model parameter (nvidia/nemotron-3-ultra-550b-a55b, thinkingmachines/inkling-small).

Nemotron 3 Ultra 550B A55B vs Inkling Small

Side-by-side pricing per provider, context window, benchmark scores and speed, all on one OpenAI-compatible API.

Estimate monthly cost for these models

Nemotron 3 Ultra 550B A55B NVIDIAnvidia/nemotron-3-ultra-550b-a55b

Inkling Small Thinking Machinesthinkingmachines/inkling-small

Creator

NVIDIA

Thinking Machines

Released

May 16, 2026

Jul 30, 2026

Context window

262K

524K

Max output

16K

262K

Input / 1MLowest provider price

$0.50

$0.45

Output / 1MLowest provider price

$2.20

$1.20

Providers

IntelligenceArtificial Analysis index

11.8

12.9

Accepts

Text

Text, Image, Audio

Produces

Text

Tool calling

Yes

Structured output

Yes

Reasoning

Yes

Nemotron 3 Ultra 550B A55B vs Inkling Small: summary

Nemotron 3 Ultra 550B A55B and Inkling Small are both available through FastRouter's OpenAI-compatible API, so switching between them is a change of model id, not a new integration.

Nemotron 3 Ultra 550B A55B, from NVIDIA, has a 262,144-token context window, costs $0.50/1M input and $2.20/1M output tokens and scores 11.8 on the Artificial Analysis Intelligence Index.

Inkling Small, from Thinking Machines, has a 524,288-token context window, costs $0.45/1M input and $1.20/1M output tokens and scores 12.9 on the Artificial Analysis Intelligence Index.

Inkling Small is the cheapest on input, 1.1× cheaper than the next model, Inkling Small has the largest context window and Inkling Small scores highest for intelligence.

Switch with one line

client = OpenAI(base_url="https://api.fastrouter.ai/api/v1", api_key="<FASTROUTER_API_KEY>") client.chat.completions.create(model="nvidia/nemotron-3-ultra-550b-a55b", messages=[...]) # or client.chat.completions.create(model="thinkingmachines/inkling-small", messages=[...])

Full API docs

Frequently asked questions

More comparisons

Benchmark scores sourced from ArtificialAnalysis