Inkling vs NVIDIA Nemotron 3 Ultra
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
| Specification |
by Fireworks
2 providers:
Fireworks $0.600/$2.40
Together $0.600/$3.60
|
|
|---|---|---|
| Overview | ||
| Status | Current mid tier Open weights | Current mid tier Open weights |
| Released | Jul 15, 2026 | Jan 1, 2026 |
| Pricing per million tokens | ||
| Input | $1.00/Mtok | $0.600/Mtok |
| Output | $4.05/Mtok | $2.40/Mtok |
| Blended avg | $1.76/Mtok | $1.05/Mtok |
| Cached input | $0.170/Mtok | $0.120/Mtok |
| Specifications | ||
| Context window | 262K tokens | 128K tokens |
| Parameters | 975B total / 41B active | Proprietary |
| Speed (TPS) | — | — |
| Modalities | ||
| Input |
textimageaudio
|
text
|
| Benchmarks source: Artificial Analysis | ||
| Independent composite scores measured for both models — each on its own scale | ||
| AA Intelligence Index | 42.3 | 38.3 |
| AA Agentic Index | 34.1 | 27.5 |
| AA-Omniscience Index (−100–100) | 2 | -0.4 |
| GDPval-AA v2 | 1239.6 ELO | 1163.4 ELO |
| LMSYS Chatbot Arena | 1441.5 ELO | 1426 ELO |
| Providers | ||
| Available from |
Thinking Machines — $1.00/$4.05/Mtok
|
Fireworks — $0.600/$2.40/Mtok
Together — $0.600/$3.60/Mtok
|
Cost at scale
1M tokens · 50/50 input/output| Volume | Inkling | NVIDIA Nemotron 3 Ultra | Savings |
|---|---|---|---|
| 1M tokens | $1.76 | $1.05 | $0.71 (40.3%) |
| 10M tokens | $17.63 | $10.5 | $7.13 (40.5%) |
| 100M tokens | $176.25 | $105 | $71.25 (40.4%) |
| 1000M tokens | $1762.5 | $1050 | $712.5 (40.4%) |
When to pick which
distilled from the pricing and spec data above- your workload re-reads context (agents, RAG, long chats): cached input costs $0.170/Mtok — 83% off its list input price
- you need the longer context: 262K tokens vs 128K (2×)
- cost dominates: $1.05/Mtok blended vs $1.76 — 40.4% less on the same 50/50 token mix
- provider flexibility: available from 2 providers, so you can price-shop hosts or fail over
The cheaper option here — NVIDIA Nemotron 3 Ultra costs $1.05/Mtok blended on Fireworks.
Summary
Inkling by Thinking Machines costs $1.00/Mtok input and $4.05/Mtok output, with a 262K-token context window. It supports text, image, audio input.
NVIDIA Nemotron 3 Ultra by Fireworks costs $0.600/Mtok input and $2.40/Mtok output, with a 128K-token context window. It supports text input and is available from 2 providers.
On a blended cost basis, NVIDIA Nemotron 3 Ultra is 40.4% cheaper than Inkling.
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.