Fireworks: Ember-1 vs NVIDIA: Nemotron 3.5 Super VL
fireworks/ember-1 · nvidia/nemotron-3.5-super-vl
As of November 3, 2026, NVIDIA: Nemotron 3.5 Super VL is the cheaper API on UberLLM: $0.1200 per million input tokens and $0.4000 per million output, versus $2.70 / $13.50 for Fireworks: Ember-1, about 97% less when output is 3 tokens for every input token. These are the best prices on the market right now. Both work with one OpenAI-compatible key and UberLLM adds no fee. Choose NVIDIA: Nemotron 3.5 Super VL to cut cost; choose Fireworks: Ember-1 when context size wins. Fireworks: Ember-1 carries the larger context window (1,048,576 vs 262,144 tokens), which can matter for long-document work.
Fireworks: Ember-1 vs NVIDIA: Nemotron 3.5 Super VL, side by side
| Spec | Fireworks: Ember-1 | NVIDIA: Nemotron 3.5 Super VL |
|---|---|---|
| Price · input / 1M | $2.70 | $0.1200 |
| Price · output / 1M | $13.50 | $0.4000 |
| Context length | 1,048,576 | 262,144 |
| Max output tokens | 943,718 | 235,929 |
| Input modalities | text, image | text, image, video |
| Output modalities | text | text |
| Tools / functions | Yes | Yes |
| Vision (image input) | Yes | Yes |
| Reasoning | Yes | Yes |
| % off list | 10% off | 20% off |
Best prices on UberLLM right now. No UberLLM fee on requests; adding credit by card costs 5.5% + $0.50. Updated November 3, 2026.
Fireworks: Ember-1 vs NVIDIA: Nemotron 3.5 Super VL — FAQ
Is Fireworks: Ember-1 or NVIDIA: Nemotron 3.5 Super VL cheaper?
NVIDIA: Nemotron 3.5 Super VL is cheaper on a blended token mix, by about 97%. A request costs what its provider charged, UberLLM adds no fee, and every request is listed with its cost in Activity.
What's the price difference between Fireworks: Ember-1 and NVIDIA: Nemotron 3.5 Super VL?
Fireworks: Ember-1: $2.70 in / $13.50 out per 1M tokens. NVIDIA: Nemotron 3.5 Super VL: $0.1200 in / $0.4000 out per 1M tokens. That's roughly a 97% blended difference. Prices are live; UberLLM adds no fee.
Can I use both Fireworks: Ember-1 and NVIDIA: Nemotron 3.5 Super VL with one API?
Yes. Both are served through a single OpenAI-compatible endpoint — set the base URL to https://api.uberllm.dev/v1 and your UberLLM key, then switch between them by changing the model id. Anthropic SDKs work via https://api.uberllm.dev/v1/messages.