InferIndex
Language, English, EN
Account

ModelsNVIDIANemotron 3 Ultra

Nemotron 3 Ultra

nvidia/nemotron-3-ultra-550b-a55b262k context Compare →
MedianThe median blended price among comparable offers: one price per provider (its cheapest route), standard tier, current prices only. Priority tiers and prices converted from points are not counted.
$1.05
Most expensiveThe highest blended price among comparable offers: one price per provider (its cheapest route), standard tier, current prices only. Priority tiers and prices converted from points are not counted.
$2.00
Offers
25
Providers
11

Cheapest right now

DeepInfra

The provider's published policy: prompts are not used for training.

directYou buy access straight from the company that runs the model on its servers. · fp4 · 262k

$0.925 blended / 1M tokens

No change7D
in
$0.50
out
$2.20
Cached input
$0.10
Go to offer Go to offer at DeepInfra (opens in a new tab)at DeepInfra

Nemotron 3 Ultra costs from $0.925 per million tokens (at a 3:1 input:output mix): the cheapest of 9 comparable offers, at DeepInfra, checked on ; 25 offers are listed.

Listed offers, by price

Comparable offersOther offersSolid steps are comparable offers; dashed steps are the other offers, which are not counted in cheapest, median or most expensive.

Offers not counted in cheapest, median or most expensive (16)

  • $0.925 · DeepInfra via Eden AI · cannot be designated the cheapest
  • $0.925 · DeepInfra via Kilo Gateway · cannot be designated the cheapest
  • $0.925 · DeepInfra via Vercel AI Gateway · another route of the same provider
  • $0.925 · Martian via Martian · cannot be designated the cheapest
  • $0.925 · DeepInfra via OpenRouter · another route of the same provider
  • $1.05 · BaseTen via Kilo Gateway · cannot be designated the cheapest
  • $1.05 · BaseTen via Kilo Gateway · cannot be designated the cheapest
  • $1.05 · Nous Portal via Nous Portal · cannot be designated the cheapest
  • $1.05 · BaseTen via OpenRouter · another route of the same provider
  • $1.25 · Venice via Kilo Gateway · cannot be designated the cheapest
  • $1.25 · Venice via OpenRouter · another route of the same provider
  • $1.33 · Arkanecloud via Eden AI · cannot be designated the cheapest
  • $1.35 · Glama via Glama · cannot be designated the cheapest
  • $1.39 · DeepInfra · priority tier
  • $1.50 · Nebius via Eden AI · cannot be designated the cheapest
  • $2.00 · DeepInfra via Eden AI · cannot be designated the cheapest

Price historyThe cheapest offer each day, against the lab's official list price when it publishes one. Each day at 00:00 UTC, the offer the API would have selected as the cheapest, with the same exclusions as /cheapest. Blended price, promotions included.

Cheapest offer and official list price, by day, 30 days
DayCheapest offerOfficial list price
2026-10-02$0.925, DeepInfra–
2026-10-03$0.925, DeepInfra–
2026-10-04$0.925, DeepInfra–
2026-10-05$0.925, DeepInfra–
2026-10-06$0.925, DeepInfra–
2026-10-07$0.925, DeepInfra–
2026-10-08$0.925, DeepInfra–
2026-10-09$0.925, DeepInfra–
2026-10-10$0.925, DeepInfra–
2026-10-11$0.925, DeepInfra–
2026-10-12$0.925, DeepInfra–
2026-10-13$0.925, DeepInfra–
2026-10-14$0.925, DeepInfra–
2026-10-15$0.925, DeepInfra–
2026-10-16$0.925, DeepInfra–
2026-10-17$0.925, DeepInfra–
2026-10-18$0.925, DeepInfra–
2026-10-19$0.925, DeepInfra–
2026-10-20$0.925, DeepInfra–
2026-10-21$0.925, DeepInfra–
2026-10-22$0.925, DeepInfra–
2026-10-23$0.925, DeepInfra–
2026-10-24$0.925, DeepInfra–
2026-10-25$0.925, DeepInfra–
2026-10-26$0.925, DeepInfra–
2026-10-27$0.925, DeepInfra–
2026-10-28$0.925, DeepInfra–
2026-10-29$0.925, DeepInfra–
2026-10-30$0.925, DeepInfra–
2026-10-31$0.925, DeepInfra–

Cheapest offer

Offers

25 of 25 offers

Offers for Nemotron 3 Ultra, one row per offer, sorted by blended price.
RankProvider · viaYou buy access through an aggregator: one account and one API that forward your requests to other providers. "Via" names the aggregator; the price is the one it charges you. When "via" says "hosted API", no aggregator is involved: the model belongs to a lab and another provider sells it.Input $/1MOutput $/1MBlended $/1MA single price that mixes input and output: 3 input tokens for 1 output token, per million tokens. It makes offers easy to rank; your real cost depends on your own mix.PrecisionHow finely the model's numbers are stored on the provider's servers. Lower precision (fp8, fp4) is cheaper to run and can slightly change answer quality; "unknown" means the provider doesn't say. ContextThe maximum amount of text, counted in tokens, the model can take in and write in a single request. Past this limit, the request is refused or cut.ConditionsWhat a provider says about how it handles your data and who can sign up: training on prompts, processing region, sign-up requirements. Each comes from the provider's published documents; when nothing is published, it stays unknown.SignalsOffer
1 DeepInfra 0.50  2.20 0.925 fp4 262k United States
Go to offer at DeepInfra (opens in a new tab)
2 DeepInfravia Eden AI 0.50  2.20 0.925 fp4 262k United States Unverified. No public page for this offer: listed, not designated cheapest
: Eden AI (opens in a new tab). No public price page for this model
3 DeepInfravia Kilo Gateway 0.50  2.20 0.925 fp4 262k United States Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
Go to offer at Kilo Gateway (opens in a new tab)
4 DeepInfravia Vercel AI Gateway 0.50  2.20 0.925 fp4 262k United States
Go to offer at Vercel AI Gateway (opens in a new tab)
5 Martian 0.50  2.20 0.925 – – worldwide Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
See pricing at Martian (opens in a new tab)
6 DeepInfravia OpenRouter 0.50  2.20 0.925 fp4 262k United States Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.
Go to offer at OpenRouter (opens in a new tab)
7 HPC-AI 0.50  2.50 1.00  – 1M
See pricing at HPC-AI (opens in a new tab)
8 NanoGPT 0.50  2.50 1.00  – 1M Thinking: Thinking: a mode of the model, not its standard offer. Never designated cheapest while a standard offer exists
Go to offer at NanoGPT (opens in a new tab)
9 BaseTenvia Kilo Gateway 0.60  2.40 1.05  fp4 203k Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
Go to offer at Kilo Gateway (opens in a new tab)
10 BaseTenvia Kilo Gateway 0.60  2.40 1.05  fp4 203k United States Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
Go to offer at Kilo Gateway (opens in a new tab)
11 BaseTenvia Vercel AI Gateway 0.60  2.40 1.05  fp4 1M
Go to offer at Vercel AI Gateway (opens in a new tab)
12 Fireworksvia Vercel AI Gateway 0.60  2.40 1.05  – 262k United States
Go to offer at Vercel AI Gateway (opens in a new tab)
13 Nous Portal 0.60  2.40 1.05  – 262k Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapestPrice changes often: 9 price changes in 7 days. Over that period: input $0.50 – $0.60, output $2.20 – $2.40 per million tokens. An offer whose price changes this often is not selected as the cheapest.
See pricing at Nous Portal (opens in a new tab)
14 BaseTenvia OpenRouter 0.60  2.40 1.05  fp4 203k Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.
Go to offer at OpenRouter (opens in a new tab)
15 BaseTenvia OpenRouter 0.60  2.40 1.05  fp4 203k United States Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.
Go to offer at OpenRouter (opens in a new tab)
16 Venicevia Kilo Gateway 0.625 3.13 1.25  fp8 256k Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
Go to offer at Kilo Gateway (opens in a new tab)
17 Venicevia OpenRouter 0.625 3.13 1.25  fp8 256k Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.
Go to offer at OpenRouter (opens in a new tab)
18 Venice 0.63  3.13 1.26  fp8 256k
Go to offer at Venice (opens in a new tab)
19 Arkanecloudvia Eden AI 0.60  3.50 1.33  – 512k Unverified. No public page for this offer: listed, not designated cheapest
: Eden AI (opens in a new tab). No public price page for this model
20 Glama 0.60  3.60 1.35  – 512k Unverified. No public page for this offer: listed, not designated cheapest
: Glama (opens in a new tab). No public price page for this model
21 DeepInfra 0.75  3.30 1.39  fp4 262k United States Priority tier: A different service tier, with its own speed and availability conditions.
Go to offer at DeepInfra (opens in a new tab)
22 Nebiusvia Eden AI 1.00  3.00 1.50  – 1M worldwide Unverified. No public page for this offer: listed, not designated cheapest
: Eden AI (opens in a new tab). No public price page for this model
23 Nebiusvia Requesty 1.00  3.00 1.50  – 128k worldwide Fee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Oct 30). Offers are ranked with this fee included.
Go to offer at Requesty (opens in a new tab)
24 DeepInfravia Eden AI 1.00  5.00 2.00  bf16 262k United States Unverified. No public page for this offer: listed, not designated cheapest
: Eden AI (opens in a new tab). No public price page for this model
25 DeepInfravia Hugging Face 1.00  5.00 2.00  bf16 262k United States
See pricing at Hugging Face (opens in a new tab)

No training on promptsPrompts may be used for trainingTraining terms not published

backend not named. The router bills this price itself without naming who serves the model.

3 flex or batch offers hidden (lower priority, variable latency).

Blended = (3 × input + output) / 4, per million tokens. Prices in USD, converted at the ECB rate when the provider bills in another currency.

Method

Monthly cost for your workload

Computed by the API for the three cheapest offers, per 30-day month.
  1. DeepInfra$63.00per month
  2. HPC-AI$67.50per month+$4.50 vs the cheapest
  3. NanoGPT$67.50per month+$4.50 vs the cheapest

Host it yourself instead? See the break-even

Compare Nemotron 3 Ultra with

Related models

More from NVIDIA

All NVIDIA models

Same index family

Use this data

The index is queryable. The API is free to use.
Free API
curl https://api.inferindex.dev/cheapest?model=nvidia/nemotron-3-ultra-550b-a55b
MCP server
claude mcp add --transport http inferindex https://mcp.inferindex.dev/mcp

Also works in Cursor and Codex: see the MCP page.