InferIndex
Language, English, EN
Account

ModelsNVIDIANemotron 3 Super

Nemotron 3 Super

nvidia/nemotron-3-super-120b-a12b262k 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.
$0.275
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.
$0.825
Offers
18
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. · bf16 · 262k

$0.164 blended / 1M tokens

No change7D
in
$0.085
out
$0.40
Cached input
–
Go to offer Go to offer at DeepInfra (opens in a new tab)at DeepInfra

Nemotron 3 Super costs from $0.164 per million tokens (at a 3:1 input:output mix): the cheapest of 5 comparable offers, at DeepInfra, checked on ; 18 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 (13)

  • $0.10 · NanoGPT via NanoGPT · cannot be designated the cheapest
  • $0.164 · DeepInfra via Eden AI · cannot be designated the cheapest
  • $0.164 · DeepInfra via Kilo Gateway · cannot be designated the cheapest
  • $0.164 · Glama via Glama · cannot be designated the cheapest
  • $0.164 · Martian via Martian · cannot be designated the cheapest
  • $0.164 · DeepInfra via OpenRouter · another route of the same provider
  • $0.173 · DekaLLM via Kilo Gateway · cannot be designated the cheapest
  • $0.20 · DeepInfra via Requesty · another route of the same provider
  • $0.246 · DeepInfra · priority tier
  • $0.45 · Nebius via Eden AI · cannot be designated the cheapest
  • $0.50 · Arkanecloud via Eden AI · cannot be designated the cheapest
  • $0.825 · Crusoe via Kilo Gateway · cannot be designated the cheapest
  • $0.825 · Nous Portal via Nous Portal · 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$0.10, NanoGPT–
2026-10-03$0.10, NanoGPT–
2026-10-04$0.10, NanoGPT–
2026-10-05$0.10, NanoGPT–
2026-10-06$0.10, NanoGPT–
2026-10-07$0.10, NanoGPT–
2026-10-08$0.10, NanoGPT–
2026-10-09$0.10, NanoGPT–
2026-10-10$0.10, NanoGPT–
2026-10-11$0.10, NanoGPT–
2026-10-12$0.10, NanoGPT–
2026-10-13$0.10, NanoGPT–
2026-10-14$0.10, NanoGPT–
2026-10-15$0.10, NanoGPT–
2026-10-16$0.10, NanoGPT–
2026-10-17$0.10, NanoGPT–
2026-10-18$0.10, NanoGPT–
2026-10-19$0.164, DeepInfra–
2026-10-20$0.164, DeepInfra–
2026-10-21$0.164, DeepInfra–
2026-10-22$0.164, DeepInfra–
2026-10-23$0.164, DeepInfra–
2026-10-24$0.164, DeepInfra–
2026-10-25$0.164, DeepInfra–
2026-10-26$0.164, DeepInfra–
2026-10-27$0.164, DeepInfra–
2026-10-28$0.164, DeepInfra–
2026-10-29$0.164, DeepInfra–
2026-10-30$0.164, DeepInfra–
2026-10-31$0.164, DeepInfra–

Cheapest offer

Offers

18 of 18 offers

Offers for Nemotron 3 Super, 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 NanoGPT 0.05  0.25 0.10  – 262k 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)
2 DeepInfra 0.085 0.40 0.164 bf16 262k United States
Go to offer at DeepInfra (opens in a new tab)
3 DeepInfravia Eden AI 0.085 0.40 0.164 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
4 DeepInfravia Kilo Gateway 0.085 0.40 0.164 bf16 262k United States Unverified. No public page for this offer: listed, not designated cheapest
: Kilo Gateway (opens in a new tab). No public price page for this model
5 Glama 0.085 0.40 0.164 – 262k Unverified. No public page for this offer: listed, not designated cheapest
: Glama (opens in a new tab). No public price page for this model
6 Martian 0.085 0.40 0.164 – – 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)
7 DeepInfravia OpenRouter 0.085 0.40 0.164 bf16 262k United States Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 31). Offers are ranked with this fee included.
Go to offer at OpenRouter (opens in a new tab)
8 DekaLLMvia Kilo Gateway 0.08  0.45 0.173 fp8 262k Unverified. No public page for this offer: listed, not designated cheapest
: Kilo Gateway (opens in a new tab). No public price page for this model
9 DekaLLMvia OpenRouter 0.08  0.45 0.173 fp8 262k Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 31). Offers are ranked with this fee included.
Go to offer at OpenRouter (opens in a new tab)
10 DeepInfravia Requesty 0.10  0.50 0.20  bf16 262k United States Fee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Oct 31). Offers are ranked with this fee included.
Go to offer at Requesty (opens in a new tab)
11 DeepInfra 0.128 0.60 0.246 bf16 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)
12 Vercel AI Gateway 0.15  0.65 0.275 – –
Go to offer at Vercel AI Gateway (opens in a new tab)
13 Featherless 0.125 1.15 0.381 bf16 262k
Go to offer at Featherless (opens in a new tab)
14 Nebiusvia Eden AI 0.30  0.90 0.45  – 262k 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
15 Arkanecloudvia Eden AI 0.40  0.80 0.50  – 256k 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
16 Crusoevia Kilo Gateway 0.30  2.40 0.825 fp8 1M Unverified. No public page for this offer: listed, not designated cheapest
: Kilo Gateway (opens in a new tab). No public price page for this model
17 Nous Portal 0.30  2.40 0.825 – 1M Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
See pricing at Nous Portal (opens in a new tab)
18 Crusoevia OpenRouter 0.30  2.40 0.825 fp8 1M Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 31). Offers are ranked with this fee included.
Go to offer at OpenRouter (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.

2 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$11.10per month
  2. DekaLLM$11.55per month+$0.45 vs the cheapest
  3. DeepInfra$16.65per month+$5.55 vs the cheapest

Host it yourself instead? See the break-even

Compare Nemotron 3 Super 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-super-120b-a12b
MCP server
claude mcp add --transport http inferindex https://mcp.inferindex.dev/mcp

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