macrostack

AI API price index · open-model host · read 17 Nov 2026

Nebius Token Factory API pricing

24 prices as Nebius Token Factory publishes them — 23 text models, 1 embeddings — read on its own pricing page on 17 Nov 2026. Its current text models cost $0.24 to $15.00 per million output tokens.

Free tier No free tier or free credit is stated on the endpoints page or in the billing docs. The billing docs say a billing account with a bank card is set up when you start, and usage is charged to it.

What to know before you build on Nebius Token Factory

  • 24 public endpoints, from $0.06 in and $0.24 out per million tokens (Nemotron-3.5-Lightning) to $3.00 and $15.00 (Kimi-K3).
  • Nebius says the public endpoints are "Suitable for testing, not production", and that their processing region may change at any time.
  • Every public endpoint prints a cached-input price.
  • GLM-5.3 is $1.40 in and $4.40 out, the same as Z.ai's own price.
  • No free credit is stated; billing starts with a bank card. Batch and dedicated endpoints are priced behind a login.

Against the other 31

Across the index, 390 current text models run from $0.03 to $50.00 per million output tokens — 1667×. Nebius Token Factory’s cheapest, Nemotron-3-Nano-30B-A3B at $0.24, has 34 cheaper text models elsewhere; its dearest, Kimi-K3, costs $15.00. A cheaper model is a different model, not the same one for less — compare capability before price.

The same model elsewhere

Open-weight models Nebius Token Factory sells that other hosts price too — the only like-for-like comparison in the index.

  • gpt-oss-120b — Novita AI $0.05 / $0.25 · Google Vertex AI (Agent Platform) $0.09 / $0.36 · SambaNova Cloud $0.22 / $0.59 · Amazon Bedrock $0.15 / $0.60 · Fireworks AI $0.15 / $0.60 · Groq $0.15 / $0.60 · Nebius Token Factory $0.15 / $0.60 · Together AI $0.15 / $0.60 · Cerebras $0.35 / $0.75 · Cloudflare Workers AI $0.35 / $0.75 — 3.0× apart
  • Qwen3.8 27B — Cerebras $0.99 / $1.49 · DeepInfra $0.20 / $2.50 · Alibaba Cloud Model Studio (Qwen) $0.50 / $3.00 · Nebius Token Factory $0.45 / $3.00 · Novita AI $0.42 / $3.00 · Cloudflare Workers AI $0.45 / $3.20 · Groq $0.80 / $4.00 — 2.7× apart
  • GLM 5.3 — DeepInfra $0.90 / $4.00 · Cloudflare Workers AI $1.40 / $4.40 · Fireworks AI $1.40 / $4.40 · Mistral AI $1.40 / $4.40 · Nebius Token Factory $1.40 / $4.40 · Novita AI $1.40 / $4.40 · Perplexity $1.40 / $4.40 · Together AI $1.40 / $4.40 · Z.ai $1.40 / $4.40 · SambaNova Cloud $2.80 / $8.80 — 2.2× apart
  • DeepSeek V4.1 Flash 1017 — DeepInfra $0.20 / $0.60 · Cloudflare Workers AI $0.30 / $1.20 · DeepSeek $0.30 / $1.20 · Nebius Token Factory $0.30 / $1.20 · Novita AI $0.30 / $1.20 — 2.0× apart
  • MiniMax M3.1 Flash — MiniMax $0.15 / $0.60 · Nebius Token Factory $0.15 / $0.60 · SambaNova Cloud $0.30 / $1.20 — 2.0× apart
  • GLM 5.2 — DeepInfra $0.75 / $2.40 · Cloudflare Workers AI $1.40 / $4.40 · Google Vertex AI (Agent Platform) $1.40 / $4.40 · Nebius Token Factory $1.40 / $4.40 · Novita AI $1.40 / $4.40 · Together AI $1.40 / $4.40 · Z.ai $1.40 / $4.40 — 1.8× apart
  • DeepSeek V4 Pro 0813 — DeepInfra $1.30 / $2.60 · Cloudflare Workers AI $1.32 / $3.96 · DeepSeek $1.32 / $3.96 · Nebius Token Factory $1.32 / $3.96 · Novita AI $1.32 / $3.96 · Perplexity $1.32 / $3.96 · Together AI $1.32 / $3.96 — 1.5× apart
  • Kimi K3 — DeepInfra $2.85 / $14.25 · Amazon Bedrock $3.00 / $15.00 · Fireworks AI $3.00 / $15.00 · Moonshot AI (Kimi) $3.00 / $15.00 · Nebius Token Factory $3.00 / $15.00 · Novita AI $3.00 / $15.00 · Perplexity $3.00 / $15.00 · Together AI $3.00 / $15.00 — 1.1× apart
  • GLM 5.3 Flash — Cloudflare Workers AI $0.15 / $0.50 · DeepInfra $0.15 / $0.50 · Fireworks AI $0.15 / $0.50 · Nebius Token Factory $0.15 / $0.50 · Novita AI $0.15 / $0.50 · Perplexity $0.15 / $0.50 · Together AI $0.15 / $0.50 · Z.ai $0.15 / $0.50 — the same everywhere
  • Kimi K3.1 Pro — DeepInfra $2.00 / $10.00 · Moonshot AI (Kimi) $2.00 / $10.00 · Nebius Token Factory $2.00 / $10.00 · Novita AI $2.00 / $10.00 — the same everywhere
  • MiniMax M3 — Fireworks AI $0.30 / $1.20 · MiniMax $0.30 / $1.20 · Nebius Token Factory $0.30 / $1.20 · Together AI $0.30 / $1.20 — the same everywhere

Input / output per 1M tokens, standard tier.

Text models

ModelInputCached inputOutputNote
Inkling-2-Small$0.30$0.06$1.00public endpoint (shared; the page says suitable for testing, not production)
Kimi-K3.1-Pro$2.00$0.20$10.00public endpoint (shared; the page says suitable for testing, not production)
MiniMax-M3.1-Flash$0.15$0.015$0.60public endpoint (shared; the page says suitable for testing, not production)
DeepSeek V4.1 Flash 1017$0.30$0.006$1.20public endpoint (shared; the page says suitable for testing, not production)
Reflection Beam 1.0$0.25$0.05$1.00public endpoint (shared; the page says suitable for testing, not production)
Nemotron 3.5 Super VL$0.30$0.06$0.90public endpoint (shared; the page says suitable for testing, not production)
DeepSeek-V4-Pro-0813$1.32$0.04$3.96public endpoint (shared; the page says suitable for testing, not production)
Muse Spark Open$1.25$0.15$4.25public endpoint (shared; the page says suitable for testing, not production)
GLM-5.3-Flash$0.15$0.03$0.50public endpoint (shared; the page says suitable for testing, not production)
GLM-5.3$1.40$0.26$4.40public endpoint (shared; the page says suitable for testing, not production)
Qwen3.8-27B$0.45$0.10$3.00public endpoint (shared; the page says suitable for testing, not production)
Nemotron-3.5-Lightning$0.06$0.03$0.24public endpoint (shared; the page says suitable for testing, not production)
MiniMax-M3$0.30$0.06$1.20public endpoint (shared; the page says suitable for testing, not production)
Kimi-K3$3.00$0.30$15.00public endpoint (shared; the page says suitable for testing, not production)
GLM-5.2$1.40$0.14$4.40public endpoint (shared; the page says suitable for testing, not production)
Nemotron-3-Ultra-550b-a55b$1.00$0.12$3.00public endpoint (shared; the page says suitable for testing, not production)
Nemotron-3-Super-120b-a12b$0.30$0.06$0.90public endpoint (shared; the page says suitable for testing, not production)
Hermes-4-405B$1.00$0.20$3.00public endpoint (shared; the page says suitable for testing, not production)
gpt-oss-120b$0.15$0.10$0.60public endpoint (shared; the page says suitable for testing, not production)
Qwen3-235B-A22B-Instruct-2507deprecated$0.20$0.05$0.60public endpoint (shared; the page says suitable for testing, not production) · Not ranked: marked deprecated on the provider's page.
Qwen3-30B-A3B-Instruct-2507$0.10$0.10$0.30public endpoint (shared; the page says suitable for testing, not production)
Gemma-3-27b-it$0.10$0.04$0.30public endpoint (shared; the page says suitable for testing, not production)
Nemotron-3-Nano-30B-A3B$0.06$0.012$0.24public endpoint (shared; the page says suitable for testing, not production)

Embeddings

ModelInputCached inputNote
Qwen3-Embedding-8B$0.01—public endpoint

23 of these 24 prices are ranked in the index; the rest say why in their note. Text and embeddings per 1M tokens unless the row says otherwise.

Discounts and surcharges, as published

  • Batch inference and dedicated endpoints are offered ("Dedicated endpoints run on isolated infrastructure for production workloads"); their prices sit behind the login and are not recorded here.
  • Cached input is billed at the "1M Cached" price the page prints for each public endpoint.

Where these numbers come from

Read on tokenfactory.nebius.com/endpoints on 17 Nov 2026, checked against 1 more of Nebius Token Factory’s own pages. Macrostack measures nothing and is paid by no provider on this index. Prices change; the date is the claim.

The other providers in the index

Questions

How much does the Nebius Token Factory API cost?
On 17 Nov 2026, Nebius Token Factory's current text models cost $0.24 to $15.00 per million output tokens at the standard tier (Nemotron-3-Nano-30B-A3B to Kimi-K3). The full list, with input and cached-input prices, is on this page.
Does Nebius Token Factory have a free tier?
What Nebius Token Factory's own pages say: No free tier or free credit is stated on the endpoints page or in the billing docs. The billing docs say a billing account with a bank card is set up when you start, and usage is charged to it.
Does Nebius Token Factory offer discounts?
Batch inference and dedicated endpoints are offered ("Dedicated endpoints run on isolated infrastructure for production workloads"); their prices sit behind the login and are not recorded here. Cached input is billed at the "1M Cached" price the page prints for each public endpoint.
The Macrostack brief

New swaps, worth your inbox.

A short, occasional email when we add a high-intent alternative or ship a new head-to-head. No spam, no selling your address — unsubscribe in one click.