Nebius Token Factory free tier: limits and models

What Nebius Token Factory's free tier allows

Limits are dynamic with a published baseline of 60 RPM and 400,000 TPM. Usage is evaluated in rolling 15-minute windows: averaging at or above 80% of the current limit raises it by 20% for the next window, averaging at or below 50% divides it by 1.5, and the ceiling is 20x the base allocation before an Enterprise plan is required. No standing free allowance is documented on this page.

Published limits: 60 requests per minute
Free access type: Metered access
Credit card: Not required
Protocol: OpenAI-compatible at https://api.tokenfactory.nebius.com/v1
Lifecycle: Active
Sources reviewed: 2026-07-25

Requests above the limit may still be served at lower priority, flagged with an x-ratelimit-over-limit header, rather than failing outright.

Where Nebius Token Factory sits in this catalog

Nebius Token Factory is one of 6 metered access entries among the 25 providers detailed here. It asks for no credit card, which is true of 23 of the 25. It publishes fixed numbers — 60 requests per minute — which only 9 of the 25 do.

Compared with	Published limits	Card	Endpoint
Nebius Token Factory (this page)	60 requests per minute	Not required	`api.tokenfactory.nebius.com`
Perplexity API	50 requests per minute	Not required	`api.perplexity.ai`
DeepInfra	Enforced but not published	Not required	`api.deepinfra.com`
Chutes	Published per paid plan	Not required	`llm.chutes.ai`

Models Nebius Token Factory lists as free

deepseek-ai/DeepSeek-V3 — DeepSeek, also free at 4 other providers here
meta-llama/Llama-3.3-70B-Instruct — Llama, also free at 8 other providers here
Qwen/Qwen3-235B-A22B — Qwen, also free at 8 other providers here

8 other providers here also host the Llama family on free terms, and the terms are not the same: GroqCloud, SambaNova Cloud, Cloudflare Workers AI, Fireworks AI, IBM watsonx.ai, Together AI, DeepInfra, Scaleway Generative APIs. 8 other providers here also host the Qwen family on free terms, and the terms are not the same: Cloudflare Workers AI, SiliconFlow, Alibaba Cloud Model Studio, Ollama Cloud, Together AI, DeepInfra, Chutes, Scaleway Generative APIs. 4 other providers here also host the DeepSeek family on free terms, and the terms are not the same: SambaNova Cloud, Hugging Face Inference Providers, SiliconFlow, DeepInfra.

Checking a Nebius Token Factory key

The CORS preflight allows any origin to send an Authorization header, so a browser can call this endpoint directly. That was measured against https://api.tokenfactory.nebius.com on 2026-07-25.

So a key can be checked in the browser checker without installing anything. If you would rather not paste a key into a web page, this does the same thing:

#!/usr/bin/env sh
set -eu

: "${NEBIUS_API_KEY:?Set NEBIUS_API_KEY to a key you created yourself at the provider console}"

# Prints the models this key can reach, then the HTTP status on its own line so
# 200, 401, and 429 stay distinguishable.
curl --silent --show-error \
  --write-out '\nHTTP %{http_code}\n' \
  --header "Authorization: Bearer $NEBIUS_API_KEY" \
  'https://api.tokenfactory.nebius.com/v1/models'

Using a Nebius Token Factory key

Nebius Token Factory serves the OpenAI chat completions protocol at https://api.tokenfactory.nebius.com/v1. Point any client that accepts a custom base URL at it, and let the client read the key from NEBIUS_API_KEY so the value never lands in a config file:

# Merge this snippet into ~/.codex/config.toml.
# Project-level config cannot select a custom model provider.
model = "deepseek-ai/DeepSeek-V3"
model_provider = "nebius"

[model_providers.nebius]
name = "Nebius Token Factory OpenAI-compatible gateway"
base_url = "https://api.tokenfactory.nebius.com/v1"
env_key = "NEBIUS_API_KEY"
wire_api = "responses"

Questions about the Nebius Token Factory free tier

Does Nebius Token Factory ask for a credit card?

No. Nebius Token Factory is one of 23 providers here that hand out free access without a card, so the only cost of trying it is the signup.

What are Nebius Token Factory's free-tier rate limits?

Nebius Token Factory publishes 60 requests per minute. Those are the numbers in its own documentation as reviewed on 2026-07-25.

What happens when a Nebius Token Factory key hits the limit?

The endpoint answers 429. That is a statement about the request that was refused, not about how much quota is left; only a reset header from the provider tells you when it clears.

Is the Nebius Token Factory free tier going away?

Nothing in Nebius Token Factory's own documentation says so as of 2026-07-25. Requests above the limit may still be served at lower priority, flagged with an x-ratelimit-over-limit header, rather than failing outright.

Can Nebius Token Factory be used with Codex, Cline, or Continue?

Yes. Nebius Token Factory serves the OpenAI chat completions protocol at https://api.tokenfactory.nebius.com/v1, so any client that accepts a custom base URL can use it. Claude Code is the exception, because it speaks the Anthropic protocol instead.

Official sources

Nebius rate limits and scalinghttps://docs.tokenfactory.nebius.com/ai-models-inference/rate-limits
Nebius Token Factory quickstarthttps://docs.tokenfactory.nebius.com/quickstart
Nebius billing and consumptionhttps://docs.tokenfactory.nebius.com/other-capabilities/billing-new

Every figure above was read from those pages on 2026-07-25. Where a provider states a limit only inside a console, this catalog records that fact instead of a number. See the methodology for how an entry gets in and how it gets corrected.