Requesty free models: limits, keys and failover

What is free on Requesty

The Free plan costs nothing, covers the full platform on free models, and needs no credit card. Requesty lists models with no token charges and says they are free for now, with any pricing change announced ahead of time in its changelog.

Examples listed as free when we checked: nvidia/nemotron-3-super-120b-a12b , nvidia/nemotron-3-nano-30b-a3b , google/gemma-4-31b-it . Check the current catalog and your account access. Ficelle refreshes catalog data and applies eligibility checks during selection.

Listed free model examples on Requesty

• Gemma 4 google/gemma-4-31b-it
• Nemotron 3 Super nvidia/nemotron-3-super-120b-a12b
• Nemotron 3 Ultra nvidia/nemotron-3-ultra-550b-a55b

Requesty free-tier limits

New organizations get 200 requests per day and 20 per minute across all free models combined; paying organizations get 1,000 per day and 60 per minute. Past the limit, free-model requests return a rate-limit error until the window resets. Paid models are not affected.

Get a Requesty API key

Sign up and create a key on the API Keys page. The Free plan needs no credit card.

https://app.requesty.ai

OpenAI compatibility

Requesty says any SDK or framework that speaks OpenAI works with it out of the box.

https://router.requesty.ai/v1

Data and privacy

Requesty stores telemetry (tokens, cost, latency, model) for every request, and prompts and responses only when logging is on. Its documented default turns payload logging on for new keys; organization-wide Zero Data Retention is available and irreversible.

Through Ficelle, your Requesty key stays on your machine and prompts go straight to Requesty: there is no Ficelle proxy in between.

Before you rely on it

• Switching to another free model on Requesty does not give you a fresh organization quota. Check the shared daily counter before retrying across its model list.
• Requesty is itself a router: free models come from upstream providers whose terms can apply.
• Payload logging is on by default for new keys unless you change it.
• The free list and its pricing may change, with notice in the changelog.

Use Requesty with automatic failover

Ficelle can include Requesty behind your local OpenAI-compatible endpoint when the integration is enabled and its models pass free-access and capability checks. Requesty is listed in Ficelle Pro's maintained provider pack. Check your installed configuration, credentials and account entitlement before relying on it. Another eligible candidate must be available for failover to succeed. Local routing guards do not control upstream billing when an account permits paid usage beyond its free allocation. See strict-zero routing and account limits.

# Requesty ships in Ficelle Pro's maintained provider pack.
ficelle doctor --text          # check this install before configuring provider access

from openai import OpenAI

client = OpenAI(base_url="http://127.0.0.1:8646/v1", api_key="ficelle-local")

# Ficelle selects among configured, enabled, eligible models.
# If none can serve the request, it returns an error.
client.chat.completions.create(
    model="ficelle/auto-tools",
    messages=[{"role": "user", "content": "..."}],
)

See what Ficelle Pro includes →

Pick a model type

Choose a model type for your request. Eligibility depends on the installed provider configuration, catalog data, free-access evidence and capability checks. A catalog listing alone does not confirm that your account can call a model.

• Tool calling
• JSON & structured output
• Fast, low-latency
• Reasoning
• Coding assistants
• Agent orchestration
• Long context
• Context compression
• Vision
• Audio input
• Video input
• Multimodal

Questions