Infron Free AI Models

Overview

Infron is a usage-based LLM router that offers selected model variants with a :free suffix at $0.00 per token — requests to free models never deduct from your credit balance. All models are served through a single OpenAI-compatible endpoint.

Free Tier Quotas & Limits

• Daily Allowance: 1,000 requests per day per account, pooled across all standard free models combined (not per-model).
• Reset Time: Daily at 00:00 UTC.
• Rate Limits: Free model requests remain subject to Infron's default per-account rate limits.

Key Free Models

• Free variants are identified by a :free suffix, e.g. deepseek/deepseek-v4-flash:free. The full current lineup is available from the /v1/models endpoint (filter for :free).
• A limited-time promotion of qwen/qwen3.8-max-preview:free (1M-token context, up to 64K output tokens, tool calling, JSON mode, streaming) ended July 28, 2026.
• Free variants may route to different providers than their paid counterparts and are served from a shared pool with no SLA; the lineup changes over time.

Eligibility

• Standard free models require an account balance of $5 or more — held, not spent, as an anti-abuse requirement. Requests fail with an error if the balance falls below $5.
• Credit top-ups incur a 5% + $0.35 platform fee per transaction.

How to Get Started

1. Create an account at infron.ai/login using email or Google sign-in.
2. Create an API key at infron.ai/dashboard/apiKeys.
3. Call https://llm.onerouter.pro/v1/chat/completions with Authorization: Bearer $INFRON_API_KEY and a :free model ID. The endpoint is OpenAI-compatible, and the Anthropic SDK works with the base URL https://llm.onerouter.pro.