I track how much each provider charges for the same open LLM: Llama 3.3 70B ranges from $0.155 to $0.78 per 1M tokens

Description and use

An automated monitor compares prices for the same open LLM across providers, highlighting the cheapest options and quantization differences.

Problem

Different providers charge varying prices for the same open-weight LLM, making it hard to identify the cheapest option.

Outcome

The monitor identifies that DeepInfra offers Llama 3.3 70B at $0.155/M, the cheapest among 9 providers, with fp8 quantization on both ends, while other models show similar price disparities.

Workflow

• Every 5 minutes read OpenRouter public per-model endpoint data (no API key).
• For each provider compute blended cost per 1M tokens assuming 3 input tokens per output token.
• Exclude endpoints that are down (negative status or 0% recent uptime).
• Compute median, mean, standard deviation per model.
• Flag providers 15% or more below the median.
• Warn if cheapest provider uses different quantization than most expensive one.
• Use n8n workflow with duplicate filter to avoid re-alerting the same provider/model pair for 6 hours unless price moves >5%.

Evidence

Every 5 minutes it reads OpenRouter's public per-model endpoint data (no API key needed).

Source

For each provider it computes a blended cost per 1M tokens, assuming 3 input tokens for every output token.

Source

It warns when the cheapest provider uses a different quantization than the most expensive one, because fp4 vs fp16 is not a fair comparison.

Source