# Cut My AI Spend

> A free, sourced catalog of every method that actually reduces AI and LLM costs, ranked by leverage. Published by Mitosis Labs. Every HTML page has a markdown twin at the same path with `.md` appended.

Structured data: /api/methods.json, /api/tools.json, /api/providers.json, /api/stats.json
Languages: en, es, de, fr, pt, ja (non-English under /<lang>/, e.g. /es/, /ja/)

## Methods (ranked)

- [#1 Fix the context & data layer (agent memory)](https://cutmyaispend.com/methods/fix-the-context-layer.md): Up to 90% (10x cheaper runs)
- [#2 Prompt caching](https://cutmyaispend.com/methods/prompt-caching.md): Up to 90% off cached input tokens
- [#3 Model routing & cascades](https://cutmyaispend.com/methods/model-routing.md): 40–98% depending on workload mix
- [#4 Semantic caching](https://cutmyaispend.com/methods/semantic-caching.md): 30–70% of redundant calls eliminated
- [#5 Batch APIs](https://cutmyaispend.com/methods/batch-apis.md): Flat 50% on most providers
- [#6 Output length control](https://cutmyaispend.com/methods/output-length-control.md): 20–60% of output-token spend
- [#7 Context hygiene & token management](https://cutmyaispend.com/methods/context-hygiene.md): 30–50% of input-token spend
- [#8 Cost attribution & AI FinOps](https://cutmyaispend.com/methods/cost-attribution-finops.md): Enables every other saving
- [#9 Cheaper & open models / self-hosting](https://cutmyaispend.com/methods/cheaper-and-open-models.md): 50–95% per token on suitable tasks
- [#10 LLM gateways & spend-tracking tools](https://cutmyaispend.com/methods/llm-gateways.md): Ops layer that unlocks methods 2–9

## Provider playbooks

- [How to cut your OpenAI API costs](https://cutmyaispend.com/providers/openai.md)
- [How to cut your Claude API costs](https://cutmyaispend.com/providers/anthropic-claude.md)
- [How to cut your AWS Bedrock costs](https://cutmyaispend.com/providers/aws-bedrock.md)
- [How to cut your Azure OpenAI costs](https://cutmyaispend.com/providers/azure-openai.md)
- [How to cut your Gemini API costs](https://cutmyaispend.com/providers/google-gemini.md)

## Tool reviews

- [Mitosis Cortex](https://cutmyaispend.com/tools/mitosis-cortex.md): Context & memory layer
- [LiteLLM](https://cutmyaispend.com/tools/litellm.md): Open-source LLM gateway
- [Portkey](https://cutmyaispend.com/tools/portkey.md): Managed AI gateway
- [OpenRouter](https://cutmyaispend.com/tools/openrouter.md): Multi-provider model marketplace
- [Helicone](https://cutmyaispend.com/tools/helicone.md): LLM observability & cost tracking
- [nOps](https://cutmyaispend.com/tools/nops.md): Cloud & AI FinOps platform

## Blog (news & analysis)

- [Latest posts](https://cutmyaispend.com/blog): pricing changes and tool shake-ups, each with a .md twin at /blog/<slug>.md

## Data

- [AI overspend statistics 2026](https://cutmyaispend.com/stats.md): every number with a primary source
- [LLM cost calculator](https://cutmyaispend.com/calculator): interactive; inputs are requests/month, tokens, prices

## Optional

- [Full content in one file](https://cutmyaispend.com/llms-full.txt)
- [About & disclosure](https://cutmyaispend.com/about)