How I Cut Aider's Token Bill 80%: Prompt Caching, MCP Code Mode, and Tier Routing

Aider is the best terminal AI coding tool I've used. But by default it sends every diff through your OpenAI or Anthropic key, which gets expensive fast on real refactors — a single 100-file repo map can torch a few dollars before Aider even reads your prompt.

This post shows how to run Aider against any LLM provider — Ollama for free local runs, OpenRouter for mixed-provider routing, AWS Bedrock for the enterprise plate — through a single OpenAI-compatible endpoint, with prompt caching and MCP Code Mode layered on top to slash the bill further. I'll use puts GPT-4o and Claude 3.5 Sonnet at the top. But you don't need a $3-per-million-tokens model to rename a variable. You need it for the architecture decisions.

Lynkr's tier routing splits the work by prompt complexity:

# .env additions

TIER_SIMPLE=ollama:qwen2.5-coder:7b

TIER_MEDIUM=openrouter:google/gemini-flash-1.5

TIER_COMPLEX=openrouter:anthropic/claude-3.5-sonnet

TIER_REASONING=openrouter:anthropic/claude-opus-4

Then point Aider at --model lynkr-auto and Lynkr scores each prompt before picking the tier.

Stacking the three levers

Each lever on its own is meaningful. Stacked, they compound:

• 
  Caching alone: ~70% input-token cut on a stable session


• 
  + Tier routing: another ~40% by pushing routine calls to Flash/Ollama


• 
  + MCP Code Mode (if you compose with other MCP tools): another 5–15x on tool-plumbing tokens

In my own Aider workflow — heavy refactors against a 200k-LOC monorepo — this combination has dropped a session that used to cost ~$8 in Claude calls down to under $1.50. Not because Claude got cheaper. Because most of the work is now happening on cached prefixes, free local models, or in-sandbox code execution.

Configuration walkthrough

Step 1 — Install and start Lynkr

npx lynkr@latest

First run creates a .env file. Minimal config:

MODEL_PROVIDER=anthropic

ANTHROPIC_API_KEY=sk-ant-...

PROMPT_CACHE=true

PORT=8081

For full local + free:

MODEL_PROVIDER=ollama

OLLAMA_ENDPOINT=http://localhost:11434

OLLAMA_MODEL=qwen2.5-coder:latest

PORT=8081

Then ollama pull qwen2.5-coder:latest.

Step 2 — Point Aider at the gateway

export OPENAI_API_BASE=http://localhost:8081/v1

export OPENAI_API_KEY=dummy

Drop those in your shell rc file.

Step 3 — Pick a model (or let Lynkr pick)

# Direct pass-through

aider --model openai/gpt-4o



# Or let Lynkr tier-route

aider --model lynkr-auto

Step 4 — Verify

curl -s http://localhost:8081/v1/models | python3 -m json.tool | head

Start Lynkr with LOG_LEVEL=info and watch the cache-hit lines on your second Aider request — that's where the savings show up.

Aider-specific gotchas

Weak model for commits / summarization. Aider uses a cheaper model for non-code calls; default is gpt-4o-mini. Override to a free local one:

aider --model openai/gpt-4o --weak-model ollama/qwen2.5-coder:7b

Long context. Local Ollama models will OOM on 200k+ token repo maps. Either set --map-tokens 0, or route long-context calls to Gemini Flash 1M-token contexts via the TIER_REASONING line above.

Streaming. Aider expects streaming responses. Lynkr streams by default. If you're on a non-streaming Databricks endpoint, set STREAM_PASSTHROUGH=false and Lynkr buffers + simulates.

Cache hit rate. Prompt caching only fires when the prefix is byte-identical across requests. If your repo map changes (you edit a /added file), the cache for that block invalidates and rebuilds. Lynkr logs cache-hit ratios per session — watch them; if hit rate is below 60% something in your workflow is busting the prefix.

Quickref

TL;DR

The default Aider setup pays full price for the same repo-map bytes on every turn. The fix isn't "use a cheaper model" — it's:

1. 
   Cache the repetitive prefix (prompt caching).


2. 
   Collapse tool plumbing into one call (MCP Code Mode).


3. 
   Match model size to task complexity (tier routing).

Stacked, those three levers have taken my Aider sessions from ~$8 to ~$1.50 without changing how I work. Lynkr is one gateway that does all three; it's Apache 2.0, single Node binary, drop-in OpenAI base URL.

Aider's GitHub: — star to follow next integration writeups (OpenHands, Vercel AI SDK, Open Interpreter queued).