A place of
abundance
Tokens should be cheap, fast, and smart - for everyone. We get there through efficiency: reducing what goes in, reducing what comes out, and routing where it performs best.
Join DiscordDownsize your Tokens costs
Works best with agents and AI coding tools
Takes 2 minutes or one prompt to set up.
Reduces inference costs for agents and AI coding tools. Uses Anthropic / OpenAI by default — or routes to alternative models at equivalent quality to reduce further.
Talk to us →Under the hood
We optimize at all levels
You point to our gateway. We handle routing, compression, and model selection.
Full token grid arrives - data, prompt and context.
We reduce input token volume by removing low-signal and redundant units.
When feasible, we cherry-pick only the most salient pieces.
Smart router sends bundle to the best model the grader recommends.
Response compressed too.
Try it out. Install the CLI and connect coding tools or agents in seconds.
CLI quickstart →Same Quality. Better prices.
Use Anthropic and OpenAI models at discounted prices
Or use our models for maximum cost savings
| Model | Input / 1M tok | Output / 1M tok |
|---|---|---|
| Anthropic | ||
Claude Fable 5 Mythos-class, most capable publicly available | $10$7.14 | $50$38.46 |
Claude Opus 4.8 Most intelligent, for agents & coding | $5$3.57 | $25$19.23 |
Claude Sonnet 4.6 Balance of intelligence, cost & speed | $3$2.14 | $15$11.54 |
Claude Haiku 4.5 Fastest, most compact Anthropic model | $0.8$0.72 | $4$3.60 |
| OpenAI | ||
GPT-5.5 Frontier model for complex reasoning | $5$3.57 | $30$23.08 |
GPT-5.4 Affordable model for coding & work | $2.50$1.79 | $15$11.54 |
GPT-5.4 mini Strongest mini for coding & sub-agents | $0.75$0.675 | $4.50$4.05 |
| Downsizing | ||
Universe Maximum capability, multimodal & deep reasoning | $1 | $4 |
Galaxy Balanced intelligence at a fraction of the cost | $0.5 | $2 |
Star Lightning-fast, ultra-low cost | $0.25 | $1 |
*These figures represent typical compression gains observed across diverse applications and agents.
Running a custom pipeline? Share your setup and we'll figure out what fits.
contact@downsizing.dev →Coding Subscription Pricing
Bring your subscription, and we'll double its capacity
Bring your existing Claude or Codex subscription — we optimize on top.
Bring your own
Flat monthly cap — never more than $5
Bring your existing Claude or Codex subscription and we'll extend your effective limits — at no extra cost for lighter usage, and a flat $5/mo for heavier workloads.
- Input & output token compression
- Smart routing across providers
- Focused attention mode
- Usage dashboard & analytics
Our subscription
Full access — no external subscription required. We provide the tokens with doubled capacity compared to direct Anthropic or OpenAI plans.
- Everything in Bring your own
- 2× token capacity vs. Claude Code or Codex
No setup fees · Cancel anytime · Charged only when you exceed 30,000 tokens
From users
Loved by developers
“We switched our code-generation pipelines to Downsizing and started seeing savings right away.”
Paula
Staff Engineer · Samsung
“Went from $8k/month on Claude Code to $5k. Didn't change a single prompt.”
Aleh
Senior Software Engineer · Nvidia
“Extends my Claude Code subscription at least by 2x on the free version. Love it.”
Darshan
Senior Software Engineer · Google
“Downsizing replaced multiple plugins with better outcomes, 2 minutes to set up.”
Anton
Senior Software Engineer · Revolut
Analytics
Numbers speak for themselves
Actual Claude Code sessions
Input tokens
3.5B
received
Input saved
1.44B
of 3.5B total
Requests
14,077
total
Output tokens
284M
received
Output saved
99.4M
of 284M total
Routed
8,602
61% of total
Input tokens by model
| Model | Requests | Tokens in | Saved |
|---|---|---|---|
| Sonnet | 8,241 | 2.1B | 891M |
| Opus | 1,034 | 412M | 176M |
| Haiku | 4,802 | 980M | 372M |
Recent requests
| Model | Saved | When |
|---|---|---|
| Sonnet | +18,432 | 2m ago |
| Haiku | +4,211 | 4m ago |
| Sonnet | +34,209 | 7m ago |
| Haiku | +2,847 | 11m ago |
Controls
Full control in real-time
Tune compression, routing, and attention for each workload — from a single config.
Input compression
Redundancy stripped from context before it reaches the model.
Output compression
Models instructed to be concise and eliminate scaffolding.
Smart routing
Match each request to the cheapest capable model.
Focused attention
Steers the model to attend only to the task-critical parts of context.
Adjust the controls above to configure your proxy — then sign up to save.
Benchmarked
Compression doesn't reduce quality.
In large contexts, it often improves it.
Claude Fable 5
Baseline
95%
Compressed
95.7%
Delta
+0.7%
Claude Opus 4.8
Baseline
88.6%
Compressed
89.3%
Delta
+0.7%
Claude Sonnet 4.6
Baseline
79.6%
Compressed
80.8%
Delta
+1.2%
GPT-5.5
Baseline
88.7%
Compressed
89.5%
Delta
+0.8%
Integrations
Works with Claude Code, Codex and many others
Zero changes to your existing tools or workflows.
Coding & agentic tools
We silently compress redundant context so you can code longer and spend significantly less.
Personal AI Assistants
We prune stale context and use cheaper models for simple tasks so your agents run longer for less.
Claude Code
Official CLI for agentic coding
LiveCodex
OpenAI's terminal coding agent with custom endpoint support
LiveJunie
JetBrains AI coding agent for terminal and IDE
LiveHermes
Evolving AI agent with persistent memory
SoonAider
Terminal pair-programming agent supporting any OpenAI-compatible backend
SoonAmp
Agentic coding tool from Sourcegraph with custom provider support
SoonCline
VS Code extension for code generation & file ops
SoonCrush
Terminal-based AI tool with CLI and TUI interfaces
SoonDroid
Enterprise terminal agent for end-to-end workflows
SoonEigent
Desktop multi-agent for browser automation
SoonGemini CLI
Google's terminal coding agent with custom endpoint support
SoonGoose
AI agent for local execution & engineering tasks
SoonPi
Minimal terminal coding harness with unified LLM API and MCP
Using a tool not listed? Let us know — we can support it.