Skip to main content
Condense

Condense: LLM Gateways

Founded 2026|Vilnius, Lithuania|1-10 people|Free for personal use; usage-based API (share of savings on the proxy, or per token removed on the Models API)

Respan Gateway: up to 55% off tokens on Gemini, GPT, Claude and 1,000+ more models. One API key, 0% fee.

What is Condense?

Key features

Core capabilities this platform advertises.

  • Drop-in proxy: change one base URL, keep your own provider key
  • Own compression models (Helene 1.1 and Adeline 1)
  • Anthropic, OpenAI, Amazon Bedrock, and Vertex AI routes
  • dense CLI for Claude Code, Codex, and OpenCode
  • Models API to call the compression models directly

Strengths and tradeoffs

What this tool does well, and the limitations to keep in mind.

Pros

  • Setup is one base URL change, with no new SDK
  • Provider keys stay yours, and the provider bills you directly
  • Proxy pricing is a share of savings, so there's no fee when nothing is saved
  • Free for personal use

Cons

  • Adds a third-party hop to every request
  • Organization API access starts with a call with the team
  • Personal accounts work through the dense CLI and can't create API keys

Plans & pricing

What's included in each plan, and how the tiers compare.

Personal

$0

 

  • Free for personal use
  • Runs through the dense CLI

Proxy API

15% of savings

Usage-based

  • Share of what Condense saves on your provider bill
  • No savings, no fee

Models API

$0.40 to $0.90 per 1M tokens removed

Usage-based

  • Helene 1.1 at $0.40 per 1M
  • Adeline 1 at $0.90 per 1M
View official pricing page

Common use cases

Developers and teams running agents on Anthropic or OpenAI who want lower token bills without changing their code.

  • Cutting token spend on long-running coding agents
  • Reducing context costs in production agent sessions
  • Lowering Claude Code or Codex usage for individual developers

Using Condense with Respan

Condense cuts the context going into each LLM call, and Respan shows what comes back. Route, observe, and evaluate every LLM call to confirm that compressed requests still produce good output.

  • Trace every compressed call with its tokens, cost, and latency
  • Score output quality on live traffic to catch regressions from compression
  • Track spend per agent run to see what compression saves
  • Route calls across 1,000+ models through one API

Run Condense in production with Respan

Up to 55%Off tokens
1,000+Models
0%Fee

Respan lets you trace LLM and agent calls across any model or framework, A/B test prompts on production traffic, and route requests across 1,000+ models through one gateway.

Best Condense alternatives & competitors

Top companies in LLM Gateways you can use instead of Condense.

View all Condense alternatives

Compare Condense

Side-by-side comparisons with other tools in this category.

Best integrations for Condense

Companies from adjacent layers in the AI stack that work well with Condense.