condense.chat operates a context-compression proxy for AI coding agents, reducing token usage and costs by compacting session history before it is sent to large language models. The service integrates with existing Anthropic and OpenAI SDKs, requiring only a base URL change, and its proprietary compaction models Helene 1 and Adeline 1 remove up to 37.3% of input tokens while maintaining or improving answer accuracy.
Funding
Funding not disclosed
Founders
Product
Problem
Coding agents become expensive because every turn re-sends the entire growing session history, forcing the model to re-read the same old context hundreds of times. Most of the bill is not raw input but cache reads and writes, which compound as sessions lengthen and drive up costs disproportionately.
Solution
condense.chat provides a proxy that compacts session history before it reaches the model, shrinking what gets written to and re-read from the cache. The service runs proprietary compaction models—Helene 1 for general traffic and Adeline 1 for long agent traces—that remove low-signal tokens while preserving answer quality. It integrates with both Anthropic and OpenAI SDKs by simply pointing the base URL at a provider route, keeping the user's existing key and changing nothing else. On real sessions, condense removes about two-thirds of total spend, with a 938-turn session dropping from $154 to $43 on Sonnet and from $771 to $214 on Opus.
Target Audience
Primary customers are individual developers and teams using coding agents like Claude Code, Codex, and OpenCode who want to reduce token costs on long, multi-turn sessions without sacrificing answer quality.
Features
- Helene 1 compaction model with auto mode that reads each input and decides how much to remove, or a fixed ratio set by the user
- Adeline 1 model optimized for long agent traces where deep compaction matters more than latency
- Proxy compatible with both Anthropic and OpenAI SDKs, requiring only a base URL change
- Cache-aware compression that targets the cache write and read tiers, which account for 67.7% of spend
- Compaction calls run in tens of milliseconds, adding no noticeable latency to the session
- Open-source minmax-bench harness that replays real sessions to measure bill reduction against competitors like headroom
- Metered pricing at $0.40 per 1M tokens saved for Helene 1 and $0.90 per 1M tokens saved for Adeline 1, with upstream model calls billed to the user's own provider key