pxpipe

pxpipe

Cut Claude Code's input tokens by rendering bulky context as images — the same system prompt, tool docs, and history, in a fraction of the tokens.

An image's token cost is fixed by its pixel dimensions, not by how much text is inside it. Dense content (code, JSON, tool output) packs ~3.1 chars per image-token vs ~1 char per text-token on real Claude Code traffic. The reader is the same vision channel that Anthropic's computer use already relies on for screenshots. pxpipe is a local proxy that uses that channel for context: it rewrites the bulky parts of each request into compact PNGs before it leaves your machine. At current Fable list prices that lands as a ~59–70% lower end-to-end bill — but prices move and workloads differ, so the durable number is the token cut itself, measured per-request against a free count_tokens counterfactual in ~/.pxpipe/events.jsonl.

This is what the model sees instead of text:

~48k chars of system prompt + tool docs: ≈25k tokens as text, ≈2.7k image tokens as this page. Real pipeline output; the model reads renders like this at 100/100 (see benchmarks).

*Eight years of context growth, in characters. Every text line tops out near ~4M chars (a 1M-token window at ~4 chars/token); Grok 4.5 is shown as a text-window point only (500K). The orange overlays are the same 1M windows read through pxpipe images — ~19.0M chars for Fable 5 (4.8×) and ~21.3M chars for Gemini 3.6 Flash (5.3× text capacity). Density is measured from a live render at generation time, not hand-typed: regenerate with npx tsx scripts/gen-context-chart.ts (source).*

Demo

Fable 5 (the default, 100/100 reader) — plain left, pxpipe right:

https://github.com/user-attachments/assets/1c8ee63a-fcd7-4958-917b-da788d718349

pxpipe counts an exact token 10/10 across 39 imaged filler files (matches grep line-for-line), gets the multi-step ledger arithmetic right, and ends the session at $6.06 with context to spare (73.5k/1M) vs $42.21 at 96% full. One caveat visible in the clip: the pxpipe arm needed a nudge to match the requested one-line output format.

Try it (30 seconds)

npx pxpipe-proxy                                  # proxy on 127.0.0.1:47821
ANTHROPIC_BASE_URL=http://127.0.0.1:47821 claude  # point Claude Code at it

Dashboard at http://127.0.0.1:47821/: tokens saved, every text→image conversion side by side, kill switch, live model chips. Responses stream normally — pxpipe compresses the request only, never the model's output. Recent turns stay text; the system prompt, tool docs, and older bulk history are imaged.

pxpipe warp

pxpipe warp -- claude          # also: cursor-agent, codex, or a shell alias

Same thing without ANTHROPIC_BASE_URL, so /remote-control, claude.ai connectors, and first-party gates keep working. Full instructions in the dashboard.

api.anthropic.com/v1/messages is routed by default. Agents that reach their provider over some other base URL need a rule for it, and a rule that names a port matches only that port:

pxpipe warp --route '127.0.0.1:9090/v1/*=http://127.0.0.1:47821' -- codex

Offline export (no proxy)

You can render text, files, or diffs to PNG pages without running the proxy or connecting Claude Code:

npx pxpipe-proxy export src/
cat prompt.txt | npx pxpipe-proxy export --stdin
npx pxpipe-proxy export --git

If the package is installed, use pxpipe export instead of npx pxpipe-proxy export.

Each run writes a fresh pxpipe-export-XXXXXX/ output folder (the exact path is printed when the command finishes) containing page-*.png, factsheet.txt, manifest.json, and prompt.txt. Upload the PNG pages and paste the prompt into image-upload clients such as Cursor when you want dense visual context without running the proxy.

The honest part

• It is lossy. Exact 12-char hex strings in dense imaged content: 13/15 on Fable 5 and 0/15 on Sol — misses are silent confabulations, not errors. Byte-exact values (IDs, hashes, secrets) must stay text; recent turns do. The factsheet selectively preserves up to 96 recognized precision-critical tokens, not every identifier. A dedicated verbatim-risk guard is not built yet.
• Escape hatch: subagents on non-allowlisted models pass through as text — route byte-exact work there (CLAUDE_CODE_SUBAGENT_MODEL=claude-sonnet-4-6, or model: sonnet in agent frontmatter).
• Real work: SWE-bench Lite pilot 10/10 both arms at −65% request size; SWE-bench Pro 14/19 ON vs 15/19 OFF at −60%, verdicts agree 18/19, and the single split re-resolved 3/3 on replication — run-to-run variance, not compression. Small n; receipts in eval/.
• Workload-dependent. Wins on token-dense content (~1 char/token), loses money on sparse prose (~3.5 chars/token); a profitability gate (calibrated on N=391 production rows) images only where the math wins.
• Client-dependent. Savings track uncached bulk the client still re-sends as text. Claude Code re-sends system + tools + history on /anthropic/messages and typically lands ~60–70%. Details and measured splits: docs/CACHING_AND_SAVINGS.md.

Model support and rendering details

• claude-opus-5: weaker recall than Fable 5 (verbatim 2/15 vs 13/15), good enough otherwise (100/100 arithmetic, 0/16 never-stated), ~4.7× context before /compact. Suggested effort: medium. Details: FINDINGS.md.
• Model scope: default PXPIPE_MODELS=claude-fable-5,gemini. The gemini base covers every Gemini id (3.6/3.7/3.8 Flash, Pro, 4, 5, and future versions); to opt Gemini out, drop gemini from PXPIPE_MODELS or click the chip off. Opus 5, Sol, GPT 5.5, and Grok are opt-in only (dashboard chips or PXPIPE_MODELS). The exact Sol id still matters. Sibling variants such as gpt-5.6-terra do not inherit Sol's allowlist or render profile. PXPIPE_MODELS=off disables imaging. Everything else passes through byte-identical. On the GPT path, tool definitions stay native JSON and no Anthropic cache_control markers are used. Responses history compression recognizes completed function_call/function_call_output pairs, including OpenCode's parallel calls-then-outputs rounds: only old closed rounds are imaged atomically; every open call and malformed/orphan state remains native. The base profile keeps the newest six completed pairs and allows 32 images; Sol keeps one pair and allows 64 images, while Grok allows 24 images. Opt-in long-session coverage can be changed (defensive cap 100) with PXPIPE_GPT_HISTORY_MAX_IMAGES=48 after validating the provider's request cap.
• Per-model rendering: opt-in gpt-5.6-sol and Grok use native 14px JetBrains Mono glyphs in a 9×16 cell, 84 columns, and a 764px full-width strip; Claude keeps its 312-column, 1568×728 5×8 Spleen profile. These are selected by exact model id, including history pages and profitability math. Recognized IDs can ride in the bounded factsheet, and recent/open tool state stays native. Sol receipts and profile evidence.
• Grok 4.5 / 4.6 (opt-in): native 14px / 84 cols / maxH 512 (100/100 arith, 97/98 gist). Off by default (dense hex still 0/15). History uses mixed collapse so Codex assistant messages between tool rounds still image. Enable with PXPIPE_MODELS=claude-fable-5,grok-4.6 or the dashboard chip. eval/grok-density/QUALITY_RESULTS.md.

Benchmark results and receipts

Model quality

This matrix shows coverage as well as scores. — means the model was not run on that test; it does not mean zero. Arithmetic uses novel random-number problems. Gist, state, and never-stated probes share one corpus. Never-stated is confabulations, so lower is better. The numbers at column is the render geometry the row's scores were measured at; a model's shipped profile can differ (Sol and Qwen ship the measured 14px/84 geometry, but their broad-suite numbers predate it).

model	numbers at	arithmetic (N=100)	gist (N=98)	state (N=18)	never-stated (N=16)	dense hex (N=15)	profile provenance and receipts
claude-fable-5	Spleen 5×8, 312 cols (shipped)	100/100	98/98	18/18	0/16	13/15	June 2026 production profiles: arithmetic + hex, gist/state/guards
claude-fable-5-1	Spleen 5×8, 312 cols (Fable 5 profile)	100/100	95/98	18/18	0/16	6/15	Fable 5 profile, no geometry of its own; 3 gist misses are image-arm negation flags answered UNKNOWN (0 confabs). Same-day Fable 5 control on the identical harness/PNGs reproduced 100/100 arithmetic and 30/30 tier-2 gist, so the gist/hex gap is the model, not the harness (hex control not rerun): arithmetic, dense hex, gist/state/guards
google/gemini-3.6-flash, 3.7-flash	Spleen 5×8, 312 cols (shipped)	100/100	98/98	18/18	0/16	14/15	current shipped profile: quality results
claude-opus-5	Spleen 5×8, 312 cols (shipped)	100/100	94/98	17/18	0/16	2/15	current profile: arithmetic, gist/state/guards, dense hex
gpt-5.6-sol	Spleen 5×8, 152 cols; ships 14px/84	98/100	83/98	17/18	4/16	0/15	broad suite predates the shipped 14px profile; 14px pilot: 7/8 exact, 0 inventions, gist/guard pass: pilot
claude-opus-4-8	Spleen 5×8, 312 cols (historical)	93/100	77/98	18/18	0/16	0/15	historical profile: arithmetic, gist/state/guards, dense hex
grok-4.5	JetBrains Mono 14px, 84 cols (shipped)	100/100	97/98	17/18	0/16	0/15	native 14px/84 quality suite (live profile); quality, native-sweep
grok-4.6 high	JetBrains Mono 14px, 84 cols (shipped)	100/100	97/98	17/18	0/16	0/15	native 14px/84, reasoning high; quality
moonshotai/kimi-k3	Spleen 5×8, 152 cols (generic default)	79/100	84/98	15/18	1/16	0/15	generic GPT profile, no measured geometry of its own: quality results
qwen-3.8 (@cf/qwen/qwen3.8-27b)	Spleen 5×8, 152 cols; ships 14px/84	98/100	72/98	11/18	0/16	0/15	broad suite predates the shipped 14px profile; 14px pilot: 8/8 exact, 0 inventions, 11/15 hex: pilot & quality
glm-5.3-flash (@cf/zai-org/glm-5.3-flash)	Spleen 5×8, 152 cols (default fallback, nothing shipped)	36/100	57/98	6/18	0/16	0/15	5×8 is illegible to GLM (0/15 hex); 14px pilot: 10/15 hex, all misses single-glyph confabs, guards 0/16: pilot & quality

Native-profile cost check

Offline export of the same deterministic 454,045-character dense record corpus through each complete profile produced:

model profile	pages	text estimate	image tokens	savings
Claude, Spleen 5×8	17	122,715	23,856	80.6%
Sol, JetBrains Mono 14px	45	122