where the money went · by token type
| type | est. cost | % of cost |
|---|---|---|
| cache reads | $62376 | 60.4% |
| cache creates | $31397 | 30.4% |
| output | $7964 | 7.7% |
| input | $1506 | 1.5% |
costs estimated using Opus 4.7 rates ($15/$75/$18.75/$1.50 per MTok) · actual spend may differ for Sonnet/Haiku turns
model spend · concentration
| model | spend | % of total |
|---|---|---|
| claude-opus-4-7 | $34874 | 38.0% |
| claude-opus-4-8 | $31385 | 34.2% |
| claude-opus-5 | $16009 | 17.4% |
| claude-opus-4-6 | $6800 | 7.4% |
| claude-fable-5 | $2128 | 2.3% |
| claude-sonnet-4-6 | $288.90 | 0.3% |
| claude-sonnet-5 | $120.43 | 0.1% |
| glm-5.2 | $109.91 | 0.1% |
| claude-haiku-4-5-20251001 | $47.93 | 0.1% |
| claude-opus-4-5-20251101 | $7.661 | 0.0% |
| fugu | $2.976 | 0.0% |
| glm-4.7 | $1.057 | 0.0% |
| deepseek-v4-flash | $0.829 | 0.0% |
| claude-sonnet-4-5-20250929 | $0.640 | 0.0% |
| deepseek-v4-pro | $0.512 | 0.0% |
| nemotron-3-nano | $0.315 | 0.0% |
fix opportunities · 5 found
97% of spend on Opus
Opus is 5× more expensive than Sonnet for input and 5× for output. Routine work (file edits, summaries, explanations) does not require Opus.
→ Set model to Sonnet for non-critical sessions. Potential savings: ~78% of total spend.
48% of spend from home-directory sessions
Sessions started without a project directory load your full ~/.claude/ context (global CLAUDE.md, all memory files) on every turn — creating more cache writes and longer prompts.
→ Always run `claude` from inside a project folder. Home-dir sessions also don't get project-level cost attribution, making it harder to see what's expensive.
Cache writes = $31397 (34% of spend)
Cache creates happen when Claude loads a large context for the first time in a session. Long CLAUDE.md files, large skills, and many MCP tool lists all trigger expensive cache writes.
→ Audit your global CLAUDE.md — trim to under 2K tokens. Disable MCP servers you don't use in every session. Each new session re-creates the cache.
Cache reads = $62376 — but that's good
High cache-read cost means Claude is successfully reusing context instead of re-reading raw files. You're already saving money on repeated context — this is working as intended.
→ No action needed. Keep sessions long (don't restart Claude mid-task) to maximize cache reuse within a session.
85% of injections unclassified
These are context injections tokenburn couldn't identify as a skill, hook, or MCP result. They may be large tool results, system prompts, or custom contexts from plugins.
→ Check your /sources page for the full injection list. Unclassified injections with high token counts are worth investigating — they may be redundant context being added repeatedly.
injected context · by source type
these tokens are injected INTO your prompts by skills, hooks, and MCP servers — on top of what you type
| source | est. tokens | % of injected | ||
|---|---|---|---|---|
| unknown | 4.30B | 84.9% | ||
| skill_inject | 501.53M | 9.9% | ||
| hook | 266.68M | 5.3% | ||
| injected tokens become input tokens on each turn they appear · see /sources for name-level drill-down | ||||