Junie
Observed throughTokscale Coding Client Report
Junie is JetBrains' coding agent for completing development tasks within supported IDEs.
Reality Snapshot
Observed tokens
6.6M+7.9%
over 30 days
Estimated tracked spend
$4.75
Invoices may differ
Active developers
4+2
deduplicated over 30 days
Observed messages
283
over 30 days
Most-used model
Claude Sonnet 4.688.2%
of observed tokens
Observed Usage
Observed tokensDaily active developers
Models used
Observed 30-day client usage by model
| Model | Tokens | Share | Change |
|---|---|---|---|
| Claude Sonnet 4.6Anthropic | 5.8M | 88% | 0% |
| gpt-4.1-mini-2025-04-14OpenAI | 209.4K | 3.2% | 0% |
| GPT-5.5OpenAI | 166.7K | 2.5% | 0% |
| Claude Haiku 4.5Anthropic | 111.7K | 1.7% | 0% |
| GPT-5.4 NanoOpenAI | 105.1K | 1.6% | 0% |
| gpt-4.1-2025-04-14OpenAI | 81.3K | 1.2% | 0% |
| GPT-5.6 TerraOpenAI | 42.3K | <1% | 0% |
| gpt-5-2025-08-07OpenAI | 29.9K | <1% | 0% |
Token composition
Share of observed client tokens
Cache read5.5M83%
Input1M16%
Output49.1K<1%
Reasoning00%
Client Economics
Claude Sonnet 4.6$3.7378%
gpt-4.1-mini-2025-04-14$0.091.8%
GPT-5.5$0.5211%
Claude Haiku 4.5$0.112.4%
GPT-5.4 Nano$0.02<1%
gpt-4.1-2025-04-14$0.163.4%
GPT-5.6 Terra$0.061.2%
gpt-5-2025-08-07$0.04<1%
Estimated spend per 1M tracked tokens$0.72
Cache-read share83.9%
Spend basisEstimated from tracked model usage
Estimated tracked spend uses Tokscale model and provider pricing data. Actual invoices may differ.
Client Momentum
+7.9%30-day growthObserved coding client
Compared with the prior non-overlapping 30-day window
Provider footprint
- Anthropic5.9M
- OpenAI634.7K
Client details
Canonical clientjunie
TelemetryAggregated Tokscale submissions
Current window2026-07-12 to 2026-08-10
Comparison window2026-06-12 to 2026-07-11
SpendEstimated; invoices may differ
About this client
Junie is JetBrains' coding agent for completing development tasks within supported IDEs.
Links & sources
TOKSCALE INSIGHT
Junie recorded 6.6M coding tokens across 4 developers during the latest 30-day Tokscale window.
Evidence confidenceStable observed sample