OpenRouter app · rank #15Snapshot 2026-04-27
Roo Code
Roo Code is a VS Code extension that gives you a team of specialized AI agents with customizable modes for coding, architecture, debugging, and review, all with flexibility across any LLM or model provider.
https://github.com/RooVetGit/Roo-Cline →
111.8B
Tokens (30d)
1.5M
Requests
$1.62M
Monthly cost
$3.70
Blended $/M tokens
Ranks in the 77th percentile by spend and 67th by raw tokens among the top 30 apps.
Primary driver
Qwen: Qwen3.6 Plus is Roo Code's top model at 105.5B — 94.4% of total token volume and 5.1% of monthly cost ($82K).
Top-20 model breakdown
Ranked by monthly cost. Prices from OpenRouter's live catalog. Blended $/M = price_in × 72% + price_out × 28%.
| # | Model | Vendor | Tokens | % of vol. | $/M in | $/M out | Blended $/M | Monthly cost | % of spend |
|---|---|---|---|---|---|---|---|---|---|
| 1 | Anthropic: Claude Sonnet 4.6 anthropic/claude-4.6-sonnet-20260217 | anthropic | 88.7B | 79.3% | $3.00 | $15.00 | $6.36 | $564K | 34.7% |
| 2 | Anthropic: Claude Opus 4.6 anthropic/claude-4.6-opus-20260205 | anthropic | 52.7B | 47.1% | $5.00 | $25.00 | $10.60 | $558K | 34.4% |
| 3 | Anthropic: Claude Sonnet 4.5 anthropic/claude-4.5-sonnet-20250929 | anthropic | 24.2B | 21.7% | $3.00 | $15.00 | $6.36 | $154K | 9.5% |
| 4 | Anthropic: Claude Opus 4.7 anthropic/claude-4.7-opus-20260416 | anthropic | 8.7B | 7.7% | $5.00 | $25.00 | $10.60 | $92K | 5.7% |
| 5 | Qwen: Qwen3.6 Plus qwen/qwen3.6-plus-04-02 | qwen | 105.5B | 94.4% | $0.33 | $1.95 | $0.78 | $82K | 5.1% |
| 6 | OpenAI: GPT-5.4 openai/gpt-5.4-20260305 | openai | 8.8B | 7.9% | $2.50 | $15.00 | $6.00 | $53K | 3.3% |
| 7 | Google: Gemini 3.1 Pro Preview Custom Tools google/gemini-3.1-pro-preview-20260219 | 6.4B | 5.8% | $2.00 | $12.00 | $4.80 | $31K | 1.9% | |
| 8 | Google: Gemini 3 Flash Preview google/gemini-3-flash-preview-20251217 | 15.4B | 13.8% | $0.50 | $3.00 | $1.20 | $19K | 1.1% | |
| 9 | Z.ai: GLM 5.1 z-ai/glm-5.1-20260406 | z-ai | 7.6B | 6.8% | $1.05 | $3.50 | $1.74 | $13K | 0.8% |
| 10 | MiniMax: MiniMax M2.7 minimax/minimax-m2.7-20260318 | minimax | 22.5B | 20.1% | $0.30 | $1.20 | $0.55 | $12K | 0.8% |
| 11 | Anthropic: Claude Haiku 4.5 anthropic/claude-4.5-haiku-20251001 | anthropic | 5.3B | 4.8% | $1.00 | $5.00 | $2.12 | $11K | 0.7% |
| 12 | Qwen: Qwen3.6 Plus qwen/qwen3.6-plus-preview | qwen | 13.4B | 12.0% | $0.33 | $1.95 | $0.78 | $10K | 0.6% |
| 13 | Xiaomi: MiMo-V2-Pro xiaomi/mimo-v2-pro-20260318 | xiaomi | 4.7B | 4.2% | $1.00 | $3.00 | $1.56 | $7K | 0.5% |
| 14 | DeepSeek: DeepSeek V3.2 deepseek/deepseek-v3.2-20251201 | deepseek | 16.3B | 14.6% | $0.25 | $0.38 | $0.29 | $5K | 0.3% |
| 15 | StepFun: Step 3.5 Flash stepfun/step-3.5-flash | stepfun | 27.3B | 24.4% | $0.10 | $0.30 | $0.16 | $4K | 0.3% |
| 16 | NVIDIA: Nemotron 3 Super nvidia/nemotron-3-super-120b-a12b-20230311 | nvidia | 14.3B | 12.8% | $0.09 | $0.45 | $0.19 | $3K | 0.2% |
| 17 | MiniMax: MiniMax M2.5 minimax/minimax-m2.5-20260211 | minimax | 5.3B | 4.7% | $0.15 | $1.15 | $0.43 | $2K | 0.1% |
| 18 | Qwen: Qwen3 Coder Next qwen/qwen3-coder-next-2025-02-03 | qwen | 5.5B | 4.9% | $0.14 | $0.80 | $0.32 | $2K | 0.1% |
| 19 | Qwen: Qwen3.5-Flash qwen/qwen3.5-flash-20260224 | qwen | 6.1B | 5.4% | $0.07 | $0.26 | $0.12 | $729 | 0.0% |
| 20 | openrouter/elephant-alpha openrouter/elephant-alpha | openrouter | 5.0B | 4.5% | — | — | — | — | 0.0% |
Cross-references
- Full leaderboard: OpenRouter app leaderboard
- Inverted view: Which models AI agents actually use
- Related benchmarks: /agentic
- Source: openrouter.ai/apps/roo-code
We reply within 48 hours
Know Roo Code better than we do?
If these numbers don't match what you see from inside this app, tell us. We reply within 48 hours and update the analysis.
Tell us what you found →
✓ No newsletter✓ Real humans read this✓ 30 seconds to send