OpenRouter app · rank #24roleplaySnapshot 2026-04-14
Agent Zero
Build autonomous AI agents effortlessly.
35.1B
Tokens (30d)
2.1M
Requests
$605K
Monthly cost
$4.22
Blended $/M tokens
Ranks in the 63th percentile by spend and 47th by raw tokens among the top 30 apps.
Primary driver
Anthropic: Claude Opus 4.6 is Agent Zero's top model at 34.8B — 99.2% of total token volume and 61.0% of monthly cost ($369K).
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 Opus 4.6 anthropic/claude-4.6-opus-20260205 | anthropic | 34.8B | 99.2% | $5.00 | $25.00 | $10.60 | $369K | 61.0% |
| 2 | Anthropic: Claude Sonnet 4.6 anthropic/claude-4.6-sonnet-20260217 | anthropic | 29.5B | 84.0% | $3.00 | $15.00 | $6.36 | $187K | 31.0% |
| 3 | Google: Gemini 3 Flash Preview google/gemini-3-flash-preview-20251217 | 10.1B | 28.9% | $0.50 | $3.00 | $1.20 | $12K | 2.0% | |
| 4 | Xiaomi: MiMo-V2-Pro xiaomi/mimo-v2-pro-20260318 | xiaomi | 5.1B | 14.5% | $1.00 | $3.00 | $1.56 | $8K | 1.3% |
| 5 | Qwen: Qwen3.6 Plus qwen/qwen3.6-plus-04-02 | qwen | 7.1B | 20.2% | $0.33 | $1.95 | $0.78 | $6K | 0.9% |
| 6 | MoonshotAI: Kimi K2.5 moonshotai/kimi-k2.5-0127 | moonshotai | 7.0B | 19.9% | $0.38 | $1.72 | $0.76 | $5K | 0.9% |
| 7 | Google: Gemini 3.1 Flash Lite Preview google/gemini-3.1-flash-lite-preview-20260303 | 6.0B | 17.2% | $0.25 | $1.50 | $0.60 | $4K | 0.6% | |
| 8 | MiniMax: MiniMax M2.7 minimax/minimax-m2.7-20260318 | minimax | 4.9B | 13.9% | $0.30 | $1.20 | $0.55 | $3K | 0.4% |
| 9 | NVIDIA: Nemotron 3 Super nvidia/nemotron-3-super-120b-a12b-20230311 | nvidia | 8.9B | 25.3% | $0.10 | $0.50 | $0.21 | $2K | 0.3% |
| 10 | Google: Gemini 2.5 Flash google/gemini-2.5-flash | 1.7B | 4.8% | $0.30 | $2.50 | $0.92 | $2K | 0.3% | |
| 11 | Qwen: Qwen3.6 Plus qwen/qwen3.6-plus-preview | qwen | 1.9B | 5.4% | $0.33 | $1.95 | $0.78 | $1K | 0.2% |
| 12 | StepFun: Step 3.5 Flash stepfun/step-3.5-flash | stepfun | 9.3B | 26.6% | $0.10 | $0.30 | $0.16 | $1K | 0.2% |
| 13 | Arcee AI: Trinity Large Thinking arcee-ai/trinity-large-preview | arcee-ai | 3.5B | 10.1% | $0.22 | $0.85 | $0.40 | $1K | 0.2% |
| 14 | DeepSeek: DeepSeek V3.2 deepseek/deepseek-v3.2-20251201 | deepseek | 4.0B | 11.3% | $0.26 | $0.38 | $0.29 | $1K | 0.2% |
| 15 | MiniMax: MiniMax M2.5 minimax/minimax-m2.5-20260211 | minimax | 2.3B | 6.7% | $0.12 | $0.99 | $0.36 | $846 | 0.1% |
| 16 | xAI: Grok 4.1 Fast x-ai/grok-4.1-fast | x-ai | 2.4B | 6.8% | $0.20 | $0.50 | $0.28 | $675 | 0.1% |
| 17 | Qwen: Qwen3.5-Flash qwen/qwen3.5-flash-20260224 | qwen | 3.2B | 9.0% | $0.07 | $0.26 | $0.12 | $379 | 0.1% |
| 18 | Google: Gemini 2.0 Flash google/gemini-2.0-flash-001 | 1.7B | 4.7% | $0.10 | $0.40 | $0.18 | $304 | 0.1% | |
| 19 | openrouter/hunter-alpha openrouter/hunter-alpha | openrouter | 7.0B | 19.9% | — | — | — | — | 0.0% |
| 20 | openrouter/healer-alpha openrouter/healer-alpha | openrouter | 3.1B | 8.9% | — | — | — | — | 0.0% |
Cross-references
- Full leaderboard: OpenRouter app leaderboard
- Inverted view: Which models AI agents actually use
- Related benchmarks: /agentic
- Source: openrouter.ai/apps/agent-zero
We reply within 48 hours
Know Agent Zero 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