OpenRouter app · rank #25Snapshot 2026-04-27
Agent Zero
Build autonomous AI agents effortlessly.
34.1B
Tokens (30d)
1.6M
Requests
$617K
Monthly cost
$4.85
Blended $/M tokens
Ranks in the 57th percentile by spend and 37th by raw tokens among the top 30 apps.
Primary driver
Anthropic: Claude Opus 4.6 is Agent Zero's top model at 28.7B — 84.2% of total token volume and 49.4% of monthly cost ($305K).
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 | 28.7B | 84.2% | $5.00 | $25.00 | $10.60 | $305K | 49.4% |
| 2 | Anthropic: Claude Sonnet 4.6 anthropic/claude-4.6-sonnet-20260217 | anthropic | 28.3B | 82.9% | $3.00 | $15.00 | $6.36 | $180K | 29.2% |
| 3 | Anthropic: Claude Opus 4.7 anthropic/claude-4.7-opus-20260416 | anthropic | 7.9B | 23.1% | $5.00 | $25.00 | $10.60 | $83K | 13.5% |
| 4 | Google: Gemini 3 Flash Preview google/gemini-3-flash-preview-20251217 | 6.7B | 19.5% | $0.50 | $3.00 | $1.20 | $8K | 1.3% | |
| 5 | Xiaomi: MiMo-V2-Pro xiaomi/mimo-v2-pro-20260318 | xiaomi | 4.9B | 14.5% | $1.00 | $3.00 | $1.56 | $8K | 1.2% |
| 6 | Qwen: Qwen3.6 Plus qwen/qwen3.6-plus-04-02 | qwen | 8.0B | 23.3% | $0.33 | $1.95 | $0.78 | $6K | 1.0% |
| 7 | MoonshotAI: Kimi K2.5 moonshotai/kimi-k2.5-0127 | moonshotai | 5.7B | 16.7% | $0.44 | $2.00 | $0.88 | $5K | 0.8% |
| 8 | Z.ai: GLM 5.1 z-ai/glm-5.1-20260406 | z-ai | 2.7B | 7.9% | $1.05 | $3.50 | $1.74 | $5K | 0.8% |
| 9 | Google: Gemini 3.1 Flash Lite Preview google/gemini-3.1-flash-lite-preview-20260303 | 7.1B | 20.9% | $0.25 | $1.50 | $0.60 | $4K | 0.7% | |
| 10 | OpenAI: GPT-5.4 Mini openai/gpt-5.4-mini-20260317 | openai | 1.4B | 4.2% | $0.75 | $4.50 | $1.80 | $3K | 0.4% |
| 11 | MoonshotAI: Kimi K2.6 moonshotai/kimi-k2.6-20260420 | moonshotai | 1.3B | 3.8% | $0.74 | $4.66 | $1.84 | $2K | 0.4% |
| 12 | MiniMax: MiniMax M2.7 minimax/minimax-m2.7-20260318 | minimax | 4.2B | 12.2% | $0.30 | $1.20 | $0.55 | $2K | 0.4% |
| 13 | Qwen: Qwen3.6 Plus qwen/qwen3.6-plus-preview | qwen | 1.9B | 5.5% | $0.33 | $1.95 | $0.78 | $1K | 0.2% |
| 14 | NVIDIA: Nemotron 3 Super nvidia/nemotron-3-super-120b-a12b-20230311 | nvidia | 6.3B | 18.5% | $0.09 | $0.45 | $0.19 | $1K | 0.2% |
| 15 | DeepSeek: DeepSeek V3.2 deepseek/deepseek-v3.2-20251201 | deepseek | 3.0B | 8.7% | $0.25 | $0.38 | $0.29 | $850 | 0.1% |
| 16 | OpenAI: GPT-5.4 Nano openai/gpt-5.4-nano-20260317 | openai | 1.5B | 4.5% | $0.20 | $1.25 | $0.49 | $754 | 0.1% |
| 17 | xAI: Grok 4.1 Fast x-ai/grok-4.1-fast | x-ai | 2.0B | 5.9% | $0.20 | $0.50 | $0.28 | $568 | 0.1% |
| 18 | StepFun: Step 3.5 Flash stepfun/step-3.5-flash | stepfun | 3.0B | 8.9% | $0.10 | $0.30 | $0.16 | $471 | 0.1% |
| 19 | Qwen: Qwen3.5-Flash qwen/qwen3.5-flash-20260224 | qwen | 2.5B | 7.3% | $0.07 | $0.26 | $0.12 | $297 | 0.0% |
| 20 | openrouter/elephant-alpha openrouter/elephant-alpha | openrouter | 2.3B | 6.8% | — | — | — | — | 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