OpenRouter app · rank #26roleplaySnapshot 2026-04-27
Open WebUI
Open WebUI is a self-hosted AI platform providing a chat interface for Large Language Models.
33.7B
Tokens (30d)
1.5M
Requests
$526K
Monthly cost
$5.37
Blended $/M tokens
Ranks in the 50th percentile by spend and 33th by raw tokens among the top 30 apps.
Primary driver
Anthropic: Claude Sonnet 4.6 is Open WebUI's top model at 35.7B — 106.1% of total token volume and 43.2% of monthly cost ($227K).
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 | 35.7B | 106.1% | $3.00 | $15.00 | $6.36 | $227K | 43.2% |
| 2 | Anthropic: Claude Opus 4.6 anthropic/claude-4.6-opus-20260205 | anthropic | 9.1B | 27.0% | $5.00 | $25.00 | $10.60 | $96K | 18.3% |
| 3 | OpenAI: GPT-5.4 openai/gpt-5.4-20260305 | openai | 13.3B | 39.6% | $2.50 | $15.00 | $6.00 | $80K | 15.2% |
| 4 | Google: Gemini 3.1 Pro Preview Custom Tools google/gemini-3.1-pro-preview-20260219 | 7.2B | 21.3% | $2.00 | $12.00 | $4.80 | $34K | 6.6% | |
| 5 | OpenAI: GPT-5.3-Codex openai/gpt-5.3-codex-20260224 | openai | 4.1B | 12.3% | $1.75 | $14.00 | $5.18 | $21K | 4.1% |
| 6 | Anthropic: Claude Opus 4.7 anthropic/claude-4.7-opus-20260416 | anthropic | 2.0B | 5.9% | $5.00 | $25.00 | $10.60 | $21K | 4.0% |
| 7 | Anthropic: Claude Sonnet 4.5 anthropic/claude-4.5-sonnet-20250929 | anthropic | 2.2B | 6.4% | $3.00 | $15.00 | $6.36 | $14K | 2.6% |
| 8 | OpenAI: GPT-5.2 openai/gpt-5.2-20251211 | openai | 1.7B | 5.1% | $1.75 | $14.00 | $5.18 | $9K | 1.7% |
| 9 | Google: Gemini 3 Flash Preview google/gemini-3-flash-preview-20251217 | 6.0B | 17.8% | $0.50 | $3.00 | $1.20 | $7K | 1.4% | |
| 10 | Anthropic: Claude Haiku 4.5 anthropic/claude-4.5-haiku-20251001 | anthropic | 1.6B | 4.8% | $1.00 | $5.00 | $2.12 | $3K | 0.7% |
| 11 | Z.ai: GLM 5.1 z-ai/glm-5.1-20260406 | z-ai | 1.1B | 3.2% | $1.05 | $3.50 | $1.74 | $2K | 0.4% |
| 12 | Google: Gemini 2.5 Flash google/gemini-2.5-flash | 1.9B | 5.8% | $0.30 | $2.50 | $0.92 | $2K | 0.3% | |
| 13 | Z.ai: GLM 5 z-ai/glm-5-20260211 | z-ai | 1.6B | 4.7% | $0.60 | $2.08 | $1.01 | $2K | 0.3% |
| 14 | Qwen: Qwen3.6 Plus qwen/qwen3.6-plus-04-02 | qwen | 1.9B | 5.6% | $0.33 | $1.95 | $0.78 | $1K | 0.3% |
| 15 | Xiaomi: MiMo-V2-Pro xiaomi/mimo-v2-pro-20260318 | xiaomi | 879.4M | 2.6% | $1.00 | $3.00 | $1.56 | $1K | 0.3% |
| 16 | Google: Gemini 3.1 Flash Lite Preview google/gemini-3.1-flash-lite-preview-20260303 | 2.2B | 6.5% | $0.25 | $1.50 | $0.60 | $1K | 0.2% | |
| 17 | MoonshotAI: Kimi K2.5 moonshotai/kimi-k2.5-0127 | moonshotai | 1.1B | 3.3% | $0.44 | $2.00 | $0.88 | $973 | 0.2% |
| 18 | MiniMax: MiniMax M2.7 minimax/minimax-m2.7-20260318 | minimax | 1.4B | 4.3% | $0.30 | $1.20 | $0.55 | $798 | 0.2% |
| 19 | Qwen: Qwen3 Coder 480B A35B qwen/qwen3-coder-480b-a35b-07-25 | qwen | 1.1B | 3.3% | $0.22 | $1.80 | $0.66 | $737 | 0.1% |
| 20 | DeepSeek: DeepSeek V3.2 deepseek/deepseek-v3.2-20251201 | deepseek | 1.8B | 5.4% | $0.25 | $0.38 | $0.29 | $522 | 0.1% |
Cross-references
- Full leaderboard: OpenRouter app leaderboard
- Inverted view: Which models AI agents actually use
- Related benchmarks: /agentic
- Source: openrouter.ai/apps/open-webui
We reply within 48 hours
Know Open WebUI 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