OpenRouter app · rank #39Snapshot 2026-06-23
openbench
11.5B
Tokens (30d)
0
Requests
$8K
Monthly cost
$0.71
Blended $/M tokens
Ranks in the 17th percentile by spend and 15th by raw tokens among the top 46 apps.
Primary driver
Google: Gemini 2.5 Flash is openbench's top model at 1.1B — 9.4% of total token volume and 12.2% of monthly cost ($995).
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 | Z.ai: GLM 5.1 z-ai/glm-5.1-20260406 | z-ai | 717.5M | 6.2% | $0.98 | $3.08 | $1.57 | $1K | 13.8% |
| 2 | MoonshotAI: Kimi K2.6 moonshotai/kimi-k2.6-20260420 | moonshotai | 716.5M | 6.2% | $0.66 | $3.41 | $1.43 | $1K | 12.6% |
| 3 | MoonshotAI: Kimi K2 0905 moonshotai/kimi-k2-0905 | moonshotai | 901.8M | 7.8% | $0.60 | $2.50 | $1.13 | $1K | 12.5% |
| 4 | Google: Gemini 2.5 Flash google/gemini-2.5-flash | 1.1B | 9.4% | $0.30 | $2.50 | $0.92 | $995 | 12.2% | |
| 5 | Z.ai: GLM 5 z-ai/glm-5-20260211 | z-ai | 675.0M | 5.9% | $0.60 | $1.92 | $0.97 | $655 | 8.0% |
| 6 | Qwen: Qwen3.5 397B A17B qwen/qwen3.5-397b-a17b-20260216 | qwen | 565.2M | 4.9% | $0.39 | $2.45 | $0.96 | $544 | 6.7% |
| 7 | Qwen: Qwen3 235B A22B qwen/qwen3-235b-a22b-07-25 | qwen | 454.1M | 3.9% | $0.46 | $1.82 | $0.84 | $380 | 4.7% |
| 8 | Z.ai: GLM 4.6 z-ai/glm-4.6 | z-ai | 459.8M | 4.0% | $0.43 | $1.74 | $0.80 | $366 | 4.5% |
| 9 | Z.ai: GLM 4.7 z-ai/glm-4.7-20251222 | z-ai | 445.6M | 3.9% | $0.40 | $1.75 | $0.78 | $347 | 4.3% |
| 10 | DeepSeek: DeepSeek V4 Pro deepseek/deepseek-v4-pro-20260423 | deepseek | 591.7M | 5.1% | $0.43 | $0.87 | $0.56 | $329 | 4.0% |
| 11 | MoonshotAI: Kimi K2.5 moonshotai/kimi-k2.5-0127 | moonshotai | 370.4M | 3.2% | $0.38 | $2.02 | $0.84 | $310 | 3.8% |
| 12 | MiniMax: MiniMax M2.5 minimax/minimax-m2.5-20260211 | minimax | 634.2M | 5.5% | $0.15 | $0.90 | $0.36 | $228 | 2.8% |
| 13 | MiniMax: MiniMax M2.7 minimax/minimax-m2.7-20260318 | minimax | 434.6M | 3.8% | $0.24 | $0.96 | $0.44 | $192 | 2.4% |
| 14 | DeepSeek: DeepSeek V3.1 deepseek/deepseek-chat-v3.1 | deepseek | 471.2M | 4.1% | $0.21 | $0.79 | $0.37 | $175 | 2.2% |
| 15 | Qwen: Qwen3.5-35B-A3B qwen/qwen3.5-35b-a3b-20260224 | qwen | 439.7M | 3.8% | $0.14 | $1.00 | $0.38 | $167 | 2.1% |
| 16 | DeepSeek: DeepSeek V4 Flash deepseek/deepseek-v4-flash-20260423 | deepseek | 681.8M | 5.9% | $0.09 | $0.18 | $0.12 | $79 | 1.0% |
| 17 | Google: Gemma 4 31B google/gemma-4-31b-it-20260402 | 381.4M | 3.3% | $0.12 | $0.35 | $0.18 | $70 | 0.9% | |
| 18 | Z.ai: GLM 4.7 Flash z-ai/glm-4.7-flash-20260119 | z-ai | 407.7M | 3.5% | $0.06 | $0.40 | $0.16 | $63 | 0.8% |
| 19 | OpenAI: gpt-oss-120b openai/gpt-oss-120b | openai | 508.0M | 4.4% | $0.04 | $0.18 | $0.08 | $40 | 0.5% |
| 20 | OpenAI: gpt-oss-20b openai/gpt-oss-20b | openai | 568.8M | 4.9% | $0.03 | $0.14 | $0.06 | $34 | 0.4% |
Cross-references
- Full leaderboard: OpenRouter app leaderboard
- Inverted view: Which models AI agents actually use
- Related benchmarks: /agentic
- Source: openrouter.ai/apps/openbench
We reply within 48 hours
Know openbench 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