AI Model Rankings
Live LLM rankings by real-world usage. Models are ranked by tokens processed through the OpenRouter API by millions of developers. View all text models
Usage data through
| Rank | Model | Author | tokens processed | Change |
|---|---|---|---|---|
| 1 | DeepSeek V4.1 Flash 1017 | deepseek | 55.8T tokens | -1% |
| 2 | Hy4 | tencent | 20.3T tokens | +405% |
| 3 | DeepSeek V4.1 Flash | deepseek | 16T tokens | -3% |
| 4 | GLM 5.3 Flash | z-ai | 12T tokens | -20% |
| 5 | GPT-6 Luna | openai | 7.43T tokens | +2% |
| 6 | Claude Opus 5.5 | anthropic | 6.79T tokens | +4% |
| 7 | Step 5 Preview | stepfun | 6.73T tokens | +1% |
| 8 | Kimi K3.1 Pro | moonshotai | 4.38T tokens | +24% |
| 9 | GPT-6.1 Sol | openai | 4.23T tokens | +17% |
| 10 | GLM 5.3 | z-ai | 3.88T tokens | +9% |
Top models today, as text
Text summary of the Today tab of the leaderboard above. Models are ranked by tokens processed on OpenRouter over the most recent complete day, with the change measured against the day before it.
| Rank | Model | Author | Tokens | Change |
|---|---|---|---|---|
| 1 | DeepSeek V4.1 Flash 1017 | deepseek | 9.51T | -1% |
| 2 | Hy4 | tencent | 2.74T | +1% |
| 3 | DeepSeek V4.1 Flash | deepseek | 2.23T | -7% |
| 4 | GLM 5.3 Flash | z-ai | 1.64T | -37% |
| 5 | GPT-6 Luna | openai | 1.35T | +8% |
| 6 | Claude Opus 5.5 | anthropic | 1.18T | +13% |
| 7 | Step 5 Preview | stepfun | 963B | +0% |
| 8 | GPT-6.1 Sol | openai | 729B | +12% |
| 9 | MiMo-V2.6-Flash | xiaomi | 637B | -5% |
| 10 | GLM 5.3 | z-ai | 611B | -23% |
Top models this month, as text
Text summary of the This Month tab of the leaderboard above. Models are ranked by tokens processed on OpenRouter over the trailing thirty days, with the change measured against the thirty days before them.
| Rank | Model | Author | Tokens | Change |
|---|---|---|---|---|
| 1 | DeepSeek V4.1 Flash 1017 | deepseek | 176T | new |
| 2 | DeepSeek V4.1 Flash | deepseek | 81.5T | -28% |
| 3 | GLM 5.3 Flash | z-ai | 57.6T | +2% |
| 4 | GPT-6 Luna | openai | 34.2T | +90% |
| 5 | Claude Opus 5.5 | anthropic | 30.5T | +197% |
| 6 | Hy4 preview | tencent | 27.1T | -31% |
| 7 | Step 5 Preview | stepfun | 26T | +73% |
| 8 | Hy4 | tencent | 24.3T | new |
| 9 | MiMo-V2.6-Flash | xiaomi | 20.6T | -31% |
| 10 | GLM 5.3 | z-ai | 19.2T | +38% |
New and trending models this week, as text
Text summary of the New & Trending tab of the leaderboard above. Models are ranked by the percentage change in tokens processed over the trailing seven days against the seven days before, among models with at least one million tokens in the current week. A model with no prior week is marked new.
| Rank | Model | Author | Tokens | Change |
|---|---|---|---|---|
| 1 | Inkling 2 Small (free) | thinkingmachines | 507B | new |
| 2 | Claude Fable 5.2 | anthropic | 457B | new |
| 3 | ERNIE-5.5-Flash-Preview (free) | baidu | 422B | new |
| 4 | Muse Ember | meta | 248B | new |
| 5 | Gemini 4 Carbon | 234B | new | |
| 6 | Grok 4.6 (batch) | x-ai | 262M | >999% |
| 7 | Motif 3 | motif-technologies | 13.6M | >999% |
| 8 | Mi | kt | 26.2M | >999% |
| 9 | GPT-5.4 Mini (batch) | openai | 285M | >999% |
| 10 | GPT-5.6 Terra Pro (batch) | openai | 1.41M | >999% |
- General33.2%
- Agent30.4%
- Code25.9%
- Data10.5%
Classification
12.8% of all spend- 1
11.2%+4.5 - 2
7.4%+5.4 - 34.6%+3.3
- 4
4.1%+0.8 - 5
3.5%-0.9
- 63.3%-2.7
- 7
3.1%+0.5 - 83.0%+1.0
- 92.9%+0.9
- 102.7%+1.5
How these rankings are measured
What is measured
Each model is ranked by the number of tokens it processed through the OpenRouter API, counting both prompt and completion tokens. Usage is aggregated into daily buckets in UTC and totalled per model variant, so variants of the same model, such as a free variant, are ranked separately. Requests that a user or app keeps private are excluded before aggregation.
Selection period
Today, This Week, and This Month each cover a trailing window of one day, seven days, and thirty days, ending with the most recent complete daily bucket. Trending compares the trailing seven days with the seven days before it and ranks models by the percentage change in tokens, including only models with at least one million tokens in the current window so that a small base cannot produce a large percentage. New models with no prior week are listed first, up to five of them.
Freshness
The date above the rankings is the newest usage bucket the leaderboard is computed from, not the time the page was rendered or deployed, so it advances only when new usage data is aggregated.
How to read these rankings
These rankings show traffic routed through OpenRouter. The Top Models chart and the LLM Leaderboard rank models by tokens processed, while the Market Share chart counts requests. None of them measures users or spend. Models differ in verbosity and tokenization, so a higher token total shows how much a model is used, not which model is best for a task. They do not rank models by accuracy, reasoning ability, or benchmark performance. The Benchmarks section ranks those using scores from Artificial Analysis and Design Arena, plus benchmarks such as GPQA Diamond that OpenRouter runs itself and reports as median accuracy across providers. For coding, compare the Artificial Analysis Coding Index there with the Programming section, which ranks models by tokens on a sample of requests in a chosen language, such as Python. The Top Models chart names the nine most-used models in each period and groups the rest as Others. The Market Share chart shows each model author's share of text requests on OpenRouter, with the remaining authors grouped as Others.
Rankings data by OpenRouter is licensed under CC BY 4.0. Reuse and republish it with attribution. The Data API docs cover the citation format and JSON access to these datasets.