#1
Kimi K2.6Moonshotai
- Source day
- 2026-05-11
- Day
- 1.5T
- 30d run-rate
- 46T
Leaderboard
Top models, cost, context, and momentum
Yes: this is the model leaderboard. It ranks public model momentum from Hugging Face, source-labeled token volume from OpenRouter rankings, and OpenRouter pricing/context boards. It does not claim global usage volume.
Public usage
Tokens spent by top OpenRouter models
OpenRouter exposes public rankings on its site. The token columns below only appear when the source is live or backed by a last-known-good snapshot; the 30-day figure is a labeled run-rate estimate.
OpenRouter rankings: staleLive OpenRouter usage parsing failed, so this board is showing the last-known-good snapshot with the source date preserved.Last checked 5/21/2026
| Rank | Model | Source day | Tokens/day | 30-day run-rate |
|---|---|---|---|---|
| #1 | Kimi K2.6Moonshotai | 2026-05-11 | 1.5T | 46T |
| #2 | Claude 4.6 SonnetAnthropic | 2026-05-11 | 1.5T | 44.7T |
| #3 | Claude 4.7 OpusAnthropic | 2026-05-11 | 1.3T | 39.9T |
| #4 | Hy3 PreviewTencent | 2026-05-11 | 1.3T | 38.9T |
| #5 | Deepseek V4 FlashDeepseek | 2026-05-11 | 1.2T | 35.8T |
| #6 | Gemini 3 Flash PreviewGoogle | 2026-05-11 | 1.1T | 33.2T |
| #7 | Deepseek V3.2Deepseek | 2026-05-11 | 886.8B | 26.6T |
| #8 | Deepseek V4 ProDeepseek | 2026-05-11 | 844.8B | 25.3T |
| #9 | Minimax M2.7Minimax | 2026-05-11 | 754.1B | 22.6T |
| #10 | Grok 4.1 FastX Ai | 2026-05-11 | 682.5B | 20.5T |
| #11 | Gemini 2.5 Flash LiteGoogle | 2026-05-11 | 623.8B | 18.7T |
| #12 | Claude 4.6 OpusAnthropic | 2026-05-11 | 586.9B | 17.6T |
#2
Claude 4.6 SonnetAnthropic
- Source day
- 2026-05-11
- Day
- 1.5T
- 30d run-rate
- 44.7T
#3
Claude 4.7 OpusAnthropic
- Source day
- 2026-05-11
- Day
- 1.3T
- 30d run-rate
- 39.9T
#4
Hy3 PreviewTencent
- Source day
- 2026-05-11
- Day
- 1.3T
- 30d run-rate
- 38.9T
#5
Deepseek V4 FlashDeepseek
- Source day
- 2026-05-11
- Day
- 1.2T
- 30d run-rate
- 35.8T
#6
Gemini 3 Flash PreviewGoogle
- Source day
- 2026-05-11
- Day
- 1.1T
- 30d run-rate
- 33.2T
#7
Deepseek V3.2Deepseek
- Source day
- 2026-05-11
- Day
- 886.8B
- 30d run-rate
- 26.6T
#8
Deepseek V4 ProDeepseek
- Source day
- 2026-05-11
- Day
- 844.8B
- 30d run-rate
- 25.3T
#9
Minimax M2.7Minimax
- Source day
- 2026-05-11
- Day
- 754.1B
- 30d run-rate
- 22.6T
#10
Grok 4.1 FastX Ai
- Source day
- 2026-05-11
- Day
- 682.5B
- 30d run-rate
- 20.5T
#11
Gemini 2.5 Flash LiteGoogle
- Source day
- 2026-05-11
- Day
- 623.8B
- 30d run-rate
- 18.7T
#12
Claude 4.6 OpusAnthropic
- Source day
- 2026-05-11
- Day
- 586.9B
- 30d run-rate
- 17.6T
Top models
Public momentum leaders
#1
Qwen/Qwen3-0.6B
Qwen
18.4M1.3K
transformerssafetensorsqwen3
View source#2
openai-community/gpt2
Openai Community
17.4M3.3K
transformerspytorchtf
View source#3
Qwen/Qwen2.5-1.5B-Instruct
Qwen
14.5M704
transformerssafetensorsqwen2
View sourceOpenRouterPricing and context windows
Hugging FaceDownloads, likes, and model tags
No fake usage claimsNo global token burn unless sourced or opt-in
Cost board
Cheapest full-context fills
| Model | Context | Input | Output | Full context |
|---|---|---|---|---|
| Baidu Qianfan: CoBuddy (free)Baidu | 131.1K | $0.00/M | $0.00/M | $0.00 |
| Owl AlphaOpenrouter | 1M | $0.00/M | $0.00/M | $0.00 |
| NVIDIA: Nemotron 3 Nano Omni (free)Nvidia | 256K | $0.00/M | $0.00/M | $0.00 |
| Poolside: Laguna XS.2 (free)Poolside | 131.1K | $0.00/M | $0.00/M | $0.00 |
| Poolside: Laguna M.1 (free)Poolside | 131.1K | $0.00/M | $0.00/M | $0.00 |
| DeepSeek: DeepSeek V4 Flash (free)Deepseek | 1M | $0.00/M | $0.00/M | $0.00 |
| Google: Gemma 4 26B A4B (free)Google | 262.1K | $0.00/M | $0.00/M | $0.00 |
| Google: Gemma 4 31B (free)Google | 262.1K | $0.00/M | $0.00/M | $0.00 |
| Arcee AI: Trinity Large Thinking (free)Arcee Ai | 262.1K | $0.00/M | $0.00/M | $0.00 |
| Google: Lyria 3 Pro PreviewGoogle | 1M | $0.00/M | $0.00/M | $0.00 |
| Google: Lyria 3 Clip PreviewGoogle | 1M | $0.00/M | $0.00/M | $0.00 |
| NVIDIA: Nemotron 3 Super (free)Nvidia | 1M | $0.00/M | $0.00/M | $0.00 |
Context board
Largest published context windows
| Model | Context | Input | Output | Full context |
|---|---|---|---|---|
| Meta: Llama 4 ScoutMeta Llama | 10M | $0.08/M | $0.30/M | $0.80 |
| xAI: Grok 4.20 Multi-AgentX Ai | 2M | $2.00/M | $6.00/M | $4.00 |
| xAI: Grok 4.20X Ai | 2M | $1.25/M | $2.50/M | $2.50 |
| OpenAI GPT Latest~openai | 1.1M | $5.00/M | $30.00/M | $5.25 |
| OpenAI: GPT-5.5 ProOpenai | 1.1M | $30.00/M | $180.00/M | $31.50 |
| OpenAI: GPT-5.5Openai | 1.1M | $5.00/M | $30.00/M | $5.25 |
| OpenAI: GPT-5.4 ProOpenai | 1.1M | $30.00/M | $180.00/M | $31.50 |
| OpenAI: GPT-5.4Openai | 1.1M | $2.50/M | $15.00/M | $2.63 |
| Owl AlphaOpenrouter | 1M | $0.00/M | $0.00/M | $0.00 |
| Google: Gemini 3.1 Pro Preview Custom ToolsGoogle | 1M | $2.00/M | $12.00/M | $2.10 |
| Google: Gemini 3.5 FlashGoogle | 1M | $1.50/M | $9.00/M | $1.57 |
| Google: Gemini 3.1 Flash LiteGoogle | 1M | $0.25/M | $1.50/M | $0.2621 |
Momentum board
Open model momentum
| Model | Downloads | Likes | Tags |
|---|---|---|---|
| Qwen/Qwen3-0.6BQwen | 18.4M | 1.3K | transformers, safetensors |
| openai-community/gpt2Openai Community | 17.4M | 3.3K | transformers, pytorch |
| Qwen/Qwen2.5-1.5B-InstructQwen | 14.5M | 704 | transformers, safetensors |
| Qwen/Qwen2.5-7B-InstructQwen | 13.2M | 1.3K | transformers, safetensors |
| Qwen/Qwen3-8BQwen | 12.2M | 1.1K | transformers, safetensors |
| meta-llama/Llama-3.1-8B-InstructMeta Llama | 10.7M | 5.9K | transformers, safetensors |
| Qwen/Qwen2.5-3B-InstructQwen | 10.6M | 463 | transformers, safetensors |
| Qwen/Qwen3-4BQwen | 10.1M | 615 | transformers, safetensors |
| facebook/opt-125mFacebook | 10M | 254 | transformers, pytorch |
| meta-llama/Llama-3.2-1B-InstructMeta Llama | 8.1M | 1.4K | transformers, safetensors |
| openai/gpt-oss-20bOpenai | 8M | 4.6K | transformers, safetensors |
| Qwen/Qwen3-32BQwen | 7.1M | 693 | transformers, safetensors |