AI model rankings
Live rankings from real traffic on FreeTheAI. Models are ranked by the tokens they served, with speed, success rate, and share by maker. Browse all models
Usage data through Nov 21, 2026
- Requests served
- 8.3M
- Saved by users
- $51,716
- Active users, 30 days
- 5,090
- Models live
- 184
Tokens per day by model
The five models with the most tokens in the last 7 days, the rest as Other. Click a model to keep it lit.
- Claude Sonnet 567.3M
- GLM-5.339.5M
- GLM-5.3 Flash10.9M
- Claude Opus 510.7M
- MiniMax M33.6M
- Others13.8M
| Day | Claude Sonnet 5 | GLM-5.3 | GLM-5.3 Flash | Claude Opus 5 | MiniMax M3 | Others | Total |
|---|---|---|---|---|---|---|---|
| Nov 15 | 3.3M | 6.5M | 350.1K | 0 | 418.2K | 1.1M | 11.6M |
| Nov 16 | 10.8M | 5.6M | 1.1M | 0 | 268.8K | 1.7M | 19.5M |
| Nov 17 | 9.7M | 4.7M | 542.6K | 0 | 701K | 1.5M | 17.1M |
| Nov 18 | 13.3M | 5.5M | 233.6K | 280.2K | 176.2K | 2M | 21.4M |
| Nov 19 | 18M | 6.7M | 2.2M | 1.9M | 621.7K | 3.4M | 32.8M |
| Nov 20 | 8.7M | 9.5M | 6.2M | 8.6M | 1.4M | 3.4M | 37.8M |
| Nov 21 | 3.4M | 917.3K | 277K | 0 | 67.4K | 786.8K | 5.5M |
Leaderboard
Models by tokens served in the last 7 days. Open one to compare its offers.
- 1Claude Sonnet 5Anthropic, 1M context69.6M46.0%up 42056%97.4%13s94 tok/s$0.22/M/ $1.12/M
- 2GLM-5.3Zhipu AI, 1M context46.1M30.5%down 99%99.9%24s54 tok/sFree
- 3GLM-5.3 FlashZhipu AI, 1M context11.2M7.4%down 98%100%3.4s69 tok/sFree
- 4Claude Opus 5Anthropic, 1M context10.7M7.1%new93.1%58s93 tok/s$0.56/M/ $2.80/M
- 5MiniMax M3MiniMax, 1M context3.7M2.5%down 99%99.8%5.8s88 tok/sFree
- 6GPT-4o MiniOpenAI, 128K context2.2M1.5%up 1214%99.6%9.3s—Free
- 7DeepSeek Flash LatestDeepSeek, 1M context2.1M1.4%new99.3%9.3s191 tok/s$0.10/M/ $1.00/M
- 8MiniMax M2.5MiniMax, 128K context846.6K0.6%up 11078%65.4%11s158 tok/sFree
- 9Nemotron 3 Ultra 550B A55BNVIDIA, 1M context809K0.5%down 98%100%12s51 tok/sFree
- 10Claude Sonnet 5.5Anthropic, 1M context742.8K0.5%down 66%100%13s118 tok/s$1.00/M/ $5.00/M
- 11Gemini 4 ArgonGoogle, 1M context578.8K0.4%new100%46s250 tok/s$0.22/M/ $1.12/M
- 12DeepSeek V4.1 FlashDeepSeek, 1M context562.5K0.4%new32.2%6.4s250 tok/s$0.11/M/ $0.57/M
- 13Claude Haiku 4.5Anthropic, 200K context435K0.3%new100%8.4s199 tok/s$0.92/M/ $4.61/M
- 14GPT-5.6 LunaOpenAI, 1.1M context411.1K0.3%new96.9%4.4s250 tok/s$0.10/M/ $1.00/M
- 15DeepSeek V4 FlashDeepSeek, 1M context296.1K0.2%new100%9.8s163 tok/s$0.12/M/ $0.48/M
- 16GPT OSS-120BOpenAI, 131.1K context261.9K0.2%new68.3%3.9s190 tok/sFree
- 17Gemini 3.8 FlashGoogle, 1M context178.4K0.1%new100%15s140 tok/s$0.084/M/ $0.42/M
- 18Kimi K2.7 CodeMoonshot, 262.1K context134.3K0.1%down 100%100%7.3s150 tok/sFree
- 19Kimi K3Moonshot, 1M context93.6K0.1%new40.0%45s80 tok/s$2.40/M/ $12.00/M
- 20GLM-5.3 FlashZhipu AI, 1M context53.9K0.0%up 270%66.7%15s110 tok/s$0.12/M/ $0.40/M
Records
Who leads on use, success, and speed in the last 7 days.
Top clients
By requests, all time, including the original free API.
| Requests | Tokens per request | Reply length | Cache hits | Models used | |
|---|---|---|---|---|---|
| janitor | 2.8M | 24K | 1.7K | 51% | 63 |
| node | 1.2M | 53.6K | 2.6K | 46% | 139 |
| openai-sdk | 513.9K | 94.3K | 1.1K | 84% | 119 |
| bun | 362.4K | 84.7K | 4.4K | 51% | 100 |
| tavo | 275.7K | 33.4K | 2.6K | 36% | 87 |
| goonpai | 9.1K | 10.9K | 1.1K | 67% | 19 |
- janitor2.8M
- node1.2M
- openai-sdk513.9K
- bun362.4K
- tavo275.7K
- goonpai9.1K
Daily usage
34.9B tokens and 963.4K requests in the last 30 days.
| Tokens | Requests | |
|---|---|---|
| Oct 23 | 1.5B | 42K |
| Oct 24 | 1.6B | 43.6K |
| Oct 25 | 1.8B | 47K |
| Oct 26 | 1.8B | 47.7K |
| Oct 27 | 1.6B | 44.3K |
| Oct 28 | 1.5B | 44K |
| Oct 29 | 1.5B | 44.1K |
| Oct 30 | 1.8B | 48.5K |
| Oct 31 | 1.7B | 49.7K |
| Nov 1 | 2B | 55K |
| Nov 2 | 2B | 54.1K |
| Nov 3 | 1.9B | 51.4K |
| Nov 4 | 2B | 52.5K |
| Nov 5 | 1.8B | 49.6K |
| Nov 6 | 2B | 54K |
| Nov 7 | 2.1B | 56.2K |
| Nov 8 | 2.2B | 58.3K |
| Nov 9 | 1.9B | 52.4K |
| Nov 10 | 1.8B | 47.8K |
| Nov 11 | 283.1M | 10.7K |
| Nov 12 | 8.3M | 623 |
| Nov 13 | 8.6M | 671 |
| Nov 14 | 10.6M | 475 |
| Nov 15 | 11.6M | 765 |
| Nov 16 | 19.5M | 1.4K |
| Nov 17 | 17.1M | 1.2K |
| Nov 18 | 21.4M | 1.1K |
| Nov 19 | 32.8M | 1.4K |
| Nov 20 | 37.8M | 2.5K |
| Nov 21 | 5.5M | 273 |
All time: 234.2B input tokens (181.8B of them cached) and 12.1B output tokens. Daily numbers cover FreeTheAI traffic. All-time totals also include the original free API.
Paid models
88.3M tokens across 1.4K requests on paid models, all time.
| Tokens | Requests | |
|---|---|---|
| Oct 23 | 0 | 0 |
| Oct 24 | 0 | 0 |
| Oct 25 | 0 | 0 |
| Oct 26 | 0 | 0 |
| Oct 27 | 0 | 0 |
| Oct 28 | 256 | 8 |
| Oct 29 | 0 | 0 |
| Oct 30 | 0 | 0 |
| Oct 31 | 0 | 0 |
| Nov 1 | 8.2K | 12 |
| Nov 2 | 0 | 0 |
| Nov 3 | 0 | 0 |
| Nov 4 | 0 | 0 |
| Nov 5 | 0 | 0 |
| Nov 6 | 0 | 0 |
| Nov 7 | 0 | 0 |
| Nov 8 | 0 | 0 |
| Nov 9 | 0 | 0 |
| Nov 10 | 0 | 0 |
| Nov 11 | 157K | 16 |
| Nov 12 | 809.6K | 47 |
| Nov 13 | 1.4M | 37 |
| Nov 14 | 2.9M | 60 |
| Nov 15 | 3.4M | 109 |
| Nov 16 | 10.9M | 130 |
| Nov 17 | 9.7M | 75 |
| Nov 18 | 13.6M | 182 |
| Nov 19 | 22M | 277 |
| Nov 20 | 19.1M | 455 |
| Nov 21 | 4.1M | 38 |
88.3M tokens and 1.4K requests in the last 30 days.
Most used paid models, all time
- claude-sonnet-5735 requests69.8M
- claude-opus-5121 requests10.7M
- claude-sonnet-5.5122 requests2.9M
- deepseek-flash-latest154 requests2.1M
- gemini-4-argon13 requests578.8K
- deepseek-v4.1-flash28 requests562.5K
- claude-haiku-4.529 requests435K
- gpt-5.6-luna126 requests411.1K
People per day by model
Accounts that used each model each day, last 30 days. The legend shows each model's daily average.
- GLM-5.3764
- Kimi K2.7 Code182
- GLM-5.3 Flash151
- MiniMax M394
- DeepSeek Chat40
- Others2.2K
| Day | GLM-5.3 | Kimi K2.7 Code | GLM-5.3 Flash | MiniMax M3 | DeepSeek Chat | Others | Total |
|---|---|---|---|---|---|---|---|
| Oct 23 | 966 | 190 | 190 | 141 | 38 | 1.8K | 3.4K |
| Oct 24 | 1K | 213 | 184 | 137 | 35 | 1.9K | 3.5K |
| Oct 25 | 996 | 188 | 192 | 118 | 36 | 1.8K | 3.3K |
| Oct 26 | 1K | 192 | 183 | 115 | 38 | 2.1K | 3.7K |
| Oct 27 | 1K | 237 | 251 | 166 | 43 | 2.4K | 4.1K |
| Oct 28 | 1.1K | 235 | 243 | 149 | 44 | 2.5K | 4.3K |
| Oct 29 | 1.1K | 242 | 265 | 132 | 47 | 2.3K | 4.1K |
| Oct 30 | 1.1K | 255 | 197 | 133 | 52 | 2.4K | 4.1K |
| Oct 31 | 1.2K | 277 | 253 | 159 | 60 | 3.9K | 5.8K |
| Nov 1 | 1.2K | 272 | 244 | 135 | 59 | 4K | 6K |
| Nov 2 | 1.2K | 285 | 234 | 146 | 44 | 3.5K | 5.4K |
| Nov 3 | 1.2K | 263 | 220 | 116 | 40 | 2.5K | 4.4K |
| Nov 4 | 1.2K | 294 | 226 | 144 | 71 | 3K | 5K |
| Nov 5 | 1.2K | 352 | 269 | 159 | 88 | 2.9K | 5K |
| Nov 6 | 1.2K | 315 | 224 | 138 | 67 | 3.2K | 5.1K |
| Nov 7 | 1.2K | 301 | 203 | 131 | 71 | 3.2K | 5.1K |
| Nov 8 | 1.2K | 313 | 217 | 134 | 75 | 3.4K | 5.4K |
| Nov 9 | 1.2K | 334 | 231 | 138 | 77 | 3.9K | 5.9K |
| Nov 10 | 1.2K | 368 | 263 | 165 | 106 | 3.2K | 5.3K |
| Nov 11 | 792 | 242 | 122 | 75 | 54 | 2.5K | 3.8K |
| Nov 12 | 108 | 21 | 24 | 17 | 13 | 1.2K | 1.4K |
| Nov 13 | 72 | 15 | 15 | 9 | 10 | 1.5K | 1.6K |
| Nov 14 | 61 | 11 | 13 | 5 | 5 | 678 | 773 |
| Nov 15 | 50 | 13 | 17 | 11 | 5 | 1.3K | 1.4K |
| Nov 16 | 41 | 9 | 15 | 9 | 6 | 1.6K | 1.7K |
| Nov 17 | 36 | 8 | 5 | 8 | 6 | 1.6K | 1.7K |
| Nov 18 | 34 | 11 | 11 | 6 | 4 | 448 | 514 |
| Nov 19 | 33 | 5 | 7 | 5 | 5 | 979 | 1K |
| Nov 20 | 26 | 8 | 10 | 5 | 4 | 885 | 938 |
| Nov 21 | 5 | 3 | 3 | 2 | 1 | 573 | 587 |
Retention and cache hits
Weekly retention
Of the people who used a model the week before last, the share who used it again last week.
Cache hits
Share of input tokens served from the prompt cache, last 7 days.
Where people use FreeTheAI
Accounts by the country of their latest request in the last 30 days.
- Accounts
- 9,532
- Countries
- 145
Top countries
- United States738
- Indonesia302
- India270
- Brazil266
- Philippines249
- Netherlands231
- Germany224
- China185
- Russia117
- Vietnam105
2,403 more users in 135 other countries.
Countries with fewer than 3 users are counted together. Updated every 30 minutes.
How we count
- Only our own traffic
- Every request through the FreeTheAI gateway is counted once, in 5-minute, hourly, and daily buckets on UTC. No vendor numbers, benchmarks, or votes are used, and only models in the public catalog are named.
- Tokens and ranking
- Tokens are input, cached ones included, plus output, as the provider reported them. Models rank by tokens served, and a tie goes to more requests. Share is a model's part of all tokens in the window.
- Growth
- Growth compares each model with the window just before it, using finished hours for 24 hours and finished days otherwise, so a day in progress never looks like a drop. No earlier traffic means no figure.
- Success and speed
- Success counts what the provider answered or failed; a caller's own bad request never counts. Speed is output tokens per second on streamed replies, shown as the median. Records need 20 requests in the window.
- People and retention
- A person is one FreeTheAI account, counted once per model per day. Retention compares the week before last with last week, for models that had at least 20 people in the first of those weeks.
- Cache hits and prices
- Cache hits are input tokens the provider read from its prompt cache over the last 7 days. Prices are what FreeTheAI charges per million tokens, beside the model maker's own published price.
Frequently asked questions
How is the leaderboard ranked?
By tokens FreeTheAI served for each model in the selected window. It is a measure of real use, not a quality score.
How fresh is it?
Requests are counted within about a minute, and the page refreshes its numbers every minute.
Why is a model missing?
A model appears once it is listed in the catalog and has served at least one request in the window.
Why does a free model rank so high?
Free models get a lot of traffic. Use the price filter to compare free and paid models separately; ranks stay the same so you can see where each sits overall.
Can I use this data?
Yes. Download it as JSON or CSV from the ranking section. Please credit FreeTheAI.







