// Chapter 03 · Usage
Follow the Tokens
Which open models carry the traffic, how much the use of models changes, and how the picture changes from one platform to another.
Data: OpenRouter rankings-daily (CC BY 4.0), 1 January 2025 – 14 October 2026.
31%
of the open-weight tokens on OpenRouter from October 2025 to September 2026 went to DeepSeek’s models; Tencent (17%), Xiaomi (12%) and Z.ai (12%) followed.
OpenRouter rankings-daily (CC BY 4.0).

From October 2025 to September 2026, DeepSeek’s models took about a third (31%) of the tokens processed by open-weight models in OpenRouter’s daily ranking. The versions themselves change much faster: none of January 2026’s ten most used versions, open or closed, was still in September’s top ten. The ranking shows intense competition for traffic.
01 Most used
DeepSeek takes a third of the open-weight tokens of the whole year
We add up the tokens processed by open-weight models in OpenRouter’s daily top 50 from October 2025 to September 2026. Of that total, DeepSeek’s models took 31.3%, and DeepSeek V4 Flash alone 18.1%.
Open-weight token consumption in OpenRouter’s ranking, October 2025 to September 2026
DeepSeek Other developers
- 1
DeepSeek V4 Flash DeepSeek
18.1% of open tokens
- 2
MiMo-V2.5 Xiaomi
9.8% of open tokens
- 3
Hy3 Tencent
7.5% of open tokens
- 4
GLM 5.3 Flash Z.ai
6.3% of open tokens
- 5
Hy4 preview Tencent
5.8% of open tokens
- 6
DeepSeek V4.1 Flash DeepSeek
5.0% of open tokens
- 7
DeepSeek V4 Pro DeepSeek
4.6% of open tokens
- 8
Nemotron 3 Ultra NVIDIA
4.6% of open tokens
- 9
MiniMax M3 MiniMax
4.5% of open tokens
- 10
GLM 5.2 Z.ai
4.0% of open tokens
Labs stay in the lead longer than their models. DeepSeek was the most used open lab in nineteen of the twenty-one complete months since January 2025, but no single model led for more than seven months. A new version overtook the previous one from the same lab in a median of four days.
Qwen, which takes more than half of the downloads in chapter 01, took only 1.0% of these tokens.
None of January 2026’s ten most used versions was still in September’s top ten
Open-weight (verified) Not verified as open (mostly closed)
- 1
claude-4.5-sonnet anthropic
9.4%
- 2
gemini-3-flash-preview google
7.2%
- 3
grok-code-fast-1 x-ai
6.9%
- 4
mimo-v2-flash xiaomi
6.2%
- 5
claude-4.5-opus anthropic
6.1%
- 6
deepseek-v3.2 deepseek
5.8%
- 7
gemini-2.5-flash google
5.6%
- 8
grok-4.1-fast x-ai
4.1%
- 9
gemini-2.5-flash-lite google
3.9%
- 10
gpt-oss-120b openai
3.2%
- 1
glm-5.3-flash z-ai
10.5%
- 2
hy4-preview tencent
10.4%
- 3
deepseek-v4.1-flash deepseek
9.5%
- 4
gpt-5.6-luna openai
9.5%
- 5
deepseek-v4-flash deepseek
8.1%
- 6
space-bunny-alpha stealth
5.3%
- 7
mimo-v2.5 xiaomi
3.7%
- 8
nemotron-3-ultra-550b-a55b nvidia
3.6%
- 9
deepseek-v4-flash deepseek
3.2%
- 10
hy3 tencent
2.9%
02 New arrivals
In September 2026, 3 in 4 tokens in the top 50 went to versions that had entered it in the previous 90 days
Figure 3.1
Tokens going to versions that arrived in the top 50 in the previous 90 days, by month (October 2026: 14 days)
Source OpenRouter (openrouter.ai/rankings), as of 15 October 2026 (CC BY 4.0)
* October 2026: measured over 14 days only.
How we measured it
Across complete months the share runs 40%–76%; with a 60-day window 28%–64%, with 180 days 70%–91%. The three windows are alternative definitions; the 90-day one is the headline.
- Source
- OpenRouter rankings-daily (CC BY 4.0). Source: OpenRouter (openrouter.ai/rankings), as of 2026-10-15T16:43:23Z
- Base
- All tokens observed each month, including the “other” row outside the top 50
- Evidence
- E3our tabulation
In September 2026 the five most used versions, Z.ai’s GLM-5.3 Flash, Tencent’s Hy4 Preview, DeepSeek V4.1 Flash, OpenAI’s GPT-5.6 Luna and a DeepSeek V4 Flash snapshot dated 31 July, had all reached the top 50 since 11 July; between them they took 45% of all the month’s tokens, the ‘other’ row included.
Part of the turnover is one lab replacing a dated version with the next.
03 Staying power
Six months after entering the top 50, only 19% of the versions appear in it
This chart counts model versions. Of the 196 that first entered the top 50 between February 2025 and 22 April 2026, how many appeared in it 7, 28, 91 and 175 days later? After three months, only 38% did. Often a new version of the same model, or another model, has taken its place.
Figure 3.3
Share of versions in the top 50 on a given day after their first appearance
62%
122 of 196
Day 7
55%
108 of 196
Day 28
38%
75 of 196
Day 91
19%
37 of 196
Day 175
Source OpenRouter (openrouter.ai/rankings), as of 15 October 2026 (CC BY 4.0)
How we measured it
Versions already in the top 50 in January 2025 are left out: their real first day may come before the series. Versions that arrived later, with shorter follow-up, are reported separately and give higher values.
- Source
- OpenRouter rankings-daily (CC BY 4.0). Source: OpenRouter (openrouter.ai/rankings), as of 2026-10-15T16:43:23Z
- Base
- 196 versions whose first day in the top 50 fell between February 2025 and 22 April 2026, early enough to be followed for 175 days
- Evidence
- E3our tabulation
Entering the top 50 is easier than staying in it: most versions give way within a few months, often to the next version from the same lab, so a ranking taken today says little about the one in half a year.
Each figure is presence on that day, not continuity: a version can leave and come back, and one that leaves may still be in use, its tokens counted in the “other” row.
04 By subject
Which open models are used most in each subject
OpenRouter sorts a sample of its requests by subject. In that sample a closed model is the most used in every subject; the open-weight model with the largest share is Kimi K3, with 9.6% of the tokens on health & wellness.
The most used open-weight model in each subject, and the most used closed model, share of the subject’s tokens
Most used open-weight model Most used closed model
Health & wellness
Kimi K3 9.6%
best closed: Claude Sonnet 4.6 14.1%
Software & technology
Kimi K3 6.1%
best closed: Claude Opus 5.5 20.0%
Finance
Kimi K3 5.1%
best closed: Claude Opus 5.5 11.5%
Legal
DeepSeek V4.1 Flash 3.8%
best closed: Claude Opus 5.5 10.1%
Marketing & advertising
DeepSeek V4.1 Flash 1017 2.7%
best closed: Claude Opus 5.5 13.7%
Show all 17 subjects
Health & wellness
Kimi K3 9.6%
best closed: Claude Sonnet 4.6 14.1%
Relationships
GLM 5.2 7.4%
best closed: Gemini 4 Argon 26.4%
Travel & hospitality
DeepSeek V4.1 Flash 1017 7.0%
best closed: Claude Sonnet 5.5 10.8%
Software & technology
Kimi K3 6.1%
best closed: Claude Opus 5.5 20.0%
Business operations
DeepSeek V4.1 Flash 1017 5.4%
best closed: Claude Opus 5.5 11.1%
Science & engineering
DeepSeek V4.1 Flash 1017 5.2%
best closed: GPT-6.1 Sol 12.6%
Finance
Kimi K3 5.1%
best closed: Claude Opus 5.5 11.5%
Government & politics
Kimi K3 4.9%
best closed: Claude Opus 5.5 13.1%
Sales & commerce
DeepSeek V4.1 Flash 1017 4.4%
best closed: Claude Sonnet 5.5 12.2%
Customer service
GLM 5.3 4.4%
best closed: Claude Sonnet 5.5 7.9%
General
DeepSeek V4.1 Flash 1017 4.2%
best closed: GPT-6 Astra 7.7%
Gaming
DeepSeek V4.1 Flash 1017 4.0%
best closed: Claude Opus 5.5 10.0%
Education
DeepSeek V4.1 Flash 1017 4.0%
best closed: GPT-6.1 Sol 11.6%
Legal
DeepSeek V4.1 Flash 3.8%
best closed: Claude Opus 5.5 10.1%
Lifestyle
DeepSeek V4.1 Flash 1017 3.7%
best closed: Claude Opus 5.5 12.0%
Arts & entertainment
DeepSeek V4.1 Flash 1017 3.4%
best closed: Claude Opus 5.5 9.2%
Marketing & advertising
DeepSeek V4.1 Flash 1017 2.7%
best closed: Claude Opus 5.5 13.7%
05 Another platform
How models move on Cloudflare
Everything above comes from one intermediary, OpenRouter, where developers call models to generate text. To check whether what it shows holds elsewhere, we look at another platform that publishes how its open models are used: Cloudflare’s Workers AI, through Cloudflare Radar. It runs the models on Cloudflare’s own network, and the answer there is different.
On Cloudflare’s Workers AI most of the work is not text generation but embeddings, which turn texts into numbers for search. One embedding model, bge-m3, took 83.7% of the inference requests Workers AI served in October 2026.
Share of Workers AI inference requests: embeddings and text generation, by month
Every month, every task
| Month | Embeddings | Text generation | Speech recognition | Text-to-image | Translation | Other tasks |
|---|---|---|---|---|---|---|
| June 2025 | 38.1% | 31.2% | 15.2% | 7.1% | 6.3% | 2.1% |
| July 2025 | 70.0% | 17.1% | 8.3% | 2.6% | 1.3% | 0.7% |
| August 2025 | 69.9% | 16.6% | 7.3% | 4.7% | 0.7% | 0.9% |
| September 2025 | 34.2% | 41.2% | 12.6% | 6.6% | 4.3% | 1.1% |
| October 2025 | 41.9% | 28.5% | 17.0% | 5.6% | 5.8% | 1.2% |
| November 2025 | 38.7% | 28.7% | 22.9% | 1.5% | 6.6% | 1.5% |
| December 2025 | 43.1% | 26.0% | 25.4% | 2.1% | 2.1% | 1.4% |
| January 2026 | 32.7% | 27.9% | 32.1% | 1.9% | 3.5% | 1.8% |
| February 2026 | 35.3% | 27.7% | 31.4% | 2.8% | 1.0% | 1.8% |
| March 2026 | 39.0% | 33.9% | 20.3% | 1.7% | 1.6% | 3.5% |
| April 2026 | 47.0% | 26.9% | 17.3% | 4.6% | 0.9% | 3.2% |
| May 2026 | 33.9% | 10.1% | 52.0% | 1.7% | 0.6% | 1.7% |
| June 2026 | 75.9% | 12.5% | 7.9% | 0.9% | 1.1% | 1.6% |
| July 2026 | 82.7% | 9.9% | 4.1% | 0.6% | 1.8% | 0.9% |
| August 2026 | 84.3% | 8.4% | 3.4% | 0.5% | 2.3% | 1.0% |
| September 2026 | 84.3% | 9.2% | 4.1% | 0.5% | 0.8% | 1.1% |
| October 2026 | 86.7% | 8.5% | 2.8% | 0.4% | 0.7% | 0.9% |
Workers AI is used above all to search: since June 2026, 76% to 87% of the requests each month turned text into embeddings, and text generation, the work OpenRouter measures, only 8% to 13%. An open model on this platform is more often a component of a search system than a chat assistant.
Radar counts requests, not tokens: embedding one sentence and writing a long answer count the same, so its shares are never added to OpenRouter’s. The data show the change in mix, not its cause: Radar publishes no accounts, so one large customer and many small ones look the same. Use has no single ranking: it depends on where it is observed and on what activity is counted.
Within text generation no model keeps the lead: five models from four labs took turns, with six changes in 17 months. And the models that lead OpenRouter are rarely the ones that lead here: of the 85 top-five places on OpenRouter since June 2025, only 6 went to models Workers AI also serves. That counts what each platform makes available, not what is popular on it.
06 A serving provider
Seen from a provider, the same versions lead and the leader changes every month
OpenRouter sends each request to one of many providers. Novita AI is one of them: an inference provider that serves open-weight models. It shared aggregated usage for this report, which lets us look at the same models from the side of a provider.
In the usage data Novita AI shared, the ten most used model IDs took 72.3% of 58.1 trillion tokens between June and November 2026, and the top three 34.6%.
The ten most used model IDs in the usage data Novita AI shared, June–November 2026, share of all tokens
Also among OpenRouter’s three most used versions in September 2026 Others
- 1
DeepSeek V4.1 Flash DeepSeek
12.2% of tokens
- 2
GLM-5.2 Z.ai
11.6% of tokens
- 3
DeepSeek V4 Flash DeepSeek
10.8% of tokens
- 4
DeepSeek V4 Pro DeepSeek
9.6% of tokens
- 5
GLM-5.3 Flash Z.ai
9.4% of tokens
- 6
DeepSeek V4 Flash 0731 DeepSeek
6.4% of tokens
- 7
MiniMax M3 MiniMax
4.4% of tokens
- 8
Ling 3.0 Flash inclusionAI
2.9% of tokens
- 9
GLM-5.3 Z.ai
2.5% of tokens
- 10
MiMo V2.6 Pro Xiaomi
2.5% of tokens
The most used model ID of each month
- JuneDeepSeek V4 Flash
- JulyGLM-5.2
- AugustDeepSeek V4 Flash 0731
- SeptemberDeepSeek V4.1 Flash and GLM-5.3 Flash · together 41.9% of the month
- OctoberDeepSeek V4.1 Flash and GLM-5.3 Flash · together 42.4% of the month
- November, partialDeepSeek V4.1 Flash 1017
The leader changed from month to month: DeepSeek V4 Flash in June, GLM-5.2 in July and DeepSeek V4 Flash 0731 in August, while DeepSeek V4.1 Flash and GLM-5.3 Flash together took 41.9% of September’s tokens and 42.4% of October’s. Both are also among OpenRouter’s three most used versions in September.
Chapter 03 · Closing
What the ranking tells us
On OpenRouter, the versions that gather the most tokens are replaced quickly. In September 2026, 76% of the tokens in the top 50 went to versions that had entered it in the previous 90 days, and six months after entering, only 19% of the versions appeared in it.
Labs last longer than their models. DeepSeek was the most used open lab in 19 of the 21 complete months since January 2025, across several releases, and the five most used versions again gathered about half of the traffic: 50% in the third quarter of 2026.
For a team that builds on these models, a ranking is a snapshot of one month. It pays to review the alternatives every few months and to be able to change model without rewriting the application.
- Versions in the top 50
- On OpenRouter, the versions that gather the most tokens are replaced quickly. In September 2026, 76% of the tokens in the top 50 went to versions that had entered it in the previous 90 days, and six months after entering, only 19% of the versions appeared in it.
- Labs’ staying power
- Labs last longer than their models. DeepSeek was the most used open lab in 19 of the 21 complete months since January 2025, across several releases.
- Building on these models
- A ranking is a snapshot of one month. It pays to review the alternatives every few months and to be able to change model without rewriting the application.