01b / Rankings
DeepSeek took a third of all tokens.
DeepSeek models took 34.1% of tokens on the Requesty gateway in week 46 (Nov 9 to 15, 2026); Azure served the most of any host, 15.3%, and the OpenAI Python SDK sent the most of any app, 21.3%.
Every token leaves an app, goes to a lab's model and is served by a host, and the three rarely line up one to one. DeepSeek's tokens alone ran on DeepInfra, Sference, Melious and DeepSeek, plus smaller hosts.
Route one model across several hosts →- Value
- 34.1% of tokens, each team capped at 2%
- Period
- Nov 9 to 15, 2026 (UTC)
- Compared with
- Nov 2 to 8, 2026
- Source
- Requesty gateway, shares, rates, ranks and latency only

Share
Post this chart
Where last week's tokens went on Requesty (Nov 9 to 15): DeepSeek models took 34.1%, Anthropic 24.4%. Azure served the most of any host (15.3%), and the OpenAI Python SDK sent the most of any app. requesty.ai/data/weekly/2026-w46/token-flow

On desktop: copy the image, open X, paste. The text is filled in for you. On a phone, Share sends the image and text to the app in one go.
| Name | This week | Last week |
|---|---|---|
| DeepSeek | 34.1% | n/a |
| Anthropic | 24.4% | n/a |
| OpenAI | 19.7% | n/a |
| Z.ai | 6.6% | n/a |
| 4.5% | n/a | |
| NVIDIA | 3.6% | n/a |
| MiniMax | 0.9% | n/a |
More from week 46
New charts every Monday
Follow by RSS →For agents
- Markdown
- /data/weekly/2026-w46/data.md
- Latest
- /data/weekly/latest.json
- llms.txt
- /data/weekly/llms.txt
# Any week URL returns Markdown when asked for it
curl -H "Accept: text/markdown" \
https://www.requesty.ai/data/weekly/2026-w46





