OpenRouter Model Usage (October 2026)

In October 2026, DeepSeek V4.1 Flash ranks first with 126.3T, followed by GLM 5.3 Flash (52.3T) and DeepSeek V4.1 Flash 1017 (47.1T). Top 20 of 1,044 candidates.

Data as of October 2026

#ModelProviderTokensRequests
1DeepSeek V4.1 FlashDeepSeek126.3T2.7B
2GLM 5.3 FlashZ.ai52.3T2.6B
3DeepSeek V4.1 Flash 1017DeepSeek47.1T801.8M
4MiMo-V2.6-FlashXiaomi40.5T514.1M
5SSpace Bunny AlphaStealth38.5T661.6M
6Hy4 previewTencent34.6T320.2M
7GPT-6 LunaOpenAI30.7T1.7B
8Step 5 PreviewStepFun27.5T136.4M
9Nemotron 3 UltraNvidia25.9T205.5M
10Claude Opus 5.5Anthropic25.5T204.7M
11DeepSeek V4 Flash 0731DeepSeek20.9T1.6B
12GLM 5.3Z.ai19.1T279.1M
13JJev 1.13Typesafe13.7T4.3B
14DeepSeek V4 Flash 0423DeepSeek13.3T1.6B
15Hy3Tencent12.1T154.5M
16Muse Spark 1.3 ContributorMeta11.3T193.7M
17Claude Sonnet 5.5Anthropic9.5T160.4M
18GPT-5.6 LunaOpenAI9.2T785.2M
19Kimi K3Moonshot9.0T142.5M
20GPT-6.1 SolOpenAI8.7T188.7M

How this chart is built

Based on public call data from a leading multi-model API gateway, reflecting how much each model is used in production. Usage is aggregated on a monthly basis.

Positions are renumbered from high to low by this table's own metric, independent of any ranking the source publishes. Figures are the current real data with no manual adjustment; values we cannot obtain show as “—” and are never filled in with estimates.

FAQ

OpenRouter Model Usage: who ranks #1?

In October 2026, DeepSeek V4.1 Flash ranks #1 (tokens: 126.3T); GLM 5.3 Flash is second (52.3T), followed by DeepSeek V4.1 Flash 1017 (47.1T).

OpenRouter Model Usage: what are the top 10?

Ranked by tokens as of October 2026, the top 10 are: 1. DeepSeek V4.1 Flash, 2. GLM 5.3 Flash, 3. DeepSeek V4.1 Flash 1017, 4. MiMo-V2.6-Flash, 5. Space Bunny Alpha, 6. Hy4 preview, 7. GPT-6 Luna, 8. Step 5 Preview, 9. Nemotron 3 Ultra, 10. Claude Opus 5.5. The full top 20 is in the table on this page.

OpenRouter Model Usage: where does the data come from, and how often is it updated?

Based on public call data from a leading multi-model API gateway, reflecting how much each model is used in production. Usage is aggregated on a monthly basis. Updated monthly; the current data is for October 2026.