# Fireworks reports serving more than 40t tokens per day

Digest AI · Business & Funding · published 2026-11-04T16:35:44Z

Canonical: https://digestai.news/story/fireworks-reports-serving-more-than-40t-tokens-per-day

## Summary

Interconnects’ dashboard tracks open model inference usage across the web, but the data is noisy and incomplete. The author notes that the best estimates come from a handful of startups—Baseten, Fireworks, and Together AI—whose public token‑volume disclosures show near‑exponential growth.

Fireworks announced at its first company conference that it is serving more than 40T tokens per day to customers’ customized models. The company said this figure grew over 2× from summer, suggesting a fall total well above 100T tokens. The author compares these numbers to closed‑model volumes from hyperscalers such as Amazon Bedrock and Azure’s model garden, noting that the latter do not break down usage by model category.

The notes also reference OpenRouter’s token volume share and Google’s earnings‑reported platform usage, which the author overlays with the open‑model data to illustrate the market’s size and trajectory. The article remains a research note, with the author acknowledging that the figures are approximations and that the dashboard will stay free for the foreseeable future.

## Key points

- fireworks serving more than 40t tokens per day
- baseten fireworks together ai used as bellwethers for open model inference
- open model inference shows near‑exponential growth before GLM 5.2 step change

## Why it matters

The rapid rise of open‑model inference volumes signals growing competition with hyperscalers and highlights the need for clearer policy and market metrics in AI deployment.

## Sources

1. [How big is the open model economy today?](https://interconnects.ai/p/how-well-can-we-measure-open-model) (Interconnects, 2026-11-04)

Part of the developing story: [Fireworks AI Accelerates Deployment and Scale](https://digestai.news/thread/fireworks-announces-faster-agent-inference-and-sovereign-deployment) (2 stories)

## Cite

Digest AI, "Fireworks reports serving more than 40t tokens per day", 4 November 2026, https://digestai.news/story/fireworks-reports-serving-more-than-40t-tokens-per-day

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/fireworks-reports-serving-more-than-40t-tokens-per-day.json