ModelClock
API availability
Available in the API since Aug 30, 2026
Fireworks AI announced API availability for this model on 2026-08-30. Serverless Training
This date applies to API availability. Rollouts in consumer products or other hosting routes can happen on different dates.
- Hosting route
- Fireworks AI platform
- Affected scope
- Serverless Training
- Announced
- Aug 30, 2026
- First seen by ModelClock
- Oct 7, 2026
What the provider published
docs.fireworks.ai ↗ New Serverless Training models: DeepSeek V4 Flash 0731, Qwen 3.8 27B, and Muse Glimmer 30B
The following models are now available for LoRA workloads on the shared Serverless Training pool:
- Qwen 3.8 27B with up to 128K context
Read from the provider's text; the quote is the provider's exact lines.
