Serverless infrastructure
Costs & management
Understanding costs and model availability for serverless deployments.
Deployment costs
Q: Are there costs associated with deploying fine-tuned models to serverless infrastructure?
No, deploying fine-tuned models to serverless infrastructure is free.
What’s free:
- Deploying fine-tuned models to serverless
- Hosting models on serverless infrastructure
- Deploying up to 100 fine-tuned models
What you pay for:
- Usage costs on a per-token basis when the model is actually used
- The fine-tuning process itself, if applicable
Note: This differs from on-demand deployments, which include hourly hosting costs.
Model availability
Q: Do you provide notice before removing model availability?
Yes, we provide advance notice before removing models from the serverless infrastructure:
- Minimum 2 weeks’ notice before model removal
- Longer notice periods may be provided for popular models, depending on usage
- Higher-usage models may have extended deprecation timelines
Best Practices:
- Monitor announcements regularly.
- Prepare a migration plan in advance.
- Test alternative models to ensure continuity.
- Keep your contact information updated for timely notifications.
Additional resources
- Discord Community: discord.gg/fireworks-ai
- Email Support: inquiries@fireworks.ai
- Documentation: Fireworks.ai docs
Was this page helpful?