Vercel AI Gateway Now Supports GPT 5.6 Sol, Luna, and Terra Models
Vercel has added support for OpenAI's GPT 5.6 Sol, Luna, and Terra models to its AI Gateway, enabling developers to monitor, cache, and manage requests to these new models.
Vercel has expanded its AI Gateway integration to include the latest GPT 5.6 Sol, Luna, and Terra models. This release allows developers to leverage existing Vercel AI Gateway features, such as caching, rate-limiting, and detailed analytics, directly with these new model variants. To implement these models, engineers must update their model endpoint configurations within their AI Gateway settings.
Primary source
Open Vercel Changelog ↗This article summarizes the source. Check the original for full details and conditions.
Comparison
| Aspect | Before / Alternative | After / This |
|---|---|---|
| Model Support | Limited to older GPT models in AI Gateway configs | Native support for GPT 5.6 Sol, Luna, and Terra variants |
| Request Monitoring | Manual tracing or external logging for new models | Unified gateway logging and performance monitoring |
| Response Caching | Custom caching logic required for unintegrated models | Edge caching enabled automatically via AI Gateway configurations |
Action Checklist
- Verify model access in your OpenAI provider credentials Ensure your API keys have permissions for the GPT 5.6 models
- Update model identifiers in the AI Gateway configuration dashboard Switch your target endpoint to point to Sol, Luna, or Terra
- Deploy configuration changes to a staging environment first Test latency and response parsing before pushing to production
- Monitor Vercel AI Gateway analytics for traffic trends Check usage rates and cache hit ratios on the new models