Platform WatchJune 30, 2026via Vercel Blog
Claude Sonnet 5 now available on Vercel AI Gateway
Why it matters
Anthropic's new mid-tier model closes the capability gap between Sonnet and Opus, giving developers production-grade agentic AI at $2/M input tokens through mid-2026. This shifts the ROI math for AI-powered applications.
Key signals
- Claude Sonnet 5 now available on Vercel AI Gateway
- Launch pricing: $2/M input tokens, $10/M output tokens (through Aug 31, 2026)
- Standard list price: $3/M input tokens, $15/M output tokens
- Improvements over Sonnet 4.6: coding, agentic work, instruction-following, document parsing, long-context memory
- Performance reaches Opus-level outcomes on many tasks at Sonnet pricing
- Updated tokenizer maps same input to more tokens
- AI Gateway provides unified API, usage tracking, cost control, retries, failover, performance optimization
- Zero Data Retention support and Bring Your Own Key (BYOK) options included
- No platform markup or platform fee on inference
The hook
Claude Sonnet 5 just hit Vercel's AI Gateway. Same Opus-level coding performance. Half the price of Opus.
Claude Sonnet 5 from Anthropic is now available on . Sonnet 5 improves on Sonnet 4.6 across coding and agentic work, reaching outcomes on many tasks that previously needed an Opus model, at Sonnet pricing.AI Gateway
The model is more agentic and follows instructions more closely. Document parsing and long-context memory use are also stronger. Sonnet 5 also uses an updated tokenizer, like the recent Opus models, which can map the same input to more tokens.
Launch pricing of $2 per million input tokens and $10 per million output tokens runs through August 31, 2026. Standard list price will be $3/M input tokens, $15/M output tokens.
To use Sonnet 5, set to in the :modelanthropic/claude-sonnet-5AI SDK
You can also try Sonnet 5 in the .model playground
AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in , , , and more.custom reportingZero Data Retention supportbudgets for API keys
AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on (BYOK) requests.Bring Your Own Key