Compare models
Pick two to four models. No markup on model usage: you pay the provider's list price.
| Attribute |   GPT-6.1 Sol |   Claude Sonnet 5.5 |
|---|---|---|
| Provider | OpenAI | Anthropic |
| Model id | openai/gpt-6.1-sol | anthropic/claude-sonnet-5-5 |
| Status | Available via Safeguard | Available via Safeguard |
| Input / 1M tokens | $2 | $2 |
| Output / 1M tokens | $10 | $10 |
| Price notes | Standard tier, prompts <=272K input tokens. Over 272K: $4 in / $15 out. Cached input $0.10. | Base price, full 1M context at standard rate. Cache hits $0.10/1M. Batch 50% off. |
| Context | 1.05M | 1M |
| Parameters | Not published | Not published |
| Max output | 128,000 tokens | 128,000 tokens |
| Modality | Text and image | Text and image |
| Weights | Closed | Closed |
| Zero data retention | Available | Available |
| Prompts go to | OpenAI (no processing-region constraint by default) | Anthropic (global routing by default) |
| Retention | API data not used for training unless you opt in, abuse monitoring logs that can include prompts and responses kept up to 30 days by default, some features store application state | Not used for model training without express permission, per Anthropic's API retention doc, conversation content is not retained by default except for Covered Models that require 30-day retention, flagged content and legal holds can be kept longer |
| Region | Global by default, data residency projects in US, EU and other regions (approval required, 10% uplift for models released on or after 2026-03-05) | Global by default, US-only inference via inference_geo at 1.1x pricing (Claude 4.6 and later) |
| Price checked | 2026-10-08 | 2026-10-08 |
Self-healing security runs on Safeguard.
Your first fix PR is minutes away.
No sales call required, even your agent can complete the purchase over MCP.