Reliable general-purpose Claude model for production apps.
Model details →Claude 3.5 Sonnet vs GPT-4o mini
Claude 3.5 Sonnet wins on 1 of 6 axes — pricing and capability skew in its favour for most workloads.
Low-cost model for high-volume API workloads.
Model details →Side-by-side comparison
| Capability | Claude 3.5 Sonnet | GPT-4o mini | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 200K | 128K | 🏆 Claude 3.5 Sonnet |
| Input price (per 1M) Cost per million input tokens billed by the provider. | Custom | Custom | — |
| Output price (per 1M) Cost per million output tokens billed by the provider. | Custom | Custom | — |
| Tool / function calling First-class support for emitting structured tool calls. | — | — | Tie |
| Vision input Accepts image inputs alongside text. | — | — | Tie |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | — | — | Tie |
Frequently asked questions
Is Claude 3.5 Sonnet better than GPT-4o mini?
Claude 3.5 Sonnet wins on 1 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between Claude 3.5 Sonnet and GPT-4o mini?
Input: Custom vs Custom per 1M tokens. Output: Custom vs Custom per 1M tokens.
What context windows do Claude 3.5 Sonnet and GPT-4o mini support?
Claude 3.5 Sonnet supports up to 200K tokens. GPT-4o mini supports up to 128K tokens.
Do both Claude 3.5 Sonnet and GPT-4o mini support tool calling?
Claude 3.5 Sonnet: not advertised. GPT-4o mini: not advertised.