A side-by-side comparison of Claude Sonnet 5 and GLM-5.3: input/output pricing, capabilities and available endpoints, served live from 370.AI. Both are reachable with the same API key.
| Item | Claude Sonnet 5 | GLM-5.3 |
|---|---|---|
| Input (per 1M tokens) | $1.4 | $0.77 |
| Output (per 1M tokens) | $7 | $2.42 |
| Cache read (per 1M tokens) | $0.14 | $0.143 |
| Cache write 5m (per 1M tokens) | $1.75 | — |
| Item | Claude Sonnet 5 | GLM-5.3 |
|---|---|---|
| Context window | 1,000,000 | 1,048,576 |
| Max output | — | 131,072 |
| Item | Claude Sonnet 5 | GLM-5.3 |
|---|---|---|
| function_calling | Yes | Yes |
| prompt_caching | Yes | Yes |
| vision | Yes | — |
On input, GLM-5.3 is cheaper ($1.4 vs $0.77 per 1M tokens). On output, GLM-5.3 is cheaper ($7 vs $2.42 per 1M tokens). All prices are per million tokens in USD.
GLM-5.3 does — Claude Sonnet 5 accepts 1,000,000 input tokens and GLM-5.3 accepts 1,048,576.
both support function_calling, prompt_caching; only Claude Sonnet 5 supports vision.
Yes. Both are available on 370.AI through one API key and the same OpenAI-compatible endpoint — switching means changing the model field from "claude-sonnet-5" to "glm-5.3", nothing else.
Both are available on 370.AI under one API key — switching between them means changing the model field and nothing else, so you can use each where it fits rather than picking one.