Compare models
Up to 4 models side by side: list prices, what a month of real traffic costs, limits and capabilities. The best value in each row is marked with a check.
| Model | ||
|---|---|---|
| Overview | ||
| Released | - | 28 Sep 2026 |
| Status | Older Newer: GLM 5.3 Fast | Current |
| Open weights | No | No |
| Hosts APIs you can call it on | 1 | 8 |
| Price · USD per million tokens, at the lab's own API where it sells the model | ||
| Priced at | Fireworks AI | Anthropic |
| Input | $2.80 | $2.00 |
| Output | $8.80 | $10.00 |
| Cached input | $0.52 | $0.10 |
| Batch input / output | - | $1.00 / $5.00 |
| Cheapest anywhere input / output | $2.80 / $8.80 Fireworks AI | $2.00 / $10.00 Databricks |
| Monthly bill · at the price above, 30 days, with each workload's cache and batch use | ||
| Chat assistant 5,000 a day, 2K in, 500 out | $1,295 | $1,179 |
| RAG over documents 2,000 a day, 8K in, 600 out | $1,114 | $864 |
| Coding agent 1,000 a day, 40K in, 2K out | $1,973 | $1,404 |
| Overnight batch 20,000 a day, 4K in, 400 out | $8,832 | $3,600 |
| Limits | ||
| Context window | 203K tokens | 1M tokens |
| Max output | 131K tokens | 128K tokens |
| Capabilities | ||
| Takes in | Text | Text, Images, PDFs |
| Produces | Text | Text |
| Effort settings as listed by the source | - | xhigh, max |
| Streaming | ||
| Function calling | ||
| JSON mode | ||
| Structured outputs | ||
| Reasoning | ||
| Tool calling | ||
| Prompt caching | ||
| Batch API | ||
| Adaptive thinking | ||
| Always reasons | ||
| Built-in web search | ||
| Computer use | ||
| Native structured output | ||