Claude Haiku 4.5 vs GLM-5
Cost and capability comparison. For a sample workload of 1,000 input and 500 output tokens across 100,000 requests/month, GLM-5 is cheaper by about $90.00/month.
| Claude Haiku 4.5 | GLM-5 | |
|---|---|---|
| Intelligence | ||
| Arena · Overall(LMArena Elo — higher is better) | 1397 | 1446✓ |
| Arena rank (overall) | #79 | #29✓ |
| Arena · Coding | 1327 | 1430✓ |
| Score evidence | Measured | Measured |
| Pricing (USD / 1M tokens) | ||
| Input | $1.00 | $1.00 |
| Output | $5.00 | $3.20✓ |
| Cached input (read) | $0.1000✓ | $0.2000 |
| Cache write | $1.25✓ | — |
| Blended(3:1 input:output blend) | $2.00 | $1.55✓ |
| Specs & capabilities | ||
| Provider | Anthropic | Z.ai (Zhipu AI) |
| Context window | 200K (200,000) | 205K (204,800)✓ |
| Max output | 8,192 | 131,072✓ |
| Modalities | text | text |
| Vision | No | No |
| Tool use | Yes | Yes |
| Reasoning | No | Yes |
| Prompt caching | Yes | Yes |
| Batch pricing | Yes | No |
| Tokenizer | claude | approx |
| Release date | — | — |
| Status | ga | ga |
Intelligence scores are community Arena ratings from LMArena / arena.ai, used under CC BY 4.0. Snapshot last refreshed 18 September 2026. Scores are a relative signal, not an absolute measure of capability. A Measured score was voted on directly; an Estimated score is inherited from an identical base model (a regional/creator-prefixed hosting duplicate). See our methodology.
Compare on your own workload
Claude Haiku 4.5 and GLM-5 are pre-loaded. Adjust the tokens and monthly volume to see which is cheaper for your usage.
Used unless you set active users below.
Results update automatically as you type.
| GLM-5 | Z.ai (Zhipu AI) | $0.00260 | $260.00 | $3,120.00 | 204,800 |
| Claude Haiku 4.5 | Anthropic | $0.00350 | $350.00 | $4,200.00 | 200,000 |
FAQ
Which is cheaper, Claude Haiku 4.5 or GLM-5?
For a workload of 1,000 input and 500 output tokens over 100,000 requests/month, GLM-5 is cheaper, costing about $260.00/month versus $350.00/month.
What is the context window of Claude Haiku 4.5 and GLM-5?
Claude Haiku 4.5 supports 200,000 tokens, while GLM-5 supports 204,800 tokens.
Estimates for planning only. Verify current pricing with each provider.