# Claude Sonnet 5.5 vs GLM 5.3

As of October 21, 2026, Claude Sonnet 5.5 costs 43% more per input token than GLM 5.3 ($2.00 vs $1.40 per 1M), and both have a 1M-token context window.

- Page: https://models.litellm.ai/compare/claude-sonnet-5-5-vs-glm-5.3
- Claude Sonnet 5.5: https://models.litellm.ai/models/claude-sonnet-5-5
- GLM 5.3: https://models.litellm.ai/models/glm-5.3

## Side by side

| | Claude Sonnet 5.5 | GLM 5.3 |
|---|---|---|
| Input, per 1M tokens | $2.00 | $1.40 |
| Output, per 1M tokens | $10.00 | $4.40 |
| Cache read, per 1M tokens | $0.10 | $0.26 |
| Cache write, per 1M tokens | $2.50 | $0 |
| Context window | 1,000,000 tokens | 1,000,000 tokens |
| Max output | 128,000 tokens | 128,000 tokens |
| Image input | Yes | Yes |
| Tool calling | Yes | Yes |
| Structured output (JSON) | Yes | Yes |
| Prompt caching | Yes | Yes |
| Reasoning | Yes | Yes |
| Providers on LiteLLM | 7 | 17 |
| Price shown is from | Anthropic | Z.ai |
| Added to LiteLLM | September 28, 2026 | August 27, 2026 |

Headline prices in USD per 1M tokens, from LiteLLM's model price file.

## Cheapest provider for each

- Claude Sonnet 5.5: Anthropic at $2.00 input per 1M tokens (`claude-sonnet-5-5`)
- GLM 5.3: Sail at $0.98 input per 1M tokens (`sail/zai-org/GLM-5.3`)

## Benchmark scores

| Benchmark | Claude Sonnet 5.5 | GLM 5.3 |
|---|---|---|
| FrontierCode (Coding and agents) | 52.1% (xhigh) | 40.1% (max) |
| FrontierSWE (Coding and agents) | 61.9% (max) | 30.2% (max) |
| APEX-Agents (Coding and agents) | 75.5% (max) | 56.6% |
| GPQA Diamond (Reasoning and knowledge) | 95.6% (max) | 90.9% (max) |
| SimpleQA Verified (Reasoning and knowledge) | 46.5% (max) | 41.0% (max) |
| FrontierMath (tiers 1-3) (Math) | 88.8% (max) | 68.8% (max) |
| FrontierMath (tier 4) (Math) | 80.5% (max) | 29.3% (max) |
| OTIS Mock AIME 2024-2025 (Math) | 100.0% (max) | 91.1% (max) |

From the Epoch AI Benchmarking Hub (https://epoch.ai/benchmarks), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/), data as of September 29, 2026: Epoch's own runs and results it collects from each benchmark's leaderboard. Higher is better.

## When to pick which

- GLM 5.3: Costs 30% less per input token: $1.40 vs $2.00 per 1M.
- GLM 5.3: Available from 17 providers through LiteLLM, vs 7.

## FAQ

### Which is cheaper, Claude Sonnet 5.5 or GLM 5.3?

GLM 5.3 is cheaper at 3 input tokens per output token: $2.15 per 1M tokens blended ($1.40 input, $4.40 output), versus $4.00 ($2.00 and $10.00) for Claude Sonnet 5.5, as of October 21, 2026.

### Which has the larger context window, Claude Sonnet 5.5 or GLM 5.3?

Both have a 1,000,000-token context window.

### Can I switch from Claude Sonnet 5.5 to GLM 5.3 without changing my code?

Yes. Through LiteLLM both use the OpenAI format, so switching means changing the model name from "claude-sonnet-5-5" to "zai/glm-5.3", or pointing a LiteLLM gateway model alias at the other model. You can also use one as a fallback for the other.