# GLM-5.3 FlashX

Model tracker · checked 2026-10-14 · https://dbggr.dev/models/glm-5-3-flashx/

GLM-5.3 FlashX is a fast open-weight model from Z.ai, released 26 August 2026. At Z.ai it costs $0.37 per million input tokens and $1.25 per million output tokens, with a 1M-token context window.

- Made by: Z.ai
- Released: 2026-08-26
- Status: Generally available
- Tier: Fast
- Weights: Open
- Context window: 1,000,000 tokens
- Max output: 128,000 tokens
- Input: text, image, video
- API id: glm-5.3-flashx
- Docs: https://docs.z.ai/guides/vlm/glm-5.3-flash

## GLM-5.3 FlashX price at Z.ai

US dollars per million tokens. Blended is 3 input tokens for every output token, one number to compare on.

| Provider | Input | Output | Cached input | Blended | Batch | Checked |
|---|---|---|---|---|---|---|
| Z.ai | $0.37 | $1.25 | $0.075 | $0.59 | – | [2026-10-14](https://docs.z.ai/guides/overview/pricing) |

- Z.ai: A faster serving tier of GLM-5.3 Flash (about 200 tokens/s). Cached-input storage is free for a limited time.

## GLM-5.3 FlashX benchmarks

| Benchmark | Score | What it measures | Reported by |
|---|---|---|---|
| LMArena text score | 1473 | Elo-style score from people voting between answers | [Independent](https://arena.ai/leaderboard/text) |

Scores reported by a model's maker aren't independently checked.

## Models like GLM-5.3 FlashX

| Model | Input | Output | Context | Weights |
|---|---|---|---|---|
| GLM-5.3 FlashX | $0.37 | $1.25 | 1M | Open |
| [Gemini 3.1 Flash-Lite](https://dbggr.dev/models/gemini-3-1-flash-lite/) | $0.25 | $1.50 | 1M | Closed |
| [Muse Glimmer 30B](https://dbggr.dev/models/muse-glimmer-30b/) | $0.35 | $1.50 | 131K | Open |
| [DeepSeek V4.1 Flash](https://dbggr.dev/models/deepseek-v4-1-flash/) | $0.30 | $1.20 | 1M | Open |
| [Step 3.7 Flash](https://dbggr.dev/models/step-3-7-flash/) | $0.20 | $1.15 | 256K | Open |
| [Qwen3.6 35B A3B](https://dbggr.dev/models/qwen3-6-35b-a3b/) | $0.375 | $2.25 | 256K | Open |

## FAQ

### How much does GLM-5.3 FlashX cost?

GLM-5.3 FlashX costs $0.37 per million input tokens and $1.25 per million output tokens at Z.ai, and $0.075 per million cached input tokens. Prices are list prices in US dollars, last checked 14 October 2026.

### What is GLM-5.3 FlashX's context window?

GLM-5.3 FlashX takes up to 1,000,000 tokens in one request and writes up to 128,000 tokens in one response.

### Is GLM-5.3 FlashX open weight?

Yes. Z.ai publishes the weights, so you can run GLM-5.3 FlashX yourself or at any host that serves it.

### Where can I use GLM-5.3 FlashX?

GLM-5.3 FlashX is available from Z.ai. At Z.ai, call it as `glm-5.3-flashx`.