GLM 5.3 FlashX
Good value at this level: no ranked model within 2 Index points costs three quarters of the price or less.
No cheaper ranked model scores higher: it is on the price frontier.
As of 16 Nov 2026, GLM 5.3 FlashX by Zhipu AI is not yet ranked on the BenchLeader Index, which needs at least five independent results across two categories. API pricing: $0.370 per 1M input tokens and $1.25 per 1M output tokens ($0.590 blended at 3:1), list price on 16 Nov 2026. It streams about 86 tokens/s (OpenRouter). Released 18 Sep 2026.
Key facts (as of 16 Nov 2026)
- GLM 5.3 FlashX API pricing: $0.370 per 1M input tokens and $1.25 per 1M output tokens ($0.590 blended at 3:1) (list price, 16 Nov 2026).
- GLM 5.3 FlashX streams about 86 tokens/s (OpenRouter, 16 Nov 2026).
- GLM 5.3 FlashX was released on 18 Sep 2026 (Zhipu AI).
In detail. GLM 5.3 FlashX is a Zhipu AI open-weights reasoning model, released 18 Sep 2026. It is not yet ranked: no independent benchmark results so far, only pricing and metadata. At $0.590 per million tokens blended it is cheaper than most ranked models. Output speed of 86 tokens per second puts it faster than most, with a first token in 1.5 s. It has been measured at 4 reasoning-effort settings; this summary describes the best-scoring one, and the tabs above switch between them.
- Blended price
- $0.590/M
- $0.370 in · $1.25 out
- via models.dev
- Output speed
- 86 tok/s
- OpenRouter traffic, 7-day median; not yet measured by Artificial Analysis
- First answer
- 1.46 s
- Context
- 1M
- via models.dev
- Cost per task
- –
- Tokens per task
- –
- Released
- 18 Sep 2026
Versions
Zhipu AI has shipped 2 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
| Model | Released | Index | Rank |
|---|---|---|---|
| GLM 5.3 FlashXlowthis page | 18 Sep 2026 | – | – |
| GLM-4.7-FlashX | 19 Jan 2026 | – | – |
Reasoning-effort configurations
The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Not stated” collects results from publishers that did not say which setting they used; for a reasoning model that is usually its thinking mode, but we do not assume it. Pick a setting here or at the top of the page to see its price, speed and category scores.
| Effort | Index | Rank | Speed | First answer | Chat reply cost | Categories |
|---|---|---|---|---|---|---|
| lowbest | – | – | 86 tok/s | 1.46 s | $0.0005 | |
| high | – | – | 86 tok/s | 1.46 s | $0.0005 | |
| max | – | – | 86 tok/s | 1.46 s | $0.0005 | |
| not stated | – | – | 86 tok/s | 1.46 s | $0.0005 |
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Coding
| Benchmark | low | high | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|
| GameBench 2 Overallnot in indexacross settings | – | – | – | 56.2#24 | DuelLab GameBench 2 | |
| GameBench 2 by reasoning settingnot in index | 49.7#100 | 50.6#92 | 68.5#45 | – | DuelLab GameBench 2 |
GameBench 2 Overall: 56.2. GameBench 2, best reasoning setting (Max): 68.5. Reference only, not part of the BenchLeader Index.
DuelLab GameBench 2, release gb2-20261111-7b598bb13de4 (https://benchmarks.duellab.org/releases/gb2-20261111-7b598bb13de4/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.
API pricing: where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| Z.ai | 87 tok/s | 1.46 s | $0.370 | $1.25 | 1.0M | fp8 |
Price history
The price above, per 1M tokens, every day it changed.
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $0.075 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0005 | $0.0004 | 4.9 s |
| Summarize a 30-page report | 12,000 / 600 | $0.0052 | $0.0025 | 8.4 s |
| Code edit | 6,000 / 1,500 | $0.0041 | $0.0028 | 18.9 s |
| Agentic coding session | 60,000 / 4,000 | $0.027 | $0.014 | 48.0 s |
| Structured extraction | 2,000 / 200 | $0.0010 | $0.0005 | 3.8 s |
More from Zhipu AI
See also
Questions people ask
- Why does GLM 5.3 FlashX have no BenchLeader Index score?
- The index needs at least five independent results across at least two categories, and as of 16 Nov 2026 GLM 5.3 FlashX does not have them yet. Launch-post scores are never used, so it is ranked once independent publishers have measured it.
- How much does GLM 5.3 FlashX cost per 1M tokens?
- As of 16 Nov 2026, GLM 5.3 FlashX costs $0.370 per 1M input tokens and $1.25 per 1M output tokens, $0.590 blended (three input tokens per output token). The list price last changed on 4 Nov 2026.
- When was GLM 5.3 FlashX released?
- Zhipu AI released GLM 5.3 FlashX on 18 Sep 2026. BenchLeader has results for it at 4 reasoning-effort settings.
Data as of 16 Nov 2026. Compare these configurations.
Cite as: BenchLeader, “GLM 5.3 FlashX: benchmarks, pricing, speed and rank”, data as of 16 Nov 2026, https://www.benchleader.com/models/glm-5-3-flashx.