Z.ai › GLM 5.3 Flash › Pricing
$0.15 / $0.50per 1M tokens in / out
$0.03cache read · −80%
$0.28per task at max?
#3on OpenRouter by tokens · 11.3T / week
Price sheetper 1M tokens
| Input | $0.15 | list |
| Output | $0.50 | |
| Cache read | $0.03 | −80% vs input |
| Context · max output | 1M · 131K | tokens |
introductory price; end date not published
Where to buy26 providers · per 1M tokens
| Provider | Input | Output | Context |
|---|---|---|---|
| OpenInference | $0.047 | $0.16 | 1M |
| Reka | $0.06 | $1.60 | 1M |
| Wafer | $0.074 | $0.20 | 1M |
| Relace | $0.075 | $0.50 | 1M |
| Sail Research | $0.078 | $0.30 | 1M |
| Near AI | $0.08 | $0.50 | 1M |
| Inceptron | $0.10 | $0.69 | 1M |
| InferenceNet | $0.12 | $0.39 | 1M |
| NextBit | $0.12 | $0.40 | 1M |
| DigitalOcean | $0.13 | $0.44 | 1M |
| Morph | $0.14 | $0.65 | 1M |
| Makora | $0.14 | $0.47 | 1M |
| BaseTen | $0.15 | $0.50 | 1M |
| CoreWeave | $0.15 | $0.50 | 1M |
| Crusoe | $0.15 | $0.50 | 1M |
| DeepInfra | $0.15 | $0.50 | — |
| Featherless | $0.15 | $0.50 | — |
| Fireworks | $0.15 | $0.50 | 1M |
| Friendli | $0.15 | $0.50 | 1M |
| GMICloud | $0.15 | $0.50 | 1M |
| Modal | $0.15 | $0.50 | 1M |
| Novita | $0.15 | $0.50 | — |
| PrimeIntellect | $0.15 | $0.50 | 1M |
| SiliconFlow | $0.15 | $0.50 | 1M |
| Together | $0.15 | $0.50 | 1M |
| Venice | $0.15 | $0.50 | 1M |
In Z.ai's line-upper 1M in / out
| GLM-4.6V-FlashX | $0.04 / $0.40 | −45% |
| GLM-4.7-FlashX | $0.07 / $0.40 | −36% |
| GLM-OCR | $0.20 / $0.20 | −16% |
| GLM 5.3 Flash | $0.15 / $0.50 | this model |
| GLM-4.1V-Thinking-Flash | $0.30 / $0.30 | +26% |
| GLM-4-Air-250414 | $0.50 / $0.50 | 2.1× |
| GLM-Z1-Air | $0.50 / $0.50 | 2.1× |
Cheaper for the same workvs GLM 5.3 Flash at max
| GPT-6.1 Sol medium | -25% | score +14% | $0.21 |
| MiMo v2.6 Pro thinkingOpen | -53% | score +11% | $0.13 |
| DeepSeek V4.1 Flash 1017 maxOpen | -8% | score +8% | $0.26 |
| Claude Haiku 5.5 max | -25% | score +4% | $0.21 |
| MiniMax M3.1 Flash thinking | -22% | same score | $0.22 |
Pricing questions
How much does GLM 5.3 Flash cost?›
$0.15 per 1M input tokens and $0.50 per 1M output tokens. Cached input is $0.03. One Intelligence Index task costs about $0.28 at the default effort.
Is GLM 5.3 Flash free to use?›
There is no free API tier, but the weights are open: you can run it on your own hardware for the cost of compute.
How much does prompt caching save?›
Cache reads cost $0.03 per 1M, 80% below the input price.
What is a cheaper alternative to GLM 5.3 Flash?›
GPT-6.1 Sol at medium effort costs -25% per task with a score +14% on Humanity's Last Exam.