$1.40 / $4.40per 1M tokens in / out
$0.26cache read · −81%
$0.85per task at low?
#10on OpenRouter by tokens · 5T / week
Price sheetper 1M tokens
| Input | $1.40 | list |
| Output | $4.40 | |
| Cache read | $0.26 | −81% vs input |
| Context · max output | 1M · 131K | tokens |
introductory price; end date not published
Cost per task by effort?
lowAPI default$0.8536.6
max$2.0142.3
per taskHumanity's Last Exam
Same price per token at every effort; the bill grows with reasoning tokens. max costs 2.4× low for +5.7 points.
Where to buy33 providers · per 1M tokens
| Provider | Input | Output | Context |
|---|---|---|---|
| Wafer | $0.07 | $1.40 | 1M |
| Relace | $0.07 | $4.38 | 1M |
| InferenceNet | $0.08 | $3.60 | 1M |
| Makora | $0.14 | $4.40 | 1M |
| AkashML | $0.19 | $4.40 | 1M |
| DekaLLM | $0.25 | $2.95 | 1M |
| Io Net | $0.49 | $3.20 | 262K |
| Sail Research | $0.50 | $2 | 1M |
| Tenstorrent | $0.60 | $2.50 | 1M |
| Morph | $0.73 | $4.75 | 1M |
| Decart | $0.84 | $2.71 | 1M |
| DeepInfra | $0.90 | $4 | — |
| Inceptron | $0.90 | $3.50 | 1M |
| DigitalOcean | $0.91 | $2.86 | 1M |
| Fireworks | $0.98 | $3.08 | 1M |
| PrimeIntellect | $0.98 | $3.08 | 1M |
| lab-qwen | $1.13 | $3.96 | — |
| Alibaba | $1.19 | $3.74 | 1M |
| CoreWeave | $1.20 | $4 | 1M |
| AtlasCloud | $1.40 | $4.40 | 1M |
| BaseTen | $1.40 | $4.40 | 1M |
| Cloudflare | $1.40 | $4.40 | 1M |
| Crusoe | $1.40 | $4.40 | 1M |
| Featherless | $1.40 | $4.40 | — |
| GMICloud | $1.40 | $4.40 | 1M |
| Mistral | $1.40 | $4.40 | 1M |
| Modal | $1.40 | $4.40 | 1M |
| Nebius | $1.40 | $4.40 | 1M |
| Novita | $1.40 | $4.40 | — |
| Parasail | $1.40 | $4.40 | 1M |
| Together | $1.40 | $4.40 | 1M |
| Amazon Bedrock | $1.68 | $5.28 | 1M |
| ModelRun | $2.10 | $6.60 | 1M |
In Z.ai's line-upper 1M in / out
| GLM-4-Long | $1 / $1 | −53% |
| GLM-4.5-AirX | $1.10 / $4.50 | −9% |
| GLM-4.1V-Thinking-FlashX | $2 / $2 | −7% |
| GLM 5.3 | $1.40 / $4.40 | this model |
| GLM 5.2 Fast Preview | $2.20 / $7.70 | +66% |
| GLM-4.5-X | $2.20 / $8.90 | +80% |
| GLM-4V-Plus-0111 | $4 / $4 | +86% |
Cheaper for the same workvs GLM 5.3 at low
| GPT-6.1 Sol max | -15% | score +51% | $0.72 |
| GPT-6.1 Terra max | -53% | score +40% | $0.40 |
| MiMo v2.6 Pro thinkingOpen | -84% | score +35% | $0.13 |
| DeepSeek V4.1 Flash 1017 maxOpen | -69% | score +31% | $0.26 |
| GPT-6 Sol xhigh | -39% | score +29% | $0.52 |
Pricing questions
How much does GLM 5.3 cost?›
$1.40 per 1M input tokens and $4.40 per 1M output tokens. Cached input is $0.26. One Intelligence Index task costs about $0.85 at the default effort.
Is GLM 5.3 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 $0.26 per 1M, 81% below the input price.
Is GLM 5.3 cheaper than GLM 5.2?›
It costs the same per token: $1.40 / $4.40.
How does effort change the price?›
The price per token is the same at every effort. Higher effort spends more reasoning tokens: a task costs $0.85 at low, $2.01 at max.
What is a cheaper alternative to GLM 5.3?›
GPT-6.1 Sol at max effort costs -15% per task with a score +51% on Humanity's Last Exam.