GLM 4.6V pricing
API list price by Z.ai · same on DeepInfra, Novita · checked Oct 23, 2026
$0.30 / $0.90per 1M tokens in / out
$0.05cache read · −83%
#331on OpenRouter by tokens · 1.1B / week
Price sheetper 1M tokens
| Input | $0.30 | list |
| Output | $0.90 | |
| Cache read | $0.05 | −83% vs input |
| Context · max output | 131K · 33K | tokens |
introductory price; end date not published
Where to buy2 providers · per 1M tokens
| Provider | Input | Output | Context |
|---|---|---|---|
| DeepInfra | $0.30 | $0.90 | — |
| Novita | $0.30 | $0.90 | 131K |
In Z.ai's line-upper 1M in / out
| GLM-OCR | $0.20 / $0.20 | −56% |
| GLM 5.3 Flash | $0.15 / $0.50 | −47% |
| GLM-4.1V-Thinking-Flash | $0.30 / $0.30 | −33% |
| GLM 4.6V | $0.30 / $0.90 | this model |
| GLM-4-Air-250414 | $0.50 / $0.50 | +11% |
| GLM-Z1-Air | $0.50 / $0.50 | +11% |
| GLM 5.3 FlashX | $0.37 / $1.25 | +31% |
Cheaper for the same workvs GLM 4.6V
| Claude Haiku 5.5 max | -56% | score ×5.2 | $0.21 |
| MiniMax M3.1 Flash thinking | -42% | score ×5.1 | $0.22 |
| GLM 5.3 Flash maxOpen | -47% | score ×5 | $0.28 |
| Qwen3.8 Flash thinkingOpen | -49% | score ×4.8 | $0.37 |
| GPT-6 Luna max | -56% | score ×4.6 | $0.068 |
Pricing questions
How much does GLM 4.6V cost?›
$0.30 per 1M input tokens and $0.90 per 1M output tokens on Z.ai's API and DeepInfra, Novita. Cached input is $0.05.
Is GLM 4.6V 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 $0.05 per 1M, 83% below the input price.
Is GLM 4.6V cheaper than GLM 4.5V?›
Yes: $0.30 / $0.90 against $0.60 / $1.80, 50% less per token.
What is a cheaper alternative to GLM 4.6V?›
Claude Haiku 5.5 at max effort costs -56% per task with a score ×5.2 on Humanity's Last Exam.