AI Rate CardTools: pick a model by cost
Find the cheapest offer for your monthly workload, count the tokens of a prompt, convert price units.
Cost picker
How many tokens a month you send to the model (input) and get back (output), in millions. For example, a chatbot with 1,000 conversations a day is about 10 M input and 2 M output. Don't know your numbers? Count them below in the token estimator.
Model: GLM-4.5-Air ×
| Model | Provider | Your cost/mo, $ | Input, $ | Output, $ | Context |
|---|---|---|---|---|---|
| Coding GLM 4.5 Air | aihubmix | $0.0308 | $0.014 | $0.084 | — |
| GLM 4.5 Air | zenmux | $0.17 | $0.12 | $0.29 | 128K |
| GLM-4.5-Air | huggingface | $0.30 | $0.13 | $0.85 | 131K |
| Z.ai: GLM 4.5 Air | kilo | $0.30 | $0.13 | $0.85 | 131K |
| GLM-4.5-Air | novita | $0.30 | $0.13 | $0.85 | 131K |
| Z.ai: GLM 4.5 Air | openrouter | $0.30 | $0.13 | $0.85 | 131K |
| GLM 4.5 Air | aihubmix | $0.31 | $0.14 | $0.84 | 131K |
| GLM-4.5-Air | edenai via FlexAI | $0.31 | $0.14 | $0.86 | 131K |
| zai-org/GLM-4.5-Air | siliconflow | $0.31 | $0.14 | $0.86 | 131K |
| GLM-4.5-Air | trustedrouter via Novita AI | $0.32 | $0.14 | $0.90 | — |
| Z.ai: GLM-4.5-Air | io-net | $0.34 | $0.16 | $0.94 | 131K |
| GLM-4.5-Air | aiml | $0.42 | $0.20 | $1.10 | — |
| GLM-4.5-Air | deepinfra | $0.42 | $0.20 | $1.10 | 131K |
| GLM-4.5-Air | edenai via Z.ai | $0.42 | $0.20 | $1.10 | 131K |
| GLM-4.5 Air | impossibl | $0.42 | $0.20 | $1.10 | 128K |
| GLM-4.5-Air | orcarouter | $0.42 | $0.20 | $1.10 | 131K |
| GLM-4.5-Air | requesty via DeepInfra | $0.42 | $0.20 | $1.10 | 131K |
| GLM 4.5 Air | vercel | $0.42 | $0.20 | $1.10 | 128K |
| GLM-4.5-Air | zai | $0.42 | $0.20 | $1.10 | — |
Token estimator
Don't know your workload in tokens? Paste an example of your prompt, say how many such requests you make a month and how long an answer is: you get the monthly workload. The button puts it into the picker above and shows the offers.
Price units
Providers quote per token, per 1K or per 1M tokens: the same price in all three.
AI picker
Describe the task in your own words - what the model must do, how fast, the budget, the region - and get a short list of models and providers with the reasons.
Coming soon.