Loading…
Your privacy choices
Necessary storage keeps the site working. Analytics and advertising stay off unless you allow them. Cookie notice
3 provider offers
USD per 1M tokens
| Provider | Input | Output | Cached input |
|---|---|---|---|
| OpenRouter6 routes · from 0.40 | |||
| GLM 4.6, OpenRouter, Upstream provider: DeepInfra, Quantization: FP4Upstream provider — the company actually serving this routeQuantization — numeric precision of the served weightsRoute ID: deepinfra/fp4/flex | 0.40 | 1.60 | 0.08 |
| GLM 4.6, OpenRouter, Upstream provider: Venice, Quantization: FP4Upstream provider — the company actually serving this routeQuantization — numeric precision of the served weights | 0.43 | 1.75 | 0.08 |
| OpenRouter | 0.43 | 1.75 | 0.08 |
| GLM 4.6, OpenRouter, Upstream provider: DeepInfra, Quantization: FP4Upstream provider — the company actually serving this routeQuantization — numeric precision of the served weightsRoute ID: deepinfra/fp4 | 0.50 | 2.00 | 0.10 |
| GLM 4.6, OpenRouter, Upstream provider: Novita AI, Quantization: BF16Upstream provider — the company actually serving this routeQuantization — numeric precision of the served weights | 0.55 | 2.20 | 0.11 |
| GLM 4.6, OpenRouter, Upstream provider: Z.AI, Quantization: FP4Upstream provider — the company actually serving this routeQuantization — numeric precision of the served weights | 0.60 | 2.20 | 0.11 |
| Vercel AI Gateway | 0.45 | 1.80 | 0.11 |
| Together AI | 0.60 | 2.20 | Not published |
No subscription currently includes this model.
· Stale
Some values were last checked a while ago; they are the last published ones.
Published API data. Missing fields are omitted; prices are in the offer's currency, without conversion.
Correction history