Mistral: Mistral Medium 3.5 vs Z.ai: GLM 5V Turbo
Z.ai: GLM 5V Turbo is 1.3× cheaper for input tokens: Mistral: Mistral Medium 3.5 costs $1.50 per M and Z.ai: GLM 5V Turbo costs $1.20 per M. Z.ai: GLM 5V Turbo is 1.9× cheaper for output tokens: Mistral: Mistral Medium 3.5 costs $7.50 per M and Z.ai: GLM 5V Turbo costs $4.00 per M. Mistral: Mistral Medium 3.5 reads more: Mistral: Mistral Medium 3.5 takes up to 262,144 tokens of context and Z.ai: GLM 5V Turbo up to 202,752. Mistral: Mistral Medium 3.5 accepts file, image, text; Z.ai: GLM 5V Turbo accepts image, text, video.
| Mistral: Mistral Medium 3.5 | Z.ai: GLM 5V Turbo | |
|---|---|---|
| Model id | mistralai/mistral-medium-3-5 | z-ai/glm-5v-turbo |
| Input | $1.50 per M | $1.20 per M |
| Output | $7.50 per M | $4.00 per M |
| Context length | 262,144 tokens | 202,752 tokens |
| Accepts | file, image, text | image, text, video |
| Produces | text | text |
| Served by | mistral | zai |
Prices are the providers' list prices per million tokens, as of . Both run on your own provider key through one OpenAI-compatible endpoint, with no fee on the tokens.