SOLVED: Pricing Issues for zai/glm-4.7, in AI Gateway?

According to the pricing page on AI Gateway, the total cost for these requests (input + output tokens) should be approximately 7x lower than they are.

Input ~30k + output ~200 = $0.01325, according to the pricing list.

This is decrementing credits in line with what the usage says, so it’s not a UI error. It also appears not to be due to reasoning tokens - these are being logged as 0 through the AI SDK, and the speed of response would support that. I suspect it’s due to Cerebras, as their pricing is substantially higher than z.ai ( https://www.cerebras.ai/pricing ) - is there any way to force the provider to be z.ai to confirm?

www.cerebras.ai

Cerebras Inference Pricing | API and Enterprise Plans

Compare Cerebras Inference pricing for free, developer, and enterprise use. Review pay-per-token options and partner access for fast AI inference.

Screenshot 2026-01-12 at 10.48.46

For reference, other GLM models are billing correctly:

Screenshot 2026-01-12 at 11.43.48

Solution: Switch the provider in providerOptions to be zai, instead of Cerebras. It is slower but correctly priced.

Screenshot 2026-01-12 at 12.02.07

Hi there, thanks for flagging. It is likely due to reasoning tokens, but we’re still confirming.

Hi - we’ve added new columns (Reasoning, Cache Read, Cache Write) to help with matching requests with cost. You can also use order: https://vercel.com/docs/ai-gateway/models-and-providers/provider-options#configure-the-provider-order-in-your-request to set your preferred providers for the model as well if you want to optimize for cost. The pricing list can vary by provider for a single model as well, if you want to check the exact prices we have by provider, that can also be found here: https://vercel.com/ai-gateway/models/glm-4.7. The pricing page shows the lowest cost per model, so this view is more accurate.

Hey there, ! Just checking in on your pricing issue for zai/glm-4.7 in AI Gateway. Have you found a solution, or do you still need help with it? Let me know!