Menu

Guides · dev · z.ai api

Z.AI API: Flash, FlashX, and the flagship price people misread

Published 16 Oct 2026. Updated 16 Oct 2026. Researched 16 Oct 2026.

Z.AI’s pricing page is unusually clear, which makes the OpenRouter headline look worse. Here is the page, per million tokens, as fetched 16 Oct 2026:

Model Input Cached input Output
GLM-5.3-Flash $0.15 $0.03 $0.50
GLM-5.3-FlashX $0.37 $0.075 $1.25
GLM-5.3 $1.40 $0.26 $4.40
GLM-5.2 $1.40 $0.26 $4.40

Cached-input storage is listed as limited-time free. Web search is $0.01 per use. Older flash models on the same page are marked free. That “free” applies to the names on that older table, not to GLM-5.3.

GLM rows on the OpenRouter listglm-5.3-flash$0.291/Mglm-5.3-flashx$0.590/Mglm-5.3$1.26/Mglm-5.2$1.07/Mclaude-opus-5.5$8.00/Mgpt-6.1-sol$4.00/M
GLM rows on the OpenRouter list. OpenRouter list price, blended 75% input / 25% output. Snapshot 2026-10-16 05:20 UTC. Comparators resolve to Anthropic: Claude Opus 5.5 and OpenAI: GPT-6.1 Sol.
ModelBlendedvs Opusvs Sol
glm-5.3-flash$0.29196% cheaper93% cheaper
glm-5.3-flashx$0.59093% cheaper85% cheaper
glm-5.3$1.2684% cheaper69% cheaper
glm-5.2$1.0787% cheaper73% cheaper

Flash on OpenRouter matches the table. The flagship does not. FlashX on our snapshot should be checked against $0.37 / $1.25 before you quote it. The bar chart is the list price. The table above is the vendor.

Sign-up, as far as the docs go

The developer docs assume an API key and show a bearer token. We did not register, so we will not claim a card brand or a phone-number rule. The international pricing is in USD. The coding plan is a second product with credits, not a cheaper version of this table.

Anthropic base URL from the model page:

https://api.z.ai/api/anthropic

Use it with a Z.AI key. The Claude Code note says the same thing and stops there.

Related: session cost at the official rate.

Questions

What is the Z.AI flagship price?

The pricing page lists GLM-5.3 at $1.40 input, $0.26 cached input, and $4.40 output per million tokens.

Which base URL does a coding agent use?

The GLM-5.3 docs list https://api.z.ai/api/anthropic for the Anthropic protocol and an OpenAI-style URL under api.z.ai.

Sources

  1. Z.AI pricing, accessed 2026-10-16
  2. GLM-5.3 docs, accessed 2026-10-16
  3. OpenRouter GLM-5.3 endpoints, accessed 2026-10-16