How do you get a cache hit on GLM-4.5-AirX?

A cache hit on GLM-4.5-AirX requires an identical prompt prefix across requests. Put your stable instructions and reference material at the start of the prompt, keep them byte-identical, and let the changing part follow. Cached reads are then billed at the cache rate rather than the input rate.

How much does prompt caching save on GLM-4.5-AirX?

Prompt caching on GLM-4.5-AirX bills cached input at $0.22 per 1,000,000 token instead of $1.1 per 1,000,000 token for standard input. The saving applies to the cached prefix only; the rest of the request is billed normally.

How should you set the output budget for GLM-4.5-AirX?

Set max_tokens on GLM-4.5-AirX to the longest response your task actually needs, not the 16,384-token ceiling. Keeping the cap tight reduces worst-case spend and shortens tail latency. Raise it only for tasks that demonstrably need longer output.

What should you evaluate before moving production traffic to GLM-4.5-AirX?

Before switching production traffic to GLM-4.5-AirX, run a pilot on a representative slice of your traffic and check output quality, latency at peak concurrency, and cost per request. Verify the error and retry behaviour, and confirm the request limits you depend on match your plan.

When was GLM-4.5-AirX released, and is it still maintained?

GLM-4.5-AirX was released on 2025-07-28. Its catalog status is stable. Check the model page for deprecation notices before you build a long-lived integration on it.

Model detail

GLM-4.5-AirX

Provided by GLM

Pay-as-you-go

A faster-serving GLM-4.5 Air variant combining lightweight inference with reasoning and responsive conversational processing.

Model specs

Model ID: glm-4.5-airx

Context length: 128K
Max output: 16.384K
I/O modalities
Released: 2025-07

API endpoints

One MixRoute gateway, OpenAI-compatible

OpenAI-compatible /v1/chat/completions POST

Pricing

Flat rate, unit: /1M Tokens

Input

$1.1000 /1M Tokens

Completion

$4.5000 /1M Tokens

Cache read

$0.2200 /1M Tokens

Selection summary

Quickly judge whether it fits your workload

What is this model good for?

A faster-serving GLM-4.5 Air variant combining lightweight inference with reasoning

A faster-serving GLM-4.5 Air variant combining lightweight inference with reasoning and responsive conversational processing.

What should you check before using it?

128,000 context, 16,384 output tokens

GLM model that supports tool calling. Released 2025-07-28.

Why use it through MixRoute?

Swap the base URL, keep the GLM-4.5-AirX client

MixRoute serves GLM-4.5-AirX on the OpenAI-compatible endpoint /v1/chat/completions; point your existing client at https://api.mixroute.ai/v1 with the model ID glm-4.5-airx and re-run your integration tests.

Capabilities & compatibility

Unconfirmed capabilities stay "Unknown," no guesses

Tool calling

GLM-4.5-AirX supports function and tool calls.

EX Send a tools definition; the response returns tool_calls to execute and feed results back.

Structured output

GLM-4.5-AirX can produce JSON-formatted output on demand.

EX response_format: { type: "json_schema" } forces valid JSON output.

Streaming

GLM-4.5-AirX supports streamed responses.

EX stream: true streams tokens incrementally, so chat UIs render as they arrive.

Prompt caching

GLM-4.5-AirX supports prompt caching under supported routing conditions.

EX Keep the system prompt and tool definitions at the start of the request; repeated prefixes are automatically billed at the cache-read rate.

OpenAI SDK

Call GLM-4.5-AirX through MixRoute's OpenAI-compatible endpoint.

EX Change base_url to https://api.mixroute.ai/v1; everything else follows the OpenAI style.

Token cost estimator

Live estimate from this page's pricing, not an actual bill

Input tokens Max per request 128K

Output tokens Max per request 16.384K

Requests / month

Cache hit rate 0%

Share of the same prefix read repeatedly, up to 100%

FAQ

GLM-4.5-AirX returns up to 16,384 output tokens per request, within a 128,000-token context window. Cap the response with the max_tokens parameter so a single call cannot run past your budget.

Get started

01

Create an API key

Generate a key in the Console; one key calls every model.
02

Set the base URL

Fully OpenAI SDK-compatible; just swap the URL to connect.

https://api.mixroute.ai/v1
03

Specify the model ID

In the request's model field, enter:

glm-4.5-airx

Create an API key

New users get $5 in free credits

Test this model and alternate routes with the same request format

Start from a real workload, then let quality, total cost, and failure conditions decide whether to send production traffic.

Create an API key View integration docs