What is the rate limit for GLM-4.5-Air?

The current model record does not publish a numeric rate limit for GLM-4.5-Air. Confirm the quota for your plan in the console, then run a short load test at your expected concurrency to establish the effective ceiling before production.

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

A cache hit on GLM-4.5-Air 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.

Can you call GLM-4.5-Air with the OpenAI SDK you already use?

Yes. GLM-4.5-Air is reachable through an OpenAI-compatible endpoint, so an existing OpenAI SDK client works after pointing the base URL at MixRoute and setting the model parameter to glm-4.5-air . Keep your current request and response handling.

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

GLM-4.5-Air was released on 2025-07-25. Its catalog status is stable. Check the model page for deprecation notices before you build a long-lived integration on it.

How does GLM-4.5-Air score on benchmarks?

Recorded results for GLM-4.5-Air: aa_intelligence_index 14.8; arena_text 75.8. Benchmark positions are a coarse filter only — run your own prompts against the candidate models before you commit, because ranking shifts with task shape and prompt style.

Model detail

GLM-4.5-Air

Q: How does GLM-4.5-Air compare with gpt-3.5-turbo-1106, and what should you compare?

GLM-4.5-Air sits alongside gpt-3.5-turbo-1106 , gpt-4.1-mini , gpt-4.1-mini-2025-04-14 in the catalog. Compare them on the dimensions that change your bill and your users’ experience: task quality on your own prompts, latency at your concurrency, context and output limits, and cost per completed task rather than per token.

Provided by GLM

Pay-as-you-go

GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter size. GLM-4.5-Air also supports hybrid inference modes, offering a "thinking mode" for advanced reasoning and tool use, and a "non-thinking mode" for real-time interaction. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)

Model specs

Model ID: glm-4.5-air

Context length: 131.072K
Max output: 98.304K
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

$0.2000 /1M Tokens

Completion

$1.1000 /1M Tokens

Cache read

$0.0300 /1M Tokens

Selection summary

Quickly judge whether it fits your workload

What is this model good for?

Lightweight variant of our latest flagship model family

What should you check before using it?

131,072 context, 98,304 output tokens

Model type: text. Verify supported features and quotas with the provider documentation. Knowledge cutoff: 2024-12-31. Released 2025-07-25.

Why use it through MixRoute?

GLM-4.5-Air runs tools and structured output here

Tool calling and structured output run on that route as well. MixRoute serves GLM-4.5-Air 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-air and re-run your integration tests.

Capabilities & compatibility

Unconfirmed capabilities stay "Unknown," no guesses

Tool calling

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

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

Streaming

GLM-4.5-Air supports streamed responses.

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

Prompt caching

GLM-4.5-Air 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-Air 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 131.072K

Output tokens Max per request 98.304K

Requests / month

Cache hit rate 0%

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

FAQ

GLM-4.5-Air sits alongside gpt-3.5-turbo-1106, gpt-4.1-mini, gpt-4.1-mini-2025-04-14 in the catalog. Compare them on the dimensions that change your bill and your users’ experience: task quality on your own prompts, latency at your concurrency, context and output limits, and cost per completed task rather than per token.

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-air

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