This model is deprecated. We still benchmark its performance, but less often: every 18 hours instead of every 6.

Z AI has launched a newer release, GLM-4.7-Flash. We suggest considering it instead.

Z AI

•

Open weights model

•

Released July 2025

GLM-4.5-Air API Provider Benchmarking & Analysis

Model Comparison

This analysis is intended to support you in choosing the best API provider of GLM-4.5-Air for your use-case.

Lowest Time per Task

Time per Intelligence Index task (minutes)

Total 2 providers

Lowest Cost per Task

Cost per Intelligence Index task

Total 2 providers

GLM-4.5-Air is available through 2 API providers, each offering different performance characteristics and pricing. Below is a comparison of the key metrics across providers.

Time per Task

Inference time (minutes) per Intelligence Index task · Lower is better

No data available

Cost per Task

Weighted average cost (USD) per Intelligence Index task · Lower is better

No data available

Pricing

Cost per Intelligence Index Task: GLM-4.5-Air

Weighted average cost (USD) per Intelligence Index task · Segmented by token type · Lower is better

No data available

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

Pricing: Cache Hit, Input, and Output: GLM-4.5-Air

Price (USD per M Tokens) · Lower is better

Price per token for cached prompts (previously processed), typically offering a significant discount compared to regular input price, represented as USD per million tokens. The values shown here are the cache hit price; cache write and cache storage are billed separately and vary by provider — see "Cache pricing by provider" for detail.

Output Speed vs. Cost per Task: GLM-4.5-Air

Output speed: output tokens divided by total request time, including time to first token · Weighted average cost (USD) per Intelligence Index task

Most attractive quadrant

No data available

Output tokens, including reasoning tokens, received per second over a request's full duration, from sending the request to receiving the final token. The headline value averages each Performance v3 workload over the past 5 days, then averages the workloads.

Speed

Average of the single-request and multi-turn agentic workloads measured

Output Speed: GLM-4.5-Air

Output tokens divided by total request time · Includes time to first token · Average of the single-request and multi-turn agentic workloads measured · Higher is better

Speed and latency metrics average each endpoint's runs over the past 5 days, and the error rate pools them. We run the benchmark every 6 hours, and endpoints of deprecated models every 18 hours.

Latency

Average of the single-request and multi-turn agentic workloads measured

Time to First Answer Token: GLM-4.5-Air

Seconds until the first answer token after any reasoning · Average of the single-request and multi-turn agentic workloads measured · Lower is better

Time to first answer token received, in seconds, after API request sent. For reasoning models, this includes the 'thinking' time of the model before providing an answer. For models which do not support streaming, this represents time to receive the completion.

Speed and latency metrics average each endpoint's runs over the past 5 days, and the error rate pools them. We run the benchmark every 6 hours, and endpoints of deprecated models every 18 hours.

Reliability

Share of requests the endpoint failed, across all the single-request and multi-turn agentic workloads measured

Endpoint Error Rate: GLM-4.5-Air

Share of requests the endpoint failed with an error, a rate limit or a timeout · Across all the single-request and multi-turn agentic workloads measured · Lower is better

Share of requests over the past 5 days that the endpoint failed with an error, a rate limit or a timeout. Failures on our side are left out of both counts. Across several workloads, the failures and requests are pooled before dividing.

Speed and latency metrics average each endpoint's runs over the past 5 days, and the error rate pools them. We run the benchmark every 6 hours, and endpoints of deprecated models every 18 hours.

Caching

Cache Hit Rate: GLM-4.5-Air

Median across multi-turn agentic session runs in the last four weeks, updated Oct 26, 2026 · Higher is better

The share of cacheable input tokens served from the provider's prompt cache, measured during multi-turn agentic sessions. We regularly measure each endpoint and report a representative rate based on recent measurements. Higher values mean more of the input is billed at the cheaper cache-hit price, where the provider offers one, which lowers the effective cost of agentic workloads. For further details, see our methodology page.

Cost per Task vs. Cache Hit Rate: GLM-4.5-Air

Weighted average cost (USD) per Intelligence Index task · Cache hit rate: median of the last four weeks, updated Oct 26, 2026

Most attractive quadrant

No data available

Key Comparison Metrics & API Features



SiliconFlow	--	--	12.48	0.0%	98k	Open
Together AI	--	--	--	--	131k	Open

Frequently Asked Questions

Common questions about GLM-4.5-Air providers

GLM-4.5-Air is available through 2 API providers: Together AI (FP8) and SiliconFlow. Each provider offers different performance characteristics and pricing.

GLM-4.5-Air is currently available through 2 API providers that we benchmark and track.

The provider with the lowest time to first answer token for GLM-4.5-Air is SiliconFlow (13.51s). Lower latency means faster initial response time.

The most affordable providers for GLM-4.5-Air by blended price are SiliconFlow ($0.21 per 1M tokens) and Together AI (FP8) ($0.29 per 1M tokens). Blended price uses a 7:2:1 cache hit/input/output token ratio.

The providers with the lowest input token pricing for GLM-4.5-Air are SiliconFlow ($0.14 per 1M input tokens) and Together AI (FP8) ($0.20 per 1M input tokens).

The providers with the lowest output token pricing for GLM-4.5-Air are SiliconFlow ($0.86 per 1M output tokens) and Together AI (FP8) ($1.10 per 1M output tokens).

Prices for GLM-4.5-Air vary up to 1.4x across providers. The most affordable is SiliconFlow at $0.21 per 1M tokens, while Together AI (FP8) charges $0.29 per 1M tokens.

1 of 2 providers support JSON mode for GLM-4.5-Air: Together AI (FP8).

All 2 providers of GLM-4.5-Air support function calling (tool use).

When choosing a provider for GLM-4.5-Air, consider: time per task (how quickly the provider completes an Intelligence Index task), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and API features like JSON mode or function calling.

Yes, provider performance can vary over time due to infrastructure changes, load balancing, and updates. We continuously benchmark all providers and display historical performance trends in the "Over Time" charts.

For information about GLM-4.5-Air's intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview

GLM-4.5-Air API Provider Benchmarking & Analysis

Lowest Time per Task

Lowest Cost per Task

Time per Task

Cost per Task

Pricing

Cost per Intelligence Index Task: GLM-4.5-Air

Cost per Intelligence Index Task

Pricing: Cache Hit, Input, and Output: GLM-4.5-Air

Cache Hit

Output Speed vs. Cost per Task: GLM-4.5-Air

End-to-End Output Speed

Speed

Output Speed: GLM-4.5-Air

End-to-End Output Speed

Time Period

Latency

Time to First Answer Token: GLM-4.5-Air

Time to First Answer Token

Time Period

Reliability

Endpoint Error Rate: GLM-4.5-Air

Endpoint Error Rate

Time Period

Caching

Cache Hit Rate: GLM-4.5-Air

What Cache Hit Rate Shows

Cost per Task vs. Cache Hit Rate: GLM-4.5-Air

Cost per Intelligence Index Task

What Cache Hit Rate Shows

Key Comparison Metrics & API Features

Frequently Asked Questions

Where can I access GLM-4.5-Air?

How many API providers offer GLM-4.5-Air?

Which provider has the lowest latency for GLM-4.5-Air?

Which provider is cheapest for GLM-4.5-Air?

Which provider has the lowest input price for GLM-4.5-Air?

Which provider has the lowest output price for GLM-4.5-Air?

How much do prices vary across GLM-4.5-Air providers?

Which GLM-4.5-Air providers support JSON mode?

Which GLM-4.5-Air providers support function calling?

How do I choose a provider for GLM-4.5-Air?

Does provider performance for GLM-4.5-Air change over time?

What are the overall capabilities of GLM-4.5-Air?