Tier A — Frontier
Runs in:CNMade in:China
Z.ai (GLM / Zhipu)

GLM-4.5

Tier A — Frontier · 131K tokens

Tokonomix Editorial Team·Reviewed by Mes Kalkan··

GLM-4.5 is a foundational model of Zhipu’s GLM-4 line, designed around agentic tool use and general reasoning. It remains a solid, economical choice and anchors the family alongside its lightweight GLM-4.5 Air sibling.

Section 01

Speed analysis

Latency measured across all benchmark runs. P50 (median) and P95 (95th percentile) give a realistic picture of response speed under normal and peak load.

P50 latency (median)P95 latency56 runs
2318961416909242053150007-0807-22ms
Section 02

Quality scores

Evaluation results from judge-model scoring across diverse task categories. Scores reflect coherence, accuracy and instruction-following.

100
Coding
98
Creative
Section 03

Pricing history

Direct provider rates per million tokens, plus a typical-conversation cost estimate.

💰
API rates — GLM-4.5
$0.6000 per 1M input tokens
$2.20 per 1M output tokens
≈ $0.0008 per typical conversation (800 tokens)
Input vs output price (per 1M tokens)
per 1M input tokens$0.6000
per 1M output tokens$2.20

Pricing over time

Input & output per 1M tokens · step-line = price changes

$0.6000

input / 1M

— stable

$2.20

output / 1M

— stable

2026-07-122026-07-192026-07-19
Input
Output
Price change
⟳ synced weekly
Section 04

Tokens per second

Throughput in tokens per second, derived from measured P50 latency. Higher is better; fluctuations track provider-side load.

Throughput (tokens / s)17 / avg 46
865

Estimated from P50 latency × 200 output tokens — the absolute number depends on this assumption; the trend is what matters.

Section 05

Capabilities

jsonnotes: GLM emits a non-standard reasoning_content field beside content; read content for the answer.toolsreasoning
Section 06

Availability

Availability

How often this model answers when we call it — measured across real API requests and live tests over the last 30 days. This is separate from quality: these numbers only tell you whether the model responds, not how good the answer is.

Last 7 days

—

Last 30 days

100.0%

n=1

Median response time

6,443ms

n=1

Based on 185 measurements over the last 30 days.

Technical details

Only live API calls and live-test requests count — internal probes and benchmark runs are excluded.

Calls with a custom API key (BYOK) are excluded: those failures are key-specific, not a sign of model downtime.

Failed calls are NOT included in quality scores — quality is measured on successful responses only. Availability and quality are independent signals.

Median response time (p50) across successful calls with a recorded duration. Outliers (very slow or very fast calls) pull the median less than the average.

Total calls (30d)

1

OK responses (30d)

1

Total calls (7d)

0

OK responses (7d)

0

Section 07

Tokonomix benchmark verdicts

⚖️
Endorsed by 1 judge
Independent LLM judges evaluated this model on our weekly intelligence tests
claude-sonnet-4-583/100 · 6 runs
5 correct0 partial1 wrong83% accuracy
● 2026-07-19

GLM-4.5 adds tool use and JSON modes while maintaining performance

GLM-4.5 has expanded its capabilities with the addition of JSON output mode, tool calling functions, and reasoning features while preserving its core performance characteristics. The model continues to demonstrate strong multilingual capabilities, though specific benchmark scores are not available in this window for direct comparison. The addition of structured output support through JSON mode addresses a common need for developers building applications that require predictable response formats. Tool use functionality enables the model to interact with external functions and APIs, expanding its utility for agentic workflows and complex task execution. The reasoning capability suggests enhanced chain-of-thought processing for problems requiring multi-step logic. These additions position GLM-4.5 as a more versatile option for production use cases requiring structured outputs and external integrations. Users should note that while these new modes expand functionality, the underlying model performance appears stable. The combination of multilingual strength and newly added structured capabilities makes this update particularly relevant for developers building applications requiring both language diversity and programmatic reliability.

Quality

—

Latency p50

—

Test runs

0

✓ Added JSON mode support✓ Tool calling now available✓ Reasoning capability introduced
Section 08

Full model profile

GLM-4.5: the established agentic GLM

GLM-4.5 is a foundational model of Zhipu’s GLM-4 line, designed around agentic tool use and general reasoning. It remains a solid, economical choice and anchors the family alongside its lightweight GLM-4.5 Air sibling.

z.ai publishes GLM-4.5 at $0.60 per 1M input tokens and $2.20 per 1M output tokens.

It advertises a 128K-token context window — ample for most documents and multi-turn agent sessions.

Architecture & training signals

GLM-4.5 is a core model of Zhipu AI’s GLM-4 line, noted for an agent- and tool-use-oriented design and for capable open-weight availability. It is a reasoning-capable chat model with tool-calling and JSON over an OpenAI-compatible endpoint. Like the rest of the GLM line, it returns a non-standard reasoning_content field alongside content in its OpenAI-compatible responses; integrations should read content for the final answer and treat reasoning_content as an optional trace.

Where it shines

  • Agentic tool use and function-calling workflows.
  • General-purpose reasoning at a value price.
  • A mature, well-understood member of the family.

Where it falls short

  • Newer GLM-4.6/4.7 and the GLM-5 generation improve on it.
  • No Tokonomix benchmark data yet; verify on your tasks.
  • Non-EU hosting.

Real-world use cases

  • Tool-using agents and function-calling pipelines.
  • General assistance, drafting and analysis at scale.
  • A low-cost, cross-family consensus proposer.

Tokonomix benchmark snapshot

GLM-4.5 is newly registered on Tokonomix and not yet activated, so we have not run it through our weekly intelligence test or speed benchmark. There are no Tokonomix scores to report yet — and we will not invent any.

When it goes live, it enters the same weekly harness as every other model: identical prompts, an independent cross-family judge, and reproducible latency and cost measurements. Until then, treat the pricing and capability notes on this page as the vendor-published starting point, not as measured Tokonomix results.

EU privacy & data residency

GLM-4.5 is built by Zhipu AI (z.ai), a China-headquartered lab, and is served from non-EU infrastructure. This is important to state plainly: routing a prompt to this model is not an EU-data-residency or GDPR-sovereign choice, and Tokonomix will never tag it as one.

If your use case requires data to stay within the EU, pick a model whose provider is EU-hosted (for example our OVH or Azure-EU routes) rather than a GLM model. Tokonomix keeps z.ai out of every EU-only / sovereign routing set by design. Use GLM where its capability or price is the priority and cross-border processing is acceptable for that workload.

Verdict & alternatives

GLM-4.5 is the established, economical GLM. For newer capability step up to GLM-4.6/4.7; when latency and cost dominate, GLM-4.5 Air or the free flash tiers. It is a reliable baseline within the GLM family.

Last automated test
Jul 22, 2026 · 02:03 UTC · Speed benchmark
P50 latency
11808 ms
P95 latency
17109 ms
Errors
0 / 6 runs
Last reviewed by Tokonomix Team·July 8, 2026