GLM 4.5

z-ai/glm-4.5
ToolsJSONReasoning
by Z.ai · 2025-07-25

Zhipu (Z.ai) flagship open-source MoE: 355B total / 32B active. Hybrid reasoning (thinking / non-thinking modes), native tool calling and agentic surface, 128K context.

ctx128K tokens
Max output96K
Inputtext
Outputtext
p50 TTFT2.50 s
INPUT$0.60/ 1M tokens
OUTPUT$2.20/ 1M tokens
p50 TTFT2.50 s7d
p95 TTFT10.00 s7d
TRAFFIC717.3Ktokens / 7d

GLM-4.5 is a text-only language model by Z.ai, accessible via OrcaRouter's OpenAI-compatible API. It offers a 128,000-token context window and can output up to 96,000 tokens per request. The model is…

What is GLM-4.5 and who is it for?

What modalities does GLM-4.5 support?

How does GLM-4.5 compare to other text-only models?

Can GLM-4.5 handle streaming responses?

Code samples

Call from any SDK

OpenAI-compatible — keep the SDK you already use

  • OpenAI SDKhttps://api.orcarouter.ai/v1
from openai import OpenAI

client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key="$ORCAROUTER_API_KEY",
)

response = client.chat.completions.create(
    model="z-ai/glm-4.5",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Supported parameters

  • do_sample
  • include_reasoning
  • max_tokens
  • reasoning
  • request_id
  • response_format
  • stop
  • stream
  • temperature
  • thinking
  • tool_choice
  • tool_stream
  • tools
  • top_p
  • user_id

Pricing

Input / 1M tokens$0.600
Output / 1M tokens$2.20
Cache read / 1M$0.110
CurrencyUSD

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $10.80 · With prompt caching $9.09

Estimate based on list price

Token & cost estimator

Input tokens: 20Cost per request: $0.001112

Estimate only — actual token counts depend on the provider's tokenizer.

Performance

p50 TTFT
2.50 s
Output speed
43.3 tok/s
p95 TTFT
10.00 s
Error rate
13.3%

Public benchmarks

26.3
AA Coding
Better than 28% of models compared
#76 of 106
26.4
AA Intelligence
Better than 26% of models compared
#81 of 110
73.7
AA Math
Better than 68% of models compared
#26 of 81
AIME
87.3
AIME 2025
73.7
GPQA Diamond
78.2
Humanity's Last Exam
12.2
IFBench
44.1
LiveCodeBench
73.8
Long-Context Recall
48.3
MATH-500
97.9
MMLU-Pro
83.5
SciCode
34.8
TerminalBench Hard
22.0
τ²-Bench
43.0
Source: artificialanalysis.ai

How it compares

GLM 4.5GLM 5.1GLM 5.2GLM 5
Input $/M$0.60$1.40$1.40$1.00
Output $/M$2.20$4.40$4.40$3.20
Context128K200K1.0M200K
Quality7/109/109/108/10
Compare side-by-sideCompare side-by-sideCompare side-by-sideCompare side-by-side

FAQ

What is the cost of using GLM-4.5?
GLM-4.5 costs $0.60 per 1M input tokens and $2.20 per 1M output tokens. Billing is at the provider rate with zero markup from OrcaRouter.
What is the context window size of GLM-4.5?
GLM-4.5 supports a context window of 128,000 tokens and can output up to 96,000 tokens per request.
What are the main strengths of GLM-4.5?
Its primary strength is mathematical reasoning, with a MATH-500 score of 97.9. It also offers a large context window and long output capability at competitive pricing.
How does GLM-4.5 compare to other models?
Compared to models with similar context windows, GLM-4.5 has a very high MATH-500 score. Pricing is moderate. It is text-only, so it lacks multimodal support.
Does OrcaRouter store or use my data when I call GLM-4.5?
Data handling policies are determined by OrcaRouter and Z.ai. The provided facts do not specify data retention. Typically, models accessed via API do not use customer data for training unless stated otherwise. Check OrcaRouter's privacy policy for details.
How do I call GLM-4.5 via OrcaRouter's OpenAI-compatible API?
Use the base URL 'https://api.orcarouter.ai/v1', model ID 'z-ai/glm-4.5', and provide your OrcaRouter API key. The API follows OpenAI's chat completion format.
Can I use GLM-4.5 for real-time applications?
Yes, GLM-4.5 supports streaming via the 'stream' parameter, making it suitable for chatbots and live code generation.
What are the limitations of GLM-4.5?
It is text-only (no vision/audio). Its performance on non-mathematical tasks is not documented. The large context window may increase latency. Outputs should be validated for accuracy.

Embed this badge

Z.ai: GLM 4.5$0.60/M in2500ms p50via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/z-ai/glm-4.5" target="_blank"> <img src="https://www.orcarouter.ai/embed/z-ai/glm-4.5.svg" alt="Z.ai: GLM 4.5 on OrcaRouter" /> </a>
Markdown [![Z.ai: GLM 4.5](https://www.orcarouter.ai/embed/z-ai/glm-4.5.svg)](https://www.orcarouter.ai/models/z-ai/glm-4.5)

Model card as data

GET /api/public/models/z-ai/glm-4.5Open
Machine-readable:/llms.txt/llms-full.txt