GLM 4.6

z-ai/glm-4.6
ToolsJSONReasoning
by Z.ai · 2025-09-30

Successor to GLM-4.5 with the context window extended to 200K, in-thinking tool calls, and stronger agentic / search behavior.

Endpoints:/v1/chat/completions
ctx200K tokens
Max output128K
Inputtext
Outputtext
p50 TTFT3.80 s
INPUT$0.60/ 1M tokens
OUTPUT$2.20/ 1M tokens
p50 TTFT3.80 s7d
p95 TTFT10.00 s7d
TRAFFIC571.2Ktokens / 7d
Get the GLM 4.6 API →▶ Try in playground</> Use via API

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-4.6",
    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

last 7 days
p50 TTFT
3.80 s
Output speed
49.5 tok/s
p95 TTFT
10.00 s
Error rate
3.0%

Public benchmarks

Last evaluated 2025-09-30
30.2
AA Coding
Better than 32% of models compared
#72 of 106
30.2
AA Intelligence
Better than 30% of models compared
#77 of 110
44.3
AA Math
Better than 21% of models compared
#64 of 81
AIME 2025
44.3
GPQA Diamond
63.2
Humanity's Last Exam
5.2
IFBench
36.7
LiveCodeBench
56.1
Long-Context Recall
26.3
MMLU-Pro
78.4
SciCode
33.1
TerminalBench Hard
28.8
τ²-Bench
76.9
Source: artificialanalysis.ai

How it compares

GLM 4.6GLM 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
Context200K200K1.0M200K
Quality7/109/109/108/10
Compare side-by-sideCompare side-by-sideCompare side-by-sideCompare side-by-side

More from Z.ai

See all models from z-ai →
GLM 4.5
z-ai/glm-4.5
$0.60 in · $2.20 out / 1M
128K ctx· quality 7/10
 Compare side-by-side
GLM 4.7
z-ai/glm-4.7
$0.60 in · $2.20 out / 1M
200K ctx· quality 7/10
 Compare side-by-side
GLM 4.5 AirCheapest
z-ai/glm-4.5-air
$0.20 in · $1.10 out / 1M
128K ctx· quality 6/10
 Compare side-by-side

FAQ

How much does Z.ai: GLM 4.6 cost on OrcaRouter?
Z.ai: GLM 4.6 is priced at $0.60 per 1M input tokens and $2.20 per 1M output tokens via OrcaRouter. Pricing is pulled live from the routing layer.
What is Z.ai: GLM 4.6's context window?
Z.ai: GLM 4.6 supports a context window of 200K tokens. Use long-context features (RAG, summarisation) up to that limit.
How do I call Z.ai: GLM 4.6 via the OpenAI SDK?
Set OpenAI base_url to https://api.orcarouter.ai/v1, supply your OrcaRouter API key, and pass model="z-ai/glm-4.6" in the chat.completions.create call.
Does OrcaRouter rate-limit Z.ai: GLM 4.6?
Per-model rate limits follow your OrcaRouter plan. Free tiers ship with conservative caps; paid tiers lift them. Check /pricing for current quotas.

Embed this badge

Paste into your blog post
Z.ai: GLM 4.6•$0.60/M in•3800ms p50•via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/z-ai/glm-4.6" target="_blank"> <img src="https://www.orcarouter.ai/embed/z-ai/glm-4.6.svg" alt="Z.ai: GLM 4.6 on OrcaRouter" /> </a>
Markdown [![Z.ai: GLM 4.6](https://www.orcarouter.ai/embed/z-ai/glm-4.6.svg)](https://www.orcarouter.ai/models/z-ai/glm-4.6)

Model card as data

GET /api/public/models/z-ai/glm-4.6Open
Machine-readable:/llms.txt/llms-full.txt