Coding GLM 4.6
Z.AI · text → text
Input$0.06 /M
Output$0.22 /M
Cache read$0.011 /M
← ModelsCoding GLM 4.6GLM 4.6
Coding GLM 4.6 vs GLM 4.6
Compare Coding GLM 4.6 from Z.AI and GLM 4.6 from Z.AI on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the AIHubMix API.
Coding GLM 4.6GLM 4.6+ Add model · 2/4
GLM 4.6
Z.AI · text → text
GLM-4.6 is Zhipu’s latest flagship model (total parameters 355B, activation parameters 32B), comprehensively surpassing GLM-4.5. Its coding capability is aligned with Claude Sonnet 4, making it a top domestic coding model; the context window has been expanded from 128K to 200K, better suited for long code and agent tasks; inference capabilities have been significantly enhanced and support tool invocation during processing; improvements have been made in tool calling, search agents, writing style, role play, and multilingual translation. The model is named glm-4.6 and is provided by three vendors, with calls prioritized to the Sophnet platform.
Input$0.274 /M
Output$1.0959 /M
Cache read$0.0548 /M
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
Coding GLM 4.6
GLM 4.6
Input /M
$0.06
$0.274
Output /M
$0.22
$1.0959
Cache read /M
$0.011
$0.0548
Context length
200,000
200,000
Max output
131,072
131,072
Time to First Token
3.7 s
1.7 s
Throughput
31.1 tok/s
34.4 tok/s
Modalities
text
text
Supported Parameters
thinkingtoolsfunction callingstructured outputs
thinkingtoolsfunction callingstructured outputs
API Formats
Released
September 30, 2025
September 30, 2025
Promotional prices show the discounted rate; see each model page for promotion windows.
Activity Past 30 Days
Daily traffic served through AIHubMix — how demand for each model is trending.
coding-glm-4.6glm-4.6
Tokens / day
-
Requests / day
-
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
coding-glm-4.6glm-4.6
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
LMArena Benchmarks
LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.
Text
coding-glm-4.6glm-4.6
1380142014601500
Overall
14251425
Coding
14591459
Math
14211421
Hard prompts
14421442
Instruction following
14151415
Multi-turn
14221422
Creative writing
14031403
Longer query
14331433
Chinese
14821482
English
14371437
WebDev Arena
coding-glm-4.6glm-4.6
134013601380
Overall
13551355
HTML
13631363
Source: LMArena (arena.ai) leaderboard, imported by AIHubMix. Models without published ratings are omitted per chart.
Cost calculator
Estimate your monthly bill for the same workload on each model.
Coding GLM 4.6
$6.90 /mo
GLM 4.6
$32.88 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: Coding GLM 4.6, GLM 4.6?
Coding GLM 4.6: $0.22/M output tokens; GLM 4.6: $1.0959/M. Use the cost calculator above to estimate your own workload.
How do their coding arena scores compare?
Coding GLM 4.6: 1459; GLM 4.6: 1459 (LMArena coding leaderboard).
Which responds faster?
GLM 4.6: 1.7s time to first token measured on AIHubMix; see the live performance charts above for how each model behaves across the day.
How large is each context window?
Coding GLM 4.6 accepts 200,000 and GLM 4.6 accepts 200,000 input tokens. Maximum output per request is 131,072 tokens on Coding GLM 4.6 and 131,072 tokens on GLM 4.6.
Which one generates tokens faster?
GLM 4.6 at 34.4 tok/s and Coding GLM 4.6 at 31.1 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.
What inputs and capabilities does each model support?
Coding GLM 4.6 accepts text input and supports thinking, tool calling, function calling and structured outputs; GLM 4.6 accepts text input and supports thinking, tool calling, function calling and structured outputs.
Can I call Coding GLM 4.6 and GLM 4.6 with the same API key?
Yes. AIHubMix serves every model on this page behind one OpenAI-compatible endpoint, so switching between them is a one-line change to the model field — no second account, key or SDK.
Popular comparisons
Related model match-ups readers also look at.
