GLM-4.6
GLM-4.6Rankingin non-thinking mode?
Alternatives?
CheaperKimi K2 ThinkingthinkingOpen×2.1-15%$0.47 / $2
BetterGPT OSS 20BhighOpen×2-96%$0.011Context: 200K → 131K
OpenDeepSeek V3.2 Specialethinking×2.2——Context: 200K → 128K
CheaperNova 2.0 Litehigh×2.1-15%$0.30 / $2.50No strict JSONCheaperGPT OSS 120BhighOpen×2.1-94%$0.11Context: 200K → 131KKimi K2 ThinkingthinkingOpen×2.1-15%$0.47 / $2Nova 2.0 Litehigh×2.1-15%$0.30 / $2.50No strict JSONGPT OSS 120BhighOpen×2.1-94%$0.11Context: 200K → 131K
Nemotron 3 Nano 30B A3BthinkingOpen×2.1-90%$0.017Context: 200K → 131K
Qwen3 235B A22B Thinking 2507thinkingOpen×2.1-25%$0.08No strict JSONGPT OSS 20BhighOpen×2-96%$0.011Context: 200K → 131KNemotron 3 Nano 30B A3BthinkingOpen×2.1-90%$0.017Context: 200K → 131KGPT-5 Minihigh×2-31%$0.053Qwen3 30B A3B 2507 (Reasoning)thinkingOpen+27%—$0.066Qwen3 235B A22B Thinking 2507thinkingOpen×2.1-25%$0.08No strict JSONDeepSeek V3.2 SpecialethinkingOpen×2.2——Context: 200K → 128KGLM 4.7thinkingOpen×2.1same$0.60 / $2.20Kimi K2 ThinkingthinkingOpen×2.1-15%$0.47 / $2GPT OSS 120BhighOpen×2.1-94%$0.11Context: 200K → 131KNemotron 3 Nano 30B A3BthinkingOpen×2.1-90%$0.017Context: 200K → 131KGLM 4.7thinkingOpen×2.1—$0.60 / $2.20GLM 4.5 AirthinkingOpen+82%—$0.20 / $1.10Context: 200K → 131K+1GLM 4.5thinkingOpen+66%—$0.60 / $2.20Context: 200K → 131KGLM 4.6Vnon-thinkingOpen-41%—$0.30 / $0.90Context: 200K → 131KGLM 4.5Vnon-thinkingOpen-65%—$0.60 / $1.80Context: 200K → 66KGLM 5.3 FlashXOpenn/a—$0.37 / $1.25GLM 5.3 FlashmaxOpenn/a—$0.28Defaults to max · Self-hosted+4GLM 5.3lowOpenn/a—$0.85Reasoning cannot be disabled+3All Z.ai models →Run it yourself
History
10 versionsBenchmarks
all categoriesFAQ
How much does GLM-4.6 cost?›
$0.60 per 1M input tokens and $2.20 per 1M output tokens; cached input $0.11 per 1M; cheapest via DeepInfra at $0.40 / $1.60.
Is GLM-4.6 free to use?›
There is no free API; the cheapest paid price is $0.40 per 1M input tokens. The weights are open, so you can run it yourself.
How good is GLM-4.6, and what is it best at?›
#260 of 336 in Chat & Knowledge, #62 of 239 in Coding, #140 of 177 in Agents & Tool Use, #172 of 245 in Writing & Language.
Is GLM-4.6 better than Apriel v1.5 15B Thinker?›
On AIME 2025 · AA archived, GLM-4.6 scores 86 vs 87.5 — lower.
How can I use GLM-4.6?›
Through the API of DeepInfra, Featherless, Novita, Z.AI.
What is the context window of GLM-4.6?›
200K tokens.
When was GLM-4.6 released? Is there a newer version?›
Released 2025-09-30. It is the current version in its line.
Is GLM-4.6 open source?›
Yes, the weights are open.
Can I run GLM-4.6 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can GLM-4.6 read images?›
No, it accepts text only.
What is GLM-4.6?›
GLM-4.6 is an open-weights language model from Z.ai, released Sep 2025.
What are the best alternatives to GLM-4.6?›
Kimi K2 Thinking (cheaper), GPT OSS 20B (better), DeepSeek V3.2 Speciale (open weights).