GLM 4.6V
GLM 4.6VAlternatives?
CheaperMiniMax M3.1 Flashthinking×13.1-42%$0.22Complete model response must be appended
BetterGPT-6 Lunalow×5.5-56%$0.005Function calling only with none · Chat Completions+3
OpenQwen3.8 Flashthinking×10.4-49%$0.37Memory (4-bit): 65 GB → 108 GB+6
CheaperClaude Haiku 5.5max×12.1-56%$0.21Remove sampling parameters+5CheaperGLM 5.3 FlashmaxOpen×10.9-47%$0.28Memory (4-bit): 65 GB → 193 GB+5MiniMax M3.1 Flashthinking×13.1-42%$0.22Complete model response must be appendedClaude Haiku 5.5max×12.1-56%$0.21Remove sampling parameters+5GLM 5.3 FlashmaxOpen×10.9-47%$0.28Memory (4-bit): 65 GB → 193 GB+5GPT-6 Lunamax×10.5-56%$0.068Function calling only with none · Chat Completions+3Qwen3.8 FlashthinkingOpen×10.4-49%$0.37Memory (4-bit): 65 GB → 108 GB+6GPT-6 Lunalow×5.5-56%$0.005Function calling only with none · Chat Completions+3
Granite 4.2 3BthinkingOpen+81%-88%$0.006Context: 131K → 128K+1GPT-5.6 Lunalow×5.4same$0.01GPT OSS 20BhighOpen×3-92%$0.011No image input
Mistral Small 4thinkingOpen×2.7-42%$0.015Memory (4-bit): 65 GB → 72 GBQwen3.8 FlashthinkingOpen×10.4-49%$0.37Memory (4-bit): 65 GB → 108 GB+6Qwen3.8 27BxhighOpen×9.3+113%$1.01max_tokens range · QwenCloud+4TInkling SmallthinkingOpen×9.1+42%$0.089Memory (4-bit): 65 GB → 160 GB+1
Nemotron 3.5 Super VLOpen×8.4-61%$0.19Memory (4-bit): 65 GB → 75 GBMiniMax M2.7thinkingOpen×8.1+17%$0.30 / $1.20Memory (4-bit): 65 GB → 137 GB+1GLM 5.3 FlashmaxOpen×10.9—$0.28Memory (4-bit): 65 GB → 193 GB+5GLM 5.3lowOpen×10—$0.85Memory (4-bit): 65 GB → 452 GB+5GLM 5.1thinkingOpen×8.2—$1.02Memory (4-bit): 65 GB → 452 GB+1GLM 5thinkingOpen×8—$1 / $3.20Memory (4-bit): 65 GB → 452 GB+1GLM 5 Turbothinking×7.6—$1.20 / $4No image inputGLM 4.7thinkingOpen×7.5—$0.60 / $2.20Memory (4-bit): 65 GB → 215 GB+1GLM 5V Turbothinking×4.7—$1.20 / $4GLM 4.5thinkingOpen×3.5—$0.60 / $2.20Memory (4-bit): 65 GB → 215 GB+1All Z.ai models →Run it yourself
estimateHistory
10 versionsBenchmarks
in Chat & KnowledgeFAQ
How much does GLM 4.6V cost?›
$0.30 per 1M input tokens and $0.90 per 1M output tokens; cached input $0.05 per 1M.
Is GLM 4.6V free to use?›
There is no free API; the cheapest paid price is $0.30 per 1M input tokens. The weights are open, so you can run it yourself.
How good is GLM 4.6V, and what is it best at?›
#319 of 334 in Chat & Knowledge, #176 of 239 in Coding, #147 of 242 in Agents & Tool Use, #101 of 195 in Writing & Language, #117 of 124 in Vision & Documents.
Is GLM 4.6V better than GLM 4.5V?›
On Humanity's Last Exam, GLM 4.6V scores 9.6 vs 6.3 — higher.
How can I use GLM 4.6V?›
Through the API of DeepInfra, Novita.
What is the context window of GLM 4.6V?›
131K tokens, with up to 33K output tokens.
When was GLM 4.6V released? Is there a newer version?›
Released 2025-12-08. It has been superseded by GLM 5V Turbo.
Is GLM 4.6V open source?›
Yes, the weights are open (MIT licence).
Can I run GLM 4.6V locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can GLM 4.6V read images?›
It accepts text and images, video as input.
What is GLM 4.6V?›
GLM 4.6V is an open-weights language model from Z.ai, released Dec 2025, the successor to GLM 4.5V.
What are the best alternatives to GLM 4.6V?›
MiniMax M3.1 Flash (cheaper), GPT-6 Luna (better), Qwen3.8 Flash (open weights).