GLM 4.6V
GLM 4.6VRankingin thinking mode?
Alternatives?
CheaperGPT OSS 120BhighOpen+10%-87%$0.11Memory (4-bit): 65 GB → 70 GB+1BetterGPT OSS 20BhighOpen+5%-92%$0.011No image input
CheaperNemotron 3 Nano 30B A3BthinkingOpen+7%-77%$0.017No image input
CheaperDeepSeek V3.1thinkingOpen+5%-6%$0.25 / $0.95Context: 131K → 128K+2
CheaperSeed OSS 36B InstructthinkingOpensame-33%$0.21 / $0.57No image inputGPT OSS 120BhighOpen+10%-87%$0.11Memory (4-bit): 65 GB → 70 GB+1Nemotron 3 Nano 30B A3BthinkingOpen+7%-77%$0.017No image inputDeepSeek V3.1thinkingOpen+5%-6%$0.25 / $0.95Context: 131K → 128K+2GPT OSS 20BhighOpen+5%-92%$0.011No image inputSeed OSS 36B InstructthinkingOpensame-33%$0.21 / $0.57No image inputGPT OSS 20BhighOpen+5%-92%$0.011No image inputNemotron 3 Nano 30B A3BthinkingOpen+7%-77%$0.017No image inputGPT-5 Minihigh+6%+53%$0.053
Qwen3 235B A22B Thinking 2507thinkingOpen+7%+66%$0.08Memory (4-bit): 65 GB → 141 GB+2GPT OSS 120BhighOpen+10%-87%$0.11Memory (4-bit): 65 GB → 70 GB+1GPT OSS 120BhighOpen+10%-87%$0.11Memory (4-bit): 65 GB → 70 GB+1Nemotron 3 Nano 30B A3BthinkingOpen+7%-77%$0.017No image inputQwen3 235B A22B Thinking 2507thinkingOpen+7%+66%$0.08Memory (4-bit): 65 GB → 141 GB+2
K EXAONEthinkingOpen+6%——Memory (4-bit): 65 GB → 142 GB+1GPT OSS 20BhighOpen+5%-92%$0.011No image inputGLM 4.7thinkingOpen+11%—$0.60 / $2.20Memory (4-bit): 65 GB → 215 GB+1GLM 4.5 AirthinkingOpen-5%—$0.20 / $1.10Memory (4-bit): 65 GB → 66 GB+2GLM 4.5thinkingOpen-14%—$0.60 / $2.20Memory (4-bit): 65 GB → 215 GB+1GLM-4.6non-thinkingOpen-48%—$0.60 / $2.20Memory (4-bit): not verified+1GLM 4.5Vnon-thinkingOpen-82%—$0.60 / $1.80Context: 131K → 66KGLM 5.3 FlashXOpenn/a—$0.37 / $1.25Memory (4-bit): not verifiedGLM 5.3 FlashmaxOpenn/a—$0.28Memory (4-bit): 65 GB → 193 GB+5GLM 5.3lowOpenn/a—$0.85Memory (4-bit): 65 GB → 452 GB+5All Z.ai models →Run it yourself
estimateHistory
10 versionsBenchmarks
all categoriesFAQ
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?›
#199 of 336 in Chat & Knowledge, #111 of 239 in Coding, #144 of 242 in Agents & Tool Use, #96 of 197 in Writing & Language, #113 of 125 in Vision & Documents.
Is GLM 4.6V better than GLM 4.5V?›
On AIME 2025 · AA archived, GLM 4.6V scores 85.3 vs 73 — 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?›
GPT OSS 120B (cheaper), GPT OSS 20B (better).