Side by side

See the difference.

Scores, capabilities and costs for the models you’re considering.

Scroll to compare models →

Comparison of GLM-4.6, GLM-4.6V-FP8
2 modelszai-orgGLM-4.6Remove ×zai-orgGLM-4.6V-FP8Remove ×
What’s differentCompared with GLM-4.5, GLM-4.6 brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex agentic tasks.…Image input · Open weights
DateSep 29, 2025ListedDec 7, 2025Listed
Listed rate$0.40 in / $1.60 out/ 1M tokensDeepInfra · via OpenRouter · all routes ↗deepinfra/fp4/flex · tier=flex · quantization=fp4See provider quotes
Provider endpoints11 endpoints →1 endpoint →
Context window204.8K—
Max output131.1K—
Parameters——
Tool callingSupportedSupported
Structured outputSupportedNot reported
Image inputNot reportedSupported
ReasoningSupportedNot reported
Prompt cachingSupportedNot reported
Open weightsSupportedSupported

Add another model

Search all models →