Model Library
Z AIReleased December 8, 2025GLM-4.6V
Z AI · Released December 8, 2025
Intelligence score
11
At a glance
- Intelligence
- 11
- Speed
- 78.0tokens/sec
- Latency
- 3.89stime to first token
- Input price
- $0.30per 1M tokens
- Output price
- $0.90per 1M tokens
- Context window
- 130Ktokens
- Parameters
- 108billions
Summary
Comparison summary
GLM-4.6V (Non-reasoning) scores 11 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other open weight non-reasoning models of similar size (median: 7). GLM-4.6V (Non-reasoning) generates output at 78.0 tokens per second (based on the median across providers serving the model), which is below average compared to other open weight non-reasoning models of similar size (median: 85.6 t/s). GLM-4.6V (Non-reasoning) costs $0.30 per 1M input tokens (better than average, median: $0.53) and $0.90 per 1M output tokens (better than average, median: $1.05), based on the median across providers serving the model.
Specifications
Technical specifications
| Model name | GLM-4.6V |
|---|---|
| Provider | Z AI |
| Release date | December 8, 2025 |
| Intelligence score | 11 |
| Speed | 78.0 tokens/sec |
| Latency (TTFT) | 3.89s |
| Input price | $0.30 / 1M tokens |
| Output price | $0.90 / 1M tokens |
| Context window | 130,000 tokens |
| Parameters | 108B |
| Reasoning | No |
| Input modalities | text, image |
| Output modalities | — |
| Open weights | Yes |
| License | MIT |
| API availability | — |
| Source | Model Intelligence legacy profile: glm-4-6v |
Pricing
Token prices
Price per 1M tokens
GLM-4.6V, as listed in the catalog record
- Input$0.30
- Output$0.90
| Token type | Price per 1M |
|---|---|
| Input | $0.30 |
| Output | $0.90 |
Model Intelligence legacy profile: glm-4-6v
FAQ · 20
Frequently asked questions
GLM-4.6V (Non-reasoning) was released on December 8, 2025.
GLM-4.6V (Non-reasoning) was created by Z AI.
GLM-4.6V (Non-reasoning) scores 11 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other open weight non-reasoning models of similar size (median: 7).
GLM-4.6V (Non-reasoning) generates output at 78.0 tokens per second (based on the median across providers serving the model), which is below average compared to other open weight non-reasoning models of similar size (median: 85.6 t/s).
GLM-4.6V (Non-reasoning) has a time to first token (TTFT) of 3.89s (based on the median across providers serving the model), which is at the higher end compared to other open weight non-reasoning models of similar size (median: 1.59s).
GLM-4.6V (Non-reasoning) costs $0.30 per 1M input tokens (better than average, median: $0.53) and $0.90 per 1M output tokens (better than average, median: $1.05), based on the median across providers serving the model.
GLM-4.6V (Non-reasoning) costs $0.30 per 1M input tokens and $0.90 per 1M output tokens (based on the median across providers serving the model). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.36 per 1M tokens. Pricing may vary by provider.
No, GLM-4.6V (Non-reasoning) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
GLM-4.6V (Non-reasoning) supports text and image input.
GLM-4.6V (Non-reasoning) supports text output.
Yes, GLM-4.6V (Non-reasoning) supports image input and can analyze, describe, and answer questions about images.
Yes, GLM-4.6V (Non-reasoning) is multimodal. It can process text and image input and generate text output.
GLM-4.6V (Non-reasoning) has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, GLM-4.6V (Non-reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
GLM-4.6V (Non-reasoning) has 108 billion parameters (12 billion active).
GLM-4.6V (Non-reasoning) is a Mixture of Experts (MoE) model with 108 billion total parameters, but only 12 billion active parameters are used during inference.
GLM-4.6V (Non-reasoning) is released under the MIT license. This license allows commercial use.
GLM-4.6V (Non-reasoning) achieves a score of 11 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, GLM-4.6V (Non-reasoning) is available via API through 2 providers.
GLM-4.6V (Non-reasoning) is available through 2 API providers.