Model Library
Z AIReleased January 19, 2026GLM-4.7-Flash
Z AI · Released January 19, 2026
Intelligence score
23
At a glance
- Intelligence
- 23
- Speed
- 80.0tokens/sec
- Latency
- 1.22stime to first token
- Input price
- $0.07per 1M tokens
- Output price
- $0.40per 1M tokens
- Context window
- 200Ktokens
- Parameters
- 31.2billions
Summary
Comparison summary
GLM-4.7-Flash (Reasoning) scores 23 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 9). GLM-4.7-Flash (Reasoning) generates output at 80.0 tokens per second (based on the median across providers serving the model), which is below average compared to other open weight models of similar size (median: 101.0 t/s). GLM-4.7-Flash (Reasoning) costs $0.07 per 1M input tokens (very competitive, median: $0.18) and $0.40 per 1M output tokens (better than average, median: $0.40), based on the median across providers serving the model.
Specifications
Technical specifications
| Model name | GLM-4.7-Flash |
|---|---|
| Provider | Z AI |
| Release date | January 19, 2026 |
| Intelligence score | 23 |
| Speed | 80.0 tokens/sec |
| Latency (TTFT) | 1.22s |
| Input price | $0.07 / 1M tokens |
| Output price | $0.40 / 1M tokens |
| Context window | 200,000 tokens |
| Parameters | 31.2B |
| Reasoning | Yes |
| Input modalities | text |
| Output modalities | — |
| Open weights | Yes |
| License | MIT |
| API availability | — |
| Source | Model Intelligence legacy profile: glm-4-7-flash |
Pricing
Token prices
Price per 1M tokens
GLM-4.7-Flash, as listed in the catalog record
- Input$0.07
- Output$0.40
| Token type | Price per 1M |
|---|---|
| Input | $0.07 |
| Output | $0.40 |
Model Intelligence legacy profile: glm-4-7-flash
FAQ · 20
Frequently asked questions
GLM-4.7-Flash (Reasoning) was released on January 19, 2026.
GLM-4.7-Flash (Reasoning) was created by Z AI.
GLM-4.7-Flash (Reasoning) scores 23 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 9).
GLM-4.7-Flash (Reasoning) generates output at 80.0 tokens per second (based on the median across providers serving the model), which is below average compared to other open weight models of similar size (median: 101.0 t/s).
GLM-4.7-Flash (Reasoning) has a time to first token (TTFT) of 1.22s (based on the median across providers serving the model), which is better than average compared to other open weight models of similar size (median: 2.09s).
GLM-4.7-Flash (Reasoning) costs $0.07 per 1M input tokens (very competitive, median: $0.18) and $0.40 per 1M output tokens (better than average, median: $0.40), based on the median across providers serving the model.
GLM-4.7-Flash (Reasoning) costs $0.07 per 1M input tokens and $0.40 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 $0.10 per 1M tokens. Pricing may vary by provider.
Yes, GLM-4.7-Flash (Reasoning) is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
GLM-4.7-Flash (Reasoning) supports text input.
GLM-4.7-Flash (Reasoning) supports text output.
No, GLM-4.7-Flash (Reasoning) does not support image input. It can only process text.
No, GLM-4.7-Flash (Reasoning) is not multimodal. It only supports text input.
GLM-4.7-Flash (Reasoning) has a context window of 200k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, GLM-4.7-Flash (Reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
GLM-4.7-Flash (Reasoning) has 31.2 billion parameters (3 billion active).
GLM-4.7-Flash (Reasoning) is a Mixture of Experts (MoE) model with 31.2 billion total parameters, but only 3 billion active parameters are used during inference.
GLM-4.7-Flash (Reasoning) is released under the MIT license. This license allows commercial use.
GLM-4.7-Flash (Reasoning) achieves a score of 23 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, GLM-4.7-Flash (Reasoning) is available via API through 3 providers.
GLM-4.7-Flash (Reasoning) is available through 3 API providers.