GLM 4.7 Flash
Fast and lightToolsZ.ai · Released January 2026
As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,...
It is part of Z.ai's GLM series, an open-weight line where the 5.x generation leads, Turbo servings cut latency and cost, and 5V adds vision.
Facts and pricing
- Provider
- Z.ai
- Context window
- 203K tokens
- Input price
- 0.66 credits / 1M tokens ($0.060 raw)
- Output price
- 4.4 credits / 1M tokens ($0.40 raw)
- Vision (image input)
- No
- Tool calling
- Yes
- Extended reasoning
- No
Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.10x margin. Raw prices shown per 1M tokens.
Try GLM 4.7 Flash now
What GLM 4.7 Flash is best for
- High-volume everyday tasks where speed and cost matter: summaries, drafts, quick questions
- Long documents: the 203K-token window holds lengthy reports, contracts or papers whole
- Tool use and agents: reliably calls functions, so it can search, run skills and drive workflows
Example prompts
Prompts that suit a fast and light model like GLM 4.7 Flash:
- Summarize this article in five bullet points
- Rewrite this email to be shorter and friendlier
- Give me ten name ideas for a hiking newsletter
- Translate this paragraph to Spanish and keep the tone
Z.ai family
| Model | Context | Input cr/M | Output cr/M | Released |
|---|---|---|---|---|
| GLM 5.2 | 1.0M | 5.9 | 19.4 | June 2026 |
| GLM 5.1 | 203K | 10.6 | 33.4 | April 2026 |
| GLM 5V Turbo | 203K | 13.2 | 44.0 | April 2026 |
| GLM 5 Turbo | 262K | 13.2 | 44.0 | March 2026 |
| GLM 5 | 203K | 6.6 | 21.1 | February 2026 |
| GLM 4.7 Flash | 203K | 0.66 | 4.4 | January 2026 |
| GLM 4.7 | 203K | 4.4 | 19.3 | December 2025 |
| GLM 4.6V | 131K | 3.3 | 9.9 | December 2025 |
| GLM 4.6 | 203K | 4.7 | 19.1 | September 2025 |
| GLM 4.5V | 66K | 6.6 | 19.8 | August 2025 |
Frequently asked questions
- What is GLM 4.7 Flash?
- GLM 4.7 Flash is an AI model by Z.ai. As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,...
- How much does GLM 4.7 Flash cost on Zeplik?
- Input tokens cost 0.66 credits per million and output tokens 4.4 credits per million (1 credit = $0.10; the raw provider rates are $0.060 and $0.40 per million). New accounts start with free credits.
- How long can a conversation with GLM 4.7 Flash be?
- GLM 4.7 Flash has a 203K-token context window (202,752 tokens), which covers the conversation plus any documents you attach.
- Does GLM 4.7 Flash support images and tools?
- GLM 4.7 Flash is text-only and supports tool calling.
Related models
GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...
GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on...
GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding,...
GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows...
GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...
GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...