GLM-4.7
GLM-4.7 is served by 5 providers that kRouter can route to, with a 200K-token context window and pricing from $0.75 per 1M input tokens. Because more than one provider offers it, the price you pay depends on which one you route to — the same request, the same model, different bills.
Where to get GLM-4.7
| Provider | Route as |
|---|---|
| CodeBuddy CN | cbcn/glm-4.7 |
| GLM Coding (Z.ai) | glm/glm-4.7 |
| GLM (China) | glm-cn/glm-4.7 |
| Alibaba | alicode/glm-4.7 |
| Alibaba Intl | alicode-intl/glm-4.7 |
What GLM-4.7 is suited for
A 200K window comfortably holds a long file plus its surrounding context, which covers most day-to-day coding turns without compaction. It supports extended reasoning, which helps on debugging and multi-step planning but spends output tokens on thinking before the answer appears — worth knowing when you set max_tokens. Tool and function calling are supported, so it can drive an agent loop. Cached input is billed at $0.38 against $0.75 fresh, which is the difference that matters most for agent work — the same context is resent on every turn.
Specs
- Context window
- 200K
- Max output
- 48K
- Input / 1M
- $0.75
- Output / 1M
- $3.00
- Extended reasoning
- Tool / function calling
Cheaper alternatives to GLM-4.7
Comparable capabilities at a lower rate. With a kRouter combo you can send routine turns to one of these and reserve GLM-4.7 for the work that actually needs it.
- Gemini 3 Flash Preview$0.50 in · $3.00 out per 1M
- Gemini 3.1 Pro$0.50 in · $3.00 out per 1M
- Gemini 3.1 Flash Lite Preview$0.50 in · $3.00 out per 1M
- Gemini 3 Flash$0.50 in · $3.00 out per 1M
GLM-4.7 FAQ
How much does GLM-4.7 cost?
GLM-4.7 is $0.75 per 1M input tokens and $3.00 per 1M output tokens. Cached input is $0.38, which matters a lot for agent work that resends the same context each turn.
Which providers serve GLM-4.7?
5 providers: CodeBuddy CN, GLM Coding (Z.ai), GLM (China), Alibaba, Alibaba Intl. Through kRouter you can switch between them by changing the route prefix, without changing your tool.
What is GLM-4.7's context window?
200K tokens, with up to 48K tokens of output. kRouter publishes this on /v1/models as context_length, so clients read the real number instead of guessing from the model name.
Is there a cheaper alternative to GLM-4.7?
Yes — Gemini 3 Flash Preview ($0.50/1M in), Gemini 3.1 Pro ($0.50/1M in), Gemini 3.1 Flash Lite Preview ($0.50/1M in), Gemini 3 Flash ($0.50/1M in) are cheaper with comparable capabilities. A kRouter combo can send routine turns to one of those and keep GLM-4.7 for the work that needs it.
Route to GLM-4.7 from any tool
kRouter runs locally and gives Claude Code, Cursor, Codex and the rest one endpoint that reaches every provider above — with automatic failover. Free and MIT-licensed.
Install kRouter