GLM 4.7 Flash

Jan 2026
GLM 4.7 Flash
Compare in
on
—per task?
$0.061 / $0.40per 1M in / out?
75 tok/sfirst token in 1.2 s?
200Kcontext

Rankingin thinking mode?

Run it yourself

estimate
Fits on✗ 8 GB (phone, laptop)✗ 16 GB✓ 24 GB GPU · compressed✓ 48 GB GPU · 8-bit✓ 80 GB GPU · full quality
LicenceMITfree for commercial use

FAQ

How much does GLM 4.7 Flash cost?›

$0.061 per 1M input tokens and $0.40 per 1M output tokens (cheapest host: OpenRouter).

Is GLM 4.7 Flash free to use?›

Yes, there is a free API option.

How good is GLM 4.7 Flash, and what is it best at?›

#212 of 334 in Chat & Knowledge, #86 of 239 in Coding, #3 of 242 in Agents & Tool Use, #128 of 195 in Writing & Language. Strongest at: Tool calling.

Is GLM 4.7 Flash better than GLM 4.5 Air?›

On τ²-bench · AA, GLM 4.7 Flash scores 98.8 vs 46.5 — higher.

How can I use GLM 4.7 Flash?›

Through the API of AWS Bedrock, Cloudflare, DeepInfra, Novita, Venice.

What is the context window of GLM 4.7 Flash?›

200K tokens, with up to 131K output tokens.

When was GLM 4.7 Flash released? Is there a newer version?›

Released 2026-01-19. It has been superseded by GLM 5.

Is GLM 4.7 Flash open source?›

Yes, the weights are open (MIT licence).

Can I run GLM 4.7 Flash locally?›

The weights are open and can be self-hosted; hardware needs are not confirmed yet.

Can GLM 4.7 Flash read images?›

No, it accepts text only.

What is GLM 4.7 Flash?›

GLM 4.7 Flash is an open-weights language model from Z.ai, released Jan 2026, the successor to GLM 4.5 Air.

What are the best alternatives to GLM 4.7 Flash?›

Qwen3.5 4B (cheaper), Qwen3.6 35B A3B (open weights).