Megatron MarketsWholesale
Sign inContact Us
Models Model details

Z.ai

Z.ai: GLM 4.7 Flash

z-ai/glm-4.7-flash

Enquire about this model Request a quote

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, and tool collaboration, and has achieved leading performance among open-source models of the same size on several current public benchmark leaderboards.

Input
$0.0605

/ 1M tokens

Output
$0.4

/ 1M tokens

Context window
200K

tokens

Limits

Context

200,000

tokens

Max output

117,964

59% of the context window

Parameters

31,221,488,576

Model facts

Author

Z.ai

Tokenizer

Other

Modality

Text -> Text

License

MIT

Created

Jan 19, 2026

Hugging Face

zai-org/GLM-4.7-Flash

Default generation parameters

temperature

1

top_p

0.95

Publication status

Hugging Face: verifiedLicense: publishedParameter count: published

Modalities

Input · TextOutput · Text

Generation controls

Frequency penaltyInclude reasoningLogit biasLogprobsMax tokensMin pPresence penaltyReasoningRepetition penaltyResponse formatSeedStopStructured outputsTemperatureTool choiceToolsTop kTop logprobsTop p

Capability scores

14.9
Intelligence index

Better than 38% of models compared

Creative tasks

Category performance

UI components
Top 49%

1207 Elo

57.6% win

Websites
Top 51%

1196 Elo

54.0% win

Code
Top 55%

1179 Elo

53.1% win

3D
Top 65%

1121 Elo

51.2% win

Games
Top 65%

1136 Elo

49.7% win

Data visualization
Top 79%

1123 Elo

45.3% win

SVG
Top 87%

1037 Elo

44.2% win