Z.ai: GLM 4.7 Flash

z-ai/glm-4.7-flash

Tool useJSONReasoningStreaming

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,...

Pricing

Input

$0.06 / 1M

Output

$0.4 / 1M

Specs

Context

202,752 tokens

Input

text

Output

text

Released: 2026-01

Supported parameters

frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p

Open weights · HuggingFace

1,038,287 downloads/mo

1,737 likes

mit text-generation

arXiv:2508.06471

View on HuggingFace →

Use this model →