Z.ai

GLM 4.7 Flash

z-ai/glm-4.7-flash

JSON

Specification

Published by the vendor; the platform bills at the target's declared price.

GLM 4.7 Flash

reasoning open weights tools

Z.ai z-ai/glm-4.7-flash

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,...

Input $/1M: $0.06
Output $/1M: $0.40
Context: 203K
Max output: 16K
Released: Jan 19, 2026
Modalities: text

Cached input reads $0.01 per 1M · weights on Hugging Face as zai-org/GLM-4.7-Flash

On this deployment

No routing target resolves to this model yet. Declare one and the router picks it up without retraining.

Not routable here yet

Add a target with metadata.model set to this id.

targets.yamlyaml

# targets.yaml - declare a target that runs GLM 4.7 Flash
targets:
  - id: glm-4-7-flash
    kind: llm
    name: GLM 4.7 Flash
    metadata:
      model: z-ai/glm-4.7-flash          # links the target to this catalogue entry
    capabilities:
      domains: [general]
      supports_tools: true
      context_window: 202752
    cost:
      usd_per_1k_tokens: 0.000230

Price among Z.ai models

Input list price per million tokens; GLM 4.7 Flash is the cheapest of 13 listed.

1
GLM 4.7 Flash
$0.06
2
GLM Flash Latest
$0.07
3
GLM 5.3 Flash
$0.07
4
GLM 5.3 Flash (batch)
$0.15
5
GLM 4.6V
$0.30
6
GLM 4.7
$0.40
7
GLM 5
$0.60
8
GLM 5.2
$0.97
9
GLM 5.1
$0.97
10
GLM Latest
$1.17
11
GLM 5V Turbo
$1.20
12
GLM 5 Turbo
$1.20

More from Z.ai

Other models by the same vendor in the catalogue.