Back to all models

GLM-4.7

Latest GLM with enhanced reasoning capabilities.

glm-4.7
STABLEGet StartedView uptime
204,800 context
Released December 22, 2025
Starting at $0.38/M input tokens
Starting at $1.98/M output tokens
Streaming
Tools
Reasoning
JSON Output
Web Search
No ratings yetSign in to rate

Select Provider

All Providers for GLM-4.7

DigitSpace routes requests to the best providers that are able to handle your prompt size and parameters.

Z AI
Context: 200k
Input
$0.6
/M tokens
Cache Read
$0.11
/M tokens
Output
$2.2
/M tokens
+ $0.010 per search
Get Started
NovitaAI
Context: 204.8kQuant: fp8
Input
$0.6
/M tokens
Cache Read
$0.11
/M tokens
Output
$2.2
/M tokens
Get Started
Cerebras
Context: 200k
Input
$2.25
/M tokens
Cache Read
—
/M tokens
Output
$2.75
/M tokens
Get Started
ByteDance
Context: 200k
Input
$0.6
/M tokens
Cache Read
$0.11
/M tokens
Output
$2.2
/M tokens
Get Started
Together AI
Context: 202.8k
Input
$0.45
/M tokens
Cache Read
—
/M tokens
Output
$2
/M tokens
Get Started
EmberCloud
Context: 200k
Input
$0.38
/M tokens
Cache Read
$0.19
/M tokens
Output
$1.98
/M tokens
Get Started
Vertex AI (OpenAI-compatible)
Context: 202.8k
Deactivating on Oct 21, 2026
Input
$0.6
/M tokens
Cache Read
—
/M tokens
Output
$2.2
/M tokens
Get Started

Frequently asked questions

What is GLM-4.7?

Latest GLM with enhanced reasoning capabilities. You can access it through DigitSpace's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.

How much does GLM-4.7 cost?

Pricing for GLM-4.7 on DigitSpace starts at $0.38 per million input tokens and $1.98 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.

What is the context length of GLM-4.7?

GLM-4.7 supports a context window of up to 204,800 tokens on its largest provider deployment.

Which providers serve GLM-4.7?

GLM-4.7 is served by Z AI, NovitaAI, Cerebras, ByteDance, Together AI, EmberCloud, Vertex AI (OpenAI-compatible) through DigitSpace. Requests are automatically routed to the best available provider, with fallback when a provider has issues.

Does GLM-4.7 support tool calling and structured outputs?

GLM-4.7 supports tool (function) calling and soft JSON output, but NOT strict JSON output schema (its upstream provider does not enforce it).

When was GLM-4.7 released?

GLM-4.7 was released on December 22, 2025.

More Z AI models

Browse all models

GLM-5.3 Flash

128,000 context$0.09 in / $0.32 out per 1M

GLM-5.3

128,000 context$0.92 in / $3.22 out per 1M

GLM-5.2

128,000 context$0.67 in / $2.35 out per 1M

GLM-5.1

128,000 context$0.92 in / $2.96 out per 1M

GLM-5 Turbo

128,000 context$1.14 in / $3.80 out per 1M