Question 1

What is GLM 4.7?

Accepted Answer

GLM 4.7 is a model from Z.ai, released on Dec 22, 2025. GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while delivering more natural conversational experiences and superior front-end aesthetics.

Question 2

How much does GLM 4.7 cost?

Accepted Answer

On the Respan gateway, input starts at $0.40 per 1M tokens on DeepInfra, and output starts at $1.75 per 1M tokens on DeepInfra, after gateway discounts. Averaged across 10 providers, it costs $0.58 per 1M input tokens and $2.10 per 1M output tokens.

Question 3

Which providers serve GLM 4.7 on Respan?

Accepted Answer

10 providers serve GLM 4.7: DeepInfra, TogetherAI, Novita, Featherless, OpenRouter, Tera, and 3 more. TogetherAI, Tera, and Google Vertex AI require your own provider API key (BYOK).

Question 4

What is GLM 4.7's context window?

Accepted Answer

GLM 4.7 accepts up to 205K tokens of context on its largest provider route.

Question 5

How do I use GLM 4.7 with the Respan gateway?

Accepted Answer

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "zai/glm-4.7". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is GLM 4.7?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was Z.ai at 130 tokens per second, and the lowest response latency was 6.1 seconds on Z.ai. Speed varies with request size and provider.

Question 7

Where does GLM 4.7 rank on the Respan Index?

Accepted Answer

GLM 4.7 scores 25.9 out of 100 on the Respan Index v1.1, ranking #76 of 138 models. By category: Coding 6.3 (estimated), Agents 41.4, Reasoning 12.5, Knowledge & language 32.1, and Human preference 51.0. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by llmmetric.com.

Question 8

How does GLM 4.7 score on benchmarks?

Accepted Answer

GLM 4.7 has 9 published benchmark scores, including Vending-Bench 2 2376.82, GPQA Diamond 83.3%, and OTIS Mock AIME 2024-2025 83.3%. Each score links to where it was published; the data is collected by llmmetric.com.

Provider	Context	Input	Output
DeepInfra`deepinfra/zai-org/GLM-4.7`	203K	$0.40/M	$1.75/M
TogetherAIBYOK only`together_ai/zai-org/GLM-4.7`	203K	$0.45/M	$2.00/M
NovitaSave 10%`novita/zai-org/glm-4.7`	205K	$0.54/M	$1.98/M
NovitaSave 10%`novita/zai-org/glm-4.7-h`	205K	$0.54/M	$1.98/M
Featherless`featherless_ai/zai-org/GLM-4.7`	203K	$0.55/M	$2.20/M
OpenRouter`openrouter/z-ai/glm-4.7`	205K	$0.60/M	$2.20/M
TeraBYOK only`tera/zai-org/GLM-4.7`	200K	$0.60/M	$2.20/M
Google Vertex AIBYOK only`vertex_ai/zai-org/glm-4.7-maas`	205K	$0.60/M	$2.20/M
Z.ai`zai/glm-4.7`	200K	$0.60/M	$2.20/M
IO.net`ionet/zai-org/GLM-4.7`	203K	$0.87/M	$2.33/M

GLM 4.7

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Time to first token

Response latency

Benchmarks

Respan Indexv1.1

Agents1

Reasoning3

Apps

GLM 4.7 FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.

Math1

Knowledge2

Arena2