Using GLM-4V 9B on Replicate API

Implementation guide · GLM-4 · Zhipu AI

ServerlessOpen Source

Replicate API exposes GLM-4V 9B through model ID cuuupid/glm-4v-9b. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-06-15. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at Replicate API and generate an API key.
  2. 2
    Use the Replicate API SDK or REST API to call cuuupid/glm-4v-9b — see the documentation for request format.
  3. 3
    You'll be billed $0.05/1M input, $0.25/1M output tokens. See full pricing.
API PortalDocumentationPricingModel Card

Code Examples

Install
pip install replicate
API key
REPLICATE_API_TOKEN
Model ID
cuuupid/glm-4v-9b

Replicate uses "owner/model-name" format (e.g. "meta/meta-llama-3-8b-instruct") for the latest version, or "owner/model-name:version-sha" to pin to a specific version. The REST endpoint splits owner and model-name into the path: /v1/models/{owner}/{model-name}/predictions.

import replicate

# reads REPLICATE_API_TOKEN from env
# cuuupid/glm-4v-9b format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
    "cuuupid/glm-4v-9b",
    input={"prompt": "Hello"}
)
# Output is a list or generator depending on the model
print("".join(output))

Pricing on Replicate API

TypePrice (per 1M)
Input tokens$0.05
Output tokens$0.25

Capabilities

Multimodal

About GLM-4V 9B

GLM-4V 9B is Tsinghua Knowledge Engineering Group (THUDM)'s GLM-4 model with multimodal text and image input. It offers a 128K-token context window and scores 48.3 on MMMU.

Full model details →

Model Specs

Released2024-06-05
Parameters9B
Context131k
ArchitectureDecoder Only

Provider

Replicate API

Replicate

San Francisco, California, United States