GLM-4V 9B on Replicate API

GLM-4 · Zhipu AI

ServerlessOpen Source

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

Why use GLM-4V 9B on Replicate API?

Replicate API offers GLM-4V 9B with pay-as-you-go pricing at $0.05/1M input tokens. Replicate is a cloud-based platform that enables users to run machine learning models easily and efficiently.

Input / 1M
$0.050
Output / 1M
$0.25
Cache
Not sourced
Batch
Not sourced

Setup recipe

Python + curl
Install
pip install replicate
Auth
export REPLICATE_API_TOKEN=...
Call
import replicate
output = replicate.run(
    "cuuupid/glm-4v-9b",
    input={"prompt": "Hello"}
Model ID
cuuupid/glm-4v-9b

Request example

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))

Gotchas

  • Use provider model ID "cuuupid/glm-4v-9b", not the LLMReference slug "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.
  • The examples expect REPLICATE_API_TOKEN; rename it only if your application config maps the new variable.

Pricing

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.

Get Started

Model CardDocsPortalPlaygroundPricing

Model Specs

Released2024-06-05
Parameters9B
Context131k
ArchitectureDecoder Only

Provider

Replicate API

Replicate

All models on Replicate API →Provider setup guide →