zaiCertifiedReleased 08/11/2025

GLM 4.5V

Built on the GLM-4.5-Air base model, GLM-4.5V inherits proven techniques from GLM-4.1V-Thinking while achieving effective scaling through a powerful 106B-parameter MoE architecture.

View API reference ↓
Input / output priceFrom$0.60 / $1.80per 1M
24h uptime99.98%
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferencebureau.com/v1",
  apiKey: process.env.IB_API_KEY,
});

const res = await client.chat.completions.create({
  model: "zai/glm-4.5v",
  messages: [{ role: "user", content: "Why is the sky blue?" }],
});

console.log(res.choices[0].message.content);

Providers

Dispatch routes requests across these providers and fails over between them without changing the model. Restrict or order providers with team Directives. Prices are gateway list prices before the platform fee.

ProviderContextMax outputLatencyThroughputInputOutputCacheCapabilitiesZDRNo trainingRegionsStatus
novita66K16K1.2 s56 tps$0.60$1.80Read $0.11Write —6 featuresNoNoGlobalCertified
zai66K16K0.8 s43 tps$0.60$1.80Read $0.11Write —6 featuresNoNoGlobalCertified

Uptime

24 hours

Request success rate per provider.

novita100.00%
zai99.97%

Throughput

last hour

P50 output tokens per second.

novita56 tps
zai43 tps

Latency

last hour

P50 time to first token.

zai0.8 s
novita1.2 s

Getting started

Create a key on the API Keys page and set it as IB_API_KEY. See the quickstart.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferencebureau.com/v1",
  apiKey: process.env.IB_API_KEY,
});

const res = await client.chat.completions.create({
  model: "zai/glm-4.5v",
  messages: [{ role: "user", content: "Why is the sky blue?" }],
});

console.log(res.choices[0].message.content);

Top-level parameters

Standard Chat Completions parameters work as documented. These have model-specific behavior.

ParameterTypeRequiredDescription
modelstringYesModel ID in the form creator/model, e.g. zai/glm-4.5v. Must be allowed by your team's Directives.
max_tokensnumberNoHard cap on generated tokens, and the basis for the balance reserved per request. GLM 4.5V supports up to 16,000 output tokens.
reasoning{ effort: 'low' | 'medium' | 'high' }NoReasoning effort, mapped to the provider's native configuration. Reasoning tokens count toward output usage.
toolsTool[]NoFunction definitions the model can call. Tool calls are returned in choices[].message.tool_calls.
Supportedmax_tokenstemperaturestoptoolstool_choicereasoninginclude_reasoningresponse_formatstructured_outputs

Input limits

InputSourcesLimits
Text—Prompt and response share the 66K-token context window
ImageURL, base64Sent as image_url content parts; counts as input tokens

More models by zai

ModelContextInputOutputCacheRelease
zai/glm-5.3-flashx-legal1M$0.37$1.25Read $0.075Write —11/02/2026
zai/glm-5.3-flashx1M$0.37$1.25Read $0.075Write —09/18/2026
zai/glm-5.3-fast1.05M$2.10$6.60Read $0.21Write —09/02/2026
zai/glm-5.3-flash1M$0.15$0.50Read $0.030Write —08/26/2026
zai/glm-5.31M$1.40$4.40Read $0.14Write —08/18/2026
zai/glm-5.2-fast1M$2.80$8.80Read $0.56Write —06/23/2026
zai/glm-5.21M$1.40$4.40Read $0.14Write —06/16/2026
zai/glm-5.1203K$1.40$4.40Read $0.26Write —04/07/2026
zai/glm-5v-turbo200K$1.20$4.00Read $0.24Write —04/01/2026
zai/glm-5-turbo203K$1.20$4.00Read $0.24Write —03/15/2026