GLM-5.3-Flash

Zhipu's first natively multimodal GLM-5 model (320B/18B MoE) with 1M context and visual coding capabilities.

Input price: $0.1168–$0.165
Output price: $0.4088–$0.55

Context: 1M
Max output: 131K

Capability: 154 (#44 of 79)
Human preference: 1471
30-day uptime: —

Released: 2026-08-26

InputTextImageVideoPDFOutputText

Providers

Providers that serve this model. With Auto, each request goes to the best available provider. Prices in USD per 1M tokens; stats cover the last 30 days.

AutoInput$0.1168–$0.165Output$0.4088–$0.55Cache read$0.03–$0.03694Context1MMax output131KWe send each request to the best-priced healthy provider. You pay that provider’s price.Tencent Cloud TokenHubCheapestInput$0.1168Output$0.4088Cache read$0.03358ChinaNo trainingZhipu AI (ChatGLM)Input$0.12848Output$0.44968Cache read$0.03694ChinaNo trainingFireworks AIInput$0.15Output$0.50Cache read$0.03Context1MMax output131KUnited StatesNo trainingNo retentionMistral AIInput$0.165Output$0.55Cache read$0.033FranceNo trainingNo retentionTogether AIInput$0.165Output$0.55Cache read$0.033Context1MUnited Statesfp4No trainingNo retention

Pricing

Prices vary by provider. Showing Tencent Cloud TokenHub, the lowest. Pick a provider above to see its prices.

Input: $0.1168; per 1M tokens
Output: $0.4088; per 1M tokens
Cache read: $0.03358; per 1M tokens

Try it

Runs on your balance and is billed like any API request.

curl https://api.ohmygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $OHMYGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zhipu/glm-5.3-flash",
    "messages": [
      {
        "role": "user",
        "content": "Hello"
      }
    ]
  }'

import os

from openai import OpenAI

client = OpenAI(
    api_key=os.environ["OHMYGPT_API_KEY"],
    base_url="https://api.ohmygpt.com/v1",
)

response = client.chat.completions.create(
    model="zhipu/glm-5.3-flash",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

import OpenAI from "openai";

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

const response = await client.chat.completions.create({
  model: "zhipu/glm-5.3-flash",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(response.choices[0].message.content);

The answer streams in here.

Billed by usage

Similar models

Other models with the same output types at a similar price.

Better value: more capable, lower price
Pareto frontier
This model
Similar models

Capability scores are from Epoch AI’s Epoch Capabilities Index (CC BY 4.0, as of 2026-11-10), which combines dozens of benchmarks with GPT-5 set at 150. epoch.ai/eci

Price: our current input price per 1M tokens in USD, lowest across channels. Dated snapshots and resold copies of the same model are merged into one point; free models are not shown.

Shaded area: capability above and price below the median of all models. Pareto frontier: no other model is both cheaper and more capable.

GLM-5.3-FlashThis model

Capability: 154
Input: $0.1168–$0.165
Output: $0.4088–$0.55

Doubao Seed 2.1 Lite (260915)

Capability: —
Input: $0.1168
Output: $0.3942

Qwen3.8 Omni Flash

Capability: —
Input: $0.113
Output: $0.382

DeepSeek V4 Flash 0731

Capability: 154
Input: $0.1104
Output: $0.22

Muse Ember

Capability: —
Input: $0.11
Output: $0.55

Human preference ratings are from the LMArena Text Arena (CC BY 4.0, as of 2026-11-09): Elo ratings from blind votes, on a different scale from capability scores. lmarena.ai/leaderboard/text