Dense multimodal reasoning for coding, visual analysis, and agents with 256K context
GLM 5.3 Flash TL3
Multimodal coding, visual reasoning, and long-horizon agents with 1M context
Pricing
Prices for this trust level. Prices are per 1M tokens.
| Trust Level | Region | Context | Max output | Input / 1M | Cache / 1M | Output / 1M | §203 |
|---|---|---|---|---|---|---|---|
| TL3 | FR | — | — | 0.125 € 0.138 $ | 0.025 € 0.028 $ | 0.40 € 0.44 $ | — |
USD prices are converted from EUR at the ECB reference rate of 1 EUR = 1.1014 USD (2026-11-16). EUR prices are authoritative.
Prices as of 16.11.2026.
About this model
GLM-5.3-Flash is Z.ai's first natively multimodal model in the GLM-5 series, designed for efficient coding, visual understanding, and long-horizon agents. Its 320B-parameter Mixture-of-Experts architecture activates 18B parameters per token and supports a 1M-token context window. Built from a newly trained base using a 30T-token multimodal corpus, it combines sparse and linear attention with Manifold-Constrained Hyper-Connections to reduce long-context compute costs. It accepts text and images and generates text for repository-level coding, document and chart analysis, UI understanding, function calling, and multi-step automation. Reasoning effort can be adjusted across low, high, and max settings. The weights are released under the MIT license.
API
glm5.3-flash-tl3
OpenAI compatibleAnthropic compatible
Base URL https://api.aki.io/v1
from openai import OpenAI
client = OpenAI(
api_key="YOUR_AKI_API_KEY",
base_url="https://api.aki.io/v1",
)
response = client.chat.completions.create(
model="glm5.3-flash-tl3",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
import OpenAI from "openai";
const client = new OpenAI({
apiKey: "YOUR_AKI_API_KEY",
baseURL: "https://api.aki.io/v1",
});
const response = await client.chat.completions.create({
model: "glm5.3-flash-tl3",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);
curl https://api.aki.io/v1/chat/completions \
-H "Authorization: Bearer $AKI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "glm5.3-flash-tl3",
"messages": [{"role": "user", "content": "Hello!"}]
}'