BroadRouter
Get started

GLM 5.3 API

Updated

GLM 5.3 runs on BroadNet Inference as broadnet/glm-5.3 through the OpenAI-compatible https://inference.broadnet.ai/v1. It costs $0.78 input, $0.173 cached input and $3.46 output per 1M tokens, with a 1,048,576-token context. It needs a qualifying top-up (not the starting credit), and inference content is not retained.

At a glance

  • Text
  • Tool calling
  • Reasoning
  • Structured output
  • 1,048,576-token context
  • Tool calling and structured output
  • Reasoning model
  • Text input
Price and limits
Model IDbroadnet/glm-5.3
Endpoint/v1/chat/completions
Supported inputstext
Context1,048,576 tokens, prompt and answer together
Input$0.78 per 1M tokens
Cached input$0.173 per 1M tokens (reported cache hits only)
Output$3.46 per 1M tokens
Pay-as-you-go limits30 requests a minute, 4 in flight per key
AccessTop-up required: opens after a qualifying top-up; the starting credit does not cover it

Prices on this page are from BroadNet's price feed snapshot dated , not checked live here. See official pricing for current rates.

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

Published benchmark results

BroadNet did not run these benchmarks; results are as published by the Z.ai model card and Epoch AI and may use different settings. BroadRouter is BroadNet's site. They refer to the published model zai-org/GLM-5.3; not measured on BroadNet's serving.

Published benchmark results for GLM 5.3, with sources
BenchmarkResultSetting or noteSource
Terminal Bench 2.188.2Default reasoning_effort max, per the card; Claude Code harnessZ.ai model card, checked 2026-11-16
DeepSWE (v1.1)66.9Default reasoning_effort max, per the card; mini-swe-agent harnessZ.ai model card, checked 2026-11-16
HLE w/ Tools62.5Default reasoning_effort max, per the cardZ.ai model card, checked 2026-11-16
Toolathlon Verified73.0Pass@1 averaged over 3 runsZ.ai model card, checked 2026-11-16
CyberGym84.5Max reasoning effort, Claude Code harnessZ.ai model card, checked 2026-11-16
GPQA Diamond0.909Max reasoning setting; Epoch run glm-5.3_max, mean score on a 0 to 1 scaleEpoch AI, checked 2026-11-16
SimpleQA Verified0.41Max reasoning setting; Epoch run glm-5.3_max, mean score on a 0 to 1 scaleEpoch AI, checked 2026-11-16
OTIS Mock AIME 2024-20250.911Max reasoning setting; Epoch run glm-5.3_max, mean score on a 0 to 1 scaleEpoch AI, checked 2026-11-16

Epoch AI rows: Epoch AI, Capabilities & benchmarking, licensed CC BY 4.0, shown as the mean score on a 0 to 1 scale, rounded to three decimals (hover a value for the exact figure in Epoch's data file).

Side by side: GLM 5.3 vs DeepSeek V4.1 Flash, GLM 5.3 vs Qwen3.8 27B and GLM 5.3 vs BroadNet Gemma 4 VL 26B, with prices, context and workload costs. GLM 5.3 is also sold by 24 other providers, from $0.5625 input and $2.50 output per 1M tokens on their own pricing pages: GLM 5.3 API pricing by provider. The same text is a different number of tokens on each model: see how GLM 5.3's tokenizer compares on Arabic, English and code in the tokenizer efficiency dataset.

Call it in Python

Install the OpenAI SDK with pip install openai, export BROADNET_API_KEY, then run:

Python
from openai import OpenAI
import os

client = OpenAI(base_url="https://inference.broadnet.ai/v1", api_key=os.environ["BROADNET_API_KEY"])

response = client.chat.completions.create(
    model="broadnet/glm-5.3",
    max_tokens=2000,  # reasoning counts toward max_tokens: leave room
    messages=[{"role": "user", "content": "Write a SQL query for monthly active users."}],
)
print(response.choices[0].message.content)

Or with curl

curl
curl https://inference.broadnet.ai/v1/chat/completions \
  -H "Authorization: Bearer $BROADNET_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"broadnet/glm-5.3","messages":[{"role":"user","content":"Reply with one short sentence."}]}'

GLM 5.3 reasons before it answers. The reasoning counts toward max_tokens and is reported as usage.completion_tokens_details.reasoning_tokens, inside the completion (output) token count, so budget for it as output. Leave 1,000 tokens or more, or set reasoning_effort to low, or the answer can come back empty. Why answers come back empty.

Guides for GLM 5.3

Use GLM 5.3 in the console

The BroadNet console on inference.broadnet.ai manages accounts and keys. It does not receive your choice from this page, so:

  1. Sign in or create an account.
  2. Add a qualifying top-up (the starting credit does not cover this model), then create a pay-as-you-go key.
  3. Send this model ID as model to /v1/chat/completions: broadnet/glm-5.3

Open the BroadNet consoleEstimate the costRead the API reference

Compare GLM 5.3

Questions

What is the model ID for GLM 5.3?

Pass broadnet/glm-5.3 as model to /v1/chat/completions. The base URL is https://inference.broadnet.ai/v1.

How much does GLM 5.3 cost?

$0.78 input, $0.173 cached input and $3.46 output per 1M tokens, from your account balance.

What is the context window of GLM 5.3?

1,048,576 tokens per request, prompt and answer together.

Can I use GLM 5.3 without a top-up?

No. GLM 5.3 opens after a qualifying top-up. The starting credit covers BroadNet Gemma 4 VL 26B, BroadNet Transcribe Arabic, BroadNet Transcribe and Gemma hourly keys.

How does GLM 5.3 score on benchmarks?

As published, the Z.ai model card reports 88.2 on Terminal Bench 2.1 and 66.9 on DeepSWE (v1.1); Epoch AI measured 0.909 on GPQA Diamond in its own run, as a mean score on a 0 to 1 scale (checked 2026-11-16). BroadNet did not run these benchmarks, and sources may use different settings, so the figures are not directly comparable. Every published result we found, with its setting and source.

Is my data stored?

Inference content is not retained: prompts, images and answers are processed for the request only. Necessary account, billing and security metadata, such as timings, token counts and cost, is retained as described in BroadNet's privacy statement. Read how.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity