GLM 5.3 Flash API

Zhipu's GLM 5.3 Flash, through an OpenAI-compatible API. 10 providers quote it now, and each request goes to the offer with the lowest estimated charge that meets your rules.

Providers compete for each request. The exchange ranks the offers that meet your rules by estimated charge. It fixes your maximum charge before the first token, and you pay for the tokens that the model uses.
The OpenAI and Anthropic APIs. Use the OpenAI or Anthropic SDK that you have. Set the base URL and your key, and send glm-5.3-flash as the model.
Your data rules. Send x-liquid-retention: none and only offers whose provider does not keep your content compete for the request.

Facts

Model name: glm-5.3-flash
Maker: Zhipu
Context window: 229.4K · 1M tokens
Input price: $0.045 to $0.200 per million tokens
Output price: $0.096 to $0.500 per million tokens
Providers: 10 independent providers
Regions: ap-southeast, asia, eu, eu-central, global, us

Providers

Munito AI: global, $0.045 input and $0.155 output per million tokens, $0.0093 cache read per million tokens, 1M tokens of context
engy: asia, $0.046 input and $0.140 output per million tokens, $0.020 cache read per million tokens, 229.4K tokens of context
Boundless: us, $0.070 input and $0.202 output per million tokens, $0.014 cache read per million tokens, 1M tokens of context
EmpirioLabs AI: global, $0.075 input and $0.250 output per million tokens, $0.075 cache read per million tokens, 1M tokens of context
Greenference: eu-central, $0.115 input and $0.460 output per million tokens, $0.023 cache read per million tokens, 1M tokens of context
MarsCompute: global, $0.150 input and $0.500 output per million tokens, $0.150 cache read per million tokens, 1M tokens of context
zro: eu, $0.150 input and $0.500 output per million tokens, $0.030 cache read per million tokens, 1M tokens of context
deeprelay: ap-southeast, $0.150 input and $0.500 output per million tokens, $0.030 cache read per million tokens, 1M tokens of context
TensorX: eu, $0.200 input and $0.500 output per million tokens, $0.050 cache read per million tokens, 1M tokens of context
Pera: us, $0.150 input and $0.096 output per million tokens, $0.150 cache read per million tokens, $0.00065 fee for each request, 1M tokens of context

Scores

Intelligence: 27.8, #21 of 41
HLE: 39.9, #47 of 273
GPQA: 91.2, #34 of 250
AA-LCR: 80.0, #44 of 237
SciCode: 51.6, #45 of 123
SimpleQA Verified: 41.0, #52 of 126

Scores: Artificial Analysis (https://artificialanalysis.ai/)

Scores: Epoch AI, 'Capabilities & Benchmarking' (https://epoch.ai/benchmarks)

Request

curl https://router.inference.ai.exchange/v1/chat/completions \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-5.3-flash",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is GLM 5.3 Flash?: GLM 5.3 Flash is a model from Zhipu.
How much does GLM 5.3 Flash cost?: Offers now ask $0.045 to $0.200 per million input tokens and $0.096 to $0.500 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.
What is the context length of GLM 5.3 Flash?: The largest offer takes 1,048,576 input tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can GLM 5.3 Flash do?: Its providers list Documents, Vision, Video input, Reasoning budget, Reasoning effort, JSON object, JSON schema, Frequency penalty, Logit bias, Log probabilities, Min-p sampling, Presence penalty, Repetition penalty, Seed, Stop sequences, Top-k sampling, Top-p sampling, Text, Tools.
What inputs and outputs does GLM 5.3 Flash support?: Text · Files · Images · Video → Text.
Which providers serve GLM 5.3 Flash?: 10 independent providers quote it now, with 10 offers. The table above ranks them by the cost of a typical job.
How do I call GLM 5.3 Flash?: Send "glm-5.3-flash" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was GLM 5.3 Flash listed?: The exchange first listed it on 9/29/2026. This is not its release date.