GLM 5.3

Z.aiReleased Aug 18, 2026

GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.

Try it in the estimate Compare

Input, per 1M tokens: $1.68$1.55 for holders
Output, per 1M tokens: $5.28$4.86 for holders
Context: 1M tokens
Tokens this week: None yet

Price

Agents pay these prices from their AI budget. $BINF holders pay up to 8% less for the credit they buy.

Charge	Agents	Holders	Per
Inputper 1M tokens	$1.68	$1.55	per 1M tokens
Outputper 1M tokens	$5.28	$4.86	per 1M tokens
Cached inputper 1M tokens	$0.31	$0.29	per 1M tokens

Price history

What an agent paid per million tokens, by day.

Unchanged since Sep 29, 2026: $1.68 in and $5.28 out per million tokens.

Usage through bInference

Every call our agents make to this model, by day. Counts only: no prompt or answer is stored.

Last 7 days: 0
Last 30 days: 0
All time: 0

InputOutputReasoning

Where it runs

The hosts serving this model now, and how often each answered over the last day.

Use it

Two settings: our address and your agent’s key. The model is set in each call.

import OpenAI from "openai";const client = new OpenAI({  baseURL: "https://binference.io/api/v1",Address  apiKey: process.env.BINF_API_KEY,Key});const reply = await client.chat.completions.create({  model: "z-ai/glm-5.3",  messages: [{ role: "user", content: "Summarize today's trades" }],  max_tokens: 1024,});

curl https://binference.io/api/v1/chat/completions \Address  -H "Authorization: Bearer $BINF_API_KEY" \Key  -H "Content-Type: application/json" \  -d '{    "model": "z-ai/glm-5.3",    "messages": [{ "role": "user", "content": "Hello" }],    "max_tokens": 1024  }'

Questions

Agents

Holders

Inputper 1M tokens

$1.68

$1.55

per 1M tokens

Outputper 1M tokens

$5.28

$4.86

per 1M tokens

Cached inputper 1M tokens

$0.31

$0.29

per 1M tokens

Host	Answered, last day	Context
Relace, answering	99.7%	1M
InferenceNet, answering	99%	1M
Sail ResearchUSfp8, answering	99.7%	1M
Sail ResearchFp8fp8, answering	99.6%	1M
WaferUS, answering	99.9%	1M
Wafer, answering	99.9%	1M
Reka, answering	99.9%	262K
DeepInfraFp4fp4, answering	99.5%	1M
InceptronFp4fp4, answering	99.1%	1M
AtlasCloudFp8fp8, answering	99.9%	1M
MorphFp8fp8, answering	99.8%	1M
NovitaFp8fp8, answering	100%	1M
MakoraFp4fp4, answering	99.1%	980K
DigitalOcean, answering	98.9%	1M
Phala, answering	99.3%	1M
GMICloudFp8fp8, answering	99.8%	1M
AkashMLFp8fp8, answering	100%	1M
SiliconFlowFp8fp8, answering	99.3%	1M
BaiduFp8fp8, answering	100%	1M
Alibaba, answering	99.9%	1M
DecartFp4fp4, having trouble	99.8%	1M
Friendli, answering	99.9%	1M
MistralZdrnvfp4, answering	99.9%	1M
BaseTenFp4fp4, answering	99.9%	1M
MistralNvfp4nvfp4, answering	99.9%	1M
CrusoeFp4fp4, answering	99.6%	1M
PrimeIntellect, answering	99.9%	1M
Venice, answering	99.5%	1M
Together, answering	99.5%	1M
ParasailFp8fp8, answering	99.8%	1M
Modal, answering	99.4%	1M
BaseTenFp4fp4, answering	99.9%	1M
Fireworks, answering	99.7%	1M
Cloudflare, answering	99.5%	1M
Z.AIFp8fp8, answering	99.9%	1M
MistralNvfp4nvfp4, answering	100%	1M
BaseTenFastfp8, answering	99.8%	1M
BaseTenFastfp8, answering	99.8%	1M
AlibabaFast, answering	99.9%	1M

Host

Answered, last day

Context

Relace

99.7%

InferenceNet

99%

Sail ResearchUSfp8

99.7%

Sail ResearchFp8fp8

99.6%

WaferUS

99.9%

Wafer

99.9%

Reka

99.9%

262K

DeepInfraFp4fp4

99.5%

InceptronFp4fp4

99.1%

AtlasCloudFp8fp8

99.9%

MorphFp8fp8

99.8%

NovitaFp8fp8

100%

MakoraFp4fp4

99.1%

980K

DigitalOcean

98.9%

Phala

99.3%

GMICloudFp8fp8

99.8%

AkashMLFp8fp8

100%

SiliconFlowFp8fp8

99.3%

BaiduFp8fp8

100%

Alibaba

99.9%

DecartFp4fp4

99.8%

Friendli

99.9%

MistralZdrnvfp4

99.9%

BaseTenFp4fp4

99.9%

MistralNvfp4nvfp4

99.9%

CrusoeFp4fp4

99.6%

PrimeIntellect

99.9%

Venice

99.5%

Together

99.5%

ParasailFp8fp8

99.8%

Modal

99.4%

BaseTenFp4fp4

99.9%

Fireworks

99.7%

Cloudflare

99.5%

Z.AIFp8fp8

99.9%

MistralNvfp4nvfp4

100%

BaseTenFastfp8

99.8%

BaseTenFastfp8

99.8%

AlibabaFast

99.9%

import OpenAI from "openai";const client = new OpenAI({ baseURL: "https://binference.io/api/v1",Address apiKey: process.env.BINF_API_KEY,Key});const reply = await client.chat.completions.create({ model: "z-ai/glm-5.3", messages: [{ role: "user", content: "Summarize today's trades" }], max_tokens: 1024,});

curl https://binference.io/api/v1/chat/completions \Address -H "Authorization: Bearer $BINF_API_KEY" \Key -H "Content-Type: application/json" \ -d '{ "model": "z-ai/glm-5.3", "messages": [{ "role": "user", "content": "Hello" }], "max_tokens": 1024 }'

GLM 5.3

Price

Price history

Usage through bInference

Where it runs

Use it

Questions

More from Z.ai

Similar models

GLM 5.3

Price

Price history

Usage through bInference

Where it runs

Where it runs

Use it

Questions

More from Z.ai

Similar models

Where it runs

GLM 5.3

Price

Price history

Usage through bInference

Where it runs

Use it

Questions

How much does GLM 5.3 cost?

How does my agent use GLM 5.3?

How much can GLM 5.3 read at once?

What can GLM 5.3 do?

Are my prompts stored?

More from Z.ai

Similar models

GLM 5.3

Price

Price history

Usage through bInference

Where it runs

Where it runs

Use it

Questions

How much does GLM 5.3 cost?

How does my agent use GLM 5.3?

How much can GLM 5.3 read at once?

What can GLM 5.3 do?

Are my prompts stored?

More from Z.ai

Similar models

Where it runs