Zhipu AI (Z.ai)

GLM-5.3-Flash

Generally availableOpen weights1M contextReasoning

Summary

GLM-5.3-Flash is an open-weight language model from Zhipu AI (Z.ai), released on 26 Aug 2026. It accepts text, images, video and PDFs and generates text, with a 1M-token context window and up to 131K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.15 per million input tokens and $0.50 per million output tokens (Z.ai API), across 14 providers we track.

Native multimodal GLM model for efficient coding and long-horizon agent tasks

Last verified 18 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperZhipu AI (Z.ai)
Release date26 Aug 2026 [models.dev]
StatusGenerally available [models.dev]
WeightsOpen weights [Hugging Face]
Licensemit [Hugging Face]
Parameters321B [Hugging Face]
Context window1M (1,000,000 tokens) [models.dev]
Max output131K tokens [models.dev]
InputText, images, video and PDFs [models.dev]
OutputText [models.dev]
Reasoning modeYes [models.dev]
Tool callingYes [models.dev]
Structured outputYes [models.dev]
Hugging Facezai-org/GLM-5.3-Flash [Hugging Face]

GLM-5.3-Flash API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
NVIDIA NIM
z-ai/glm-5.3-flash
FreeFree–1Mmodels.dev, 18 Nov 2026
Z.ai API
glm-5.3-flash
$0.15$0.50$0.031Mmodels.dev, 18 Nov 2026
Mistral API
zai-glm-5-3-flash
$0.15$0.50$0.031Mmodels.dev, 18 Nov 2026
Fireworks AI
accounts/fireworks/models/glm-5p3-flash
$0.15$0.50$0.031Mmodels.dev, 18 Nov 2026
FriendliAI
zai-org/GLM-5.3-Flash
$0.15$0.50$0.031Mmodels.dev, 18 Nov 2026
Hugging Face Inference Providers
zai-org/GLM-5.3-Flash
$0.15$0.50–1Mmodels.dev, 18 Nov 2026
Nebius AI Studio
zai-org/GLM-5.3-Flash
$0.15$0.50$0.031Mmodels.dev, 18 Nov 2026
Baseten
zai-org/GLM-5.3-Flash
$0.15$0.50$0.031Mmodels.dev, 18 Nov 2026
Novita AI
zai-org/glm-5.3-flash
$0.15$0.50$0.031Mmodels.dev, 18 Nov 2026
DeepInfra
zai-org/GLM-5.3-Flash
$0.15$0.50$0.031Mmodels.dev, 18 Nov 2026
Fireworks AI
accounts/fireworks/routers/glm-flash-latest
$0.15$0.50$0.031Mmodels.dev, 18 Nov 2026
SiliconFlow
zai-org/GLM-5.3-Flash
$0.15$0.50$0.031Mmodels.dev, 18 Nov 2026
Together AI
zai-org/GLM-5.3-Flash
$0.15$0.50$0.031Mmodels.dev, 18 Nov 2026
Vercel AI Gateway
zai/glm-5.3-flash
$0.15$0.50$0.031Mmodels.dev, 18 Nov 2026
OpenRouter
z-ai/glm-5.3-flash
$0.15$0.50$0.031MOpenRouter, 18 Nov 2026
Z.ai API
glm-5.3-flashx
$0.37$1.25$0.071Mmodels.dev, 18 Nov 2026
Novita AI
zai-org/glm-5.3-flashX
$0.37$1.25$0.071Mmodels.dev, 18 Nov 2026
Vercel AI Gateway
zai/glm-5.3-flashx
$0.37$1.25$0.071Mmodels.dev, 18 Nov 2026

Running GLM-5.3-Flash locally

Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.

QuantizationWeightsTotal, 8K contextTotal, 32K context
Q4_K_M (4-bit)195 GB196 GB196 GB
Q8_0 (8-bit)341 GB342 GB343 GB
FP16 / BF16 (16-bit)643 GB644 GB644 GB

At 4-bit with an 8K conversation, GLM-5.3-Flash needs about 196 GB, more than any single consumer graphics card; it needs a unified-memory machine, a multi-GPU setup or a split between graphics card and system RAM. Check your own hardware, or see Best computer for local AI on our sister site AIPCs.

Frequently asked questions

What is the context window of GLM-5.3-Flash?

GLM-5.3-Flash has a context window of 1,000,000 tokens (1M) and can generate up to 131,072 tokens in a single response, according to models.dev.

How much does the GLM-5.3-Flash API cost?

Through Z.ai API, GLM-5.3-Flash costs $0.15 per million input tokens and $0.50 per million output tokens. Prices last verified 18 Nov 2026.

Is GLM-5.3-Flash open source?

GLM-5.3-Flash is an open-weight model: its weights are published on Hugging Face as zai-org/GLM-5.3-Flash under the mit license. Check the license terms before commercial use.

When was GLM-5.3-Flash released?

Zhipu AI (Z.ai) released GLM-5.3-Flash on 26 Aug 2026, according to models.dev.

Which providers offer GLM-5.3-Flash?

We track GLM-5.3-Flash on 14 providers: NVIDIA NIM, Z.ai API, Mistral API, Fireworks AI, FriendliAI, Hugging Face Inference Providers, Nebius AI Studio, Baseten, Novita AI, DeepInfra, SiliconFlow, Together AI, Vercel AI Gateway, OpenRouter.

How much VRAM does GLM-5.3-Flash need?

About 196 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 342 GB at 8-bit. That is more than any single consumer graphics card holds. These are estimates from the model's published parameter count and architecture.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
GPT-6 Luna ProOpenAI22 Sept 20261.1M$0.10$0.50–
DeepSeek V4 Flash Vision ExpDeepSeek21 Aug 20261M$0.22$0.65Open
NVIDIA Nemotron 3.5 Super VLNVIDIA15 Oct 20261M$0.15$0.50Open
DeepSeek V4 ProDeepSeek13 Aug 20261M$0.11$0.87Open
MiMo-V2.6-FlashXiaomi (MiMo)22 Sept 20261M$0.14$0.28Open
Muse Spark 1.2 ContributorMeta21 Aug 20261M$0.10$0.20–

Change history

  • OpenRouter price changed: input $0.04 → $0.15, output $0.08 → $0.50 per 1M tokens
  • Release date changed from 18 Sept 2026 to 26 Aug 2026
  • Name changed from GLM-5.3-FlashX to GLM-5.3-Flash
  • Name changed from GLM-5.3-Flash to GLM-5.3-FlashX
  • Release date changed from 26 Aug 2026 to 18 Sept 2026
  • OpenRouter price changed: input $0.03 → $0.04, output $0.08 → $0.08 per 1M tokens
  • Release date changed from 18 Sept 2026 to 26 Aug 2026
  • Name changed from GLM-5.3-FlashX to GLM-5.3-Flash
  • No longer listed on cloudflare-workers-ai
  • OpenRouter price changed: input $0.15 → $0.03, output $0.50 → $0.08 per 1M tokens
  • Name changed from GLM-5.3-Flash to GLM-5.3-FlashX
  • Release date changed from 26 Aug 2026 to 18 Sept 2026
  • Now listed on Novita AI
  • Release date changed from 18 Sept 2026 to 26 Aug 2026
  • Name changed from GLM-5.3-FlashX to GLM-5.3-Flash
  • OpenRouter price changed: input $0.03 → $0.15, output $0.10 → $0.50 per 1M tokens
  • OpenRouter price changed: input $0.03 → $0.03, output $0.08 → $0.10 per 1M tokens
  • Name changed from GLM-5.3-Flash to GLM-5.3-FlashX
  • Release date changed from 26 Aug 2026 to 18 Sept 2026
  • OpenRouter price changed: input $0.03 → $0.03, output $0.09 → $0.08 per 1M tokens
  • Release date changed from 18 Sept 2026 to 26 Aug 2026
  • Name changed from GLM-5.3-FlashX to GLM-5.3-Flash
  • Name changed from GLM-5.3-Flash to GLM-5.3-FlashX
  • Release date changed from 26 Aug 2026 to 18 Sept 2026
  • OpenRouter price changed: input $0.02 → $0.03, output $0.15 → $0.09 per 1M tokens

Sources