impulse

GLM 5.3 Flash

Open weights

GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks.

API id glm-5.3-flashReleased 26 Aug 2026 (Aug 2026)
Input / 1M
$0.15
at Z.ai
Output / 1M
$0.50
at Z.ai
Context window
1M
tokens
Max output
128K
tokens per reply
Hosts
26
28 listings
Released
Aug 2026
26 Aug 2026

Pricing

List prices at Z.ai, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.15$0.50
Cached input
80% off input
$0.03
Cache write, 5 minutes$0.00

What it costs a month

At Z.ai list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$71.70
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$61.20
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$109
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$480
Use your own numbers

Where to run it

26 hosts serve GLM 5.3 Flash. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
Z.aiLab API
glm-5.3-flash
$0.15 / $0.50
glm-5.3-flash
$0.06 / $0.20
−60% vs headline
glm-5-3-flash
$0.075 / $0.25
−50% vs headline
GMI CloudInference
GLM-5.3-Flash
$0.075 / $0.25
−50% vs headline
ZeroGPUCloud
glm-5.3-flash
$0.10 / $0.35
−32% vs headline
SailCloud
GLM-5.3-Flash
$0.11 / $0.35
−28% vs headline
AIHubMixGateway
glm-5.3-flash
$0.113 / $0.394
−23% vs headline
W&B InferenceInference
GLM-5.3-Flash
$0.12 / $0.38
−22% vs headline
glm-5.3-flash
$0.114 / $0.40
−22% vs headline
GLM-5.3-Flash
$0.15 / $0.50
ai&Cloud
glm-5.3-flash
$0.15 / $0.50
glm-5.3-flash
$0.15 / $0.50
glm-5.3-flash
$0.15 / $0.50
BasetenInference
GLM-5.3-Flash
$0.15 / $0.50
DeepInfraInference
GLM-5.3-Flash
$0.15 / $0.50
FriendliAIInference
GLM-5.3-Flash
$0.15 / $0.50
GLM-5.3-Flash
$0.15 / $0.50
Together AIInference
GLM-5.3-Flash
$0.15 / $0.50
Fireworks AIInference
glm-5p3-flash
$0.15 / $0.50
PerplexityGateway
glm-5.3-flash
$0.15 / $0.50
databricks-glm-5-3-flash
$0.15 / $0.50
glm-5.3-flash
$0.172 / $0.573
+15% vs headline
GLM-5.3-Flash
$0.20 / $0.66
+33% vs headline
WallyCloud
glm-5.3-flash
$0.272 / $0.65
+54% vs headline
GLM-5.3-Flash
$0.195 / $1.56
+126% vs headline
NVIDIA NIMInference
glm-5.3-flash
-
Show 2 more listings: regions, snapshots and variants
Fireworks AI
Alias
glm-5p3-flash
$0.15 / $0.50
Inference APIs
Alias
glm-5.3-flash
$0.20 / $0.66
+33% vs headline

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
TextImages
Produces
Text
Features
Prompt caching
Open weights
License: MIT
Runs in about 771.2 GB of GPU memory

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

  • CLF AI Gateway
    glm-5.3-flash
    $0.06 / $0.20
    60% less
  • GMI Cloud
    GLM-5.3-Flash
    $0.075 / $0.25
    50% less
  • EmpirioLabs AI
    glm-5-3-flash
    $0.075 / $0.25
    50% less
  • ZeroGPU
    glm-5.3-flash
    $0.10 / $0.35
    32% less
  • Sail
    GLM-5.3-Flash
    $0.11 / $0.35
    28% less

Smaller Zhipu AI models

No cheaper Zhipu AI model keeps its key capabilities.

Other frontier labs

  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    16% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    16% less

Open-weight picks

Model line

Newer and older versions, at each lab's own price.

  1. Aug 2026GLM 5.3 FlashLatest$0.15 / $0.50
  2. Jan 2026GLM 4.7 FlashNot listed
  3. UndatedGLM 4.5 FlashNot listed

Call it

Using Z.ai's API.

Python
from litellm import completion

response = completion(
    model="zai/glm-5.3-flash",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does GLM 5.3 Flash cost?

On Z.ai, GLM 5.3 Flash costs $0.15 per million input tokens and $0.50 per million output tokens. Cached input costs $0.03 per million tokens. The cheapest host is CLF AI Gateway, at $0.06 per million input tokens and $0.20 per million output tokens.

Which APIs offer GLM 5.3 Flash?

GLM 5.3 Flash runs on 26 APIs: Z.ai, CLF AI Gateway, EmpirioLabs AI, GMI Cloud, ZeroGPU, Sail, AIHubMix, W&B Inference, BigModel (Zhipu AI) and 17 more.

What is GLM 5.3 Flash's context window?

1M tokens, with up to 128K tokens in one reply.

Is GLM 5.3 Flash being retired?

No retirement date is scheduled for it on any API we track.

Is there a newer version of GLM 5.3 Flash?

No. GLM 5.3 Flash is the newest model in its line.

What are cheaper alternatives to GLM 5.3 Flash?

Models that cost less and keep most of what it can do: Claude Haiku 5.5 on Anthropic (16% less), GPT-6 Luna on OpenAI (16% less) and Qwen3.8 Omni Flash on Alibaba DashScope (3% less). GLM 5.3 Flash itself costs 60% less on CLF AI Gateway. Savings are on a mix of 3 input tokens to 1 output token.

When was GLM 5.3 Flash released?

Zhipu AI released it on 26 Aug 2026.

What is GLM 5.3 Flash's API model id?

Use glm-5.3-flash with Z.ai. Other hosts use their own ids: glm-5-3-flash on EmpirioLabs AI, GLM-5.3-Flash on GMI Cloud, GLM-5.3-Flash on Sail, GLM-5.3-Flash on W&B Inference.

Sources

Raw catalog entry for glm-5.3-flash on Z.ai
{
  "cache_creation_input_token_cost": 0,
  "cache_read_input_token_cost": 3e-8,
  "input_cost_per_token": 1.5e-7,
  "output_cost_per_token": 5e-7,
  "litellm_provider": "zai",
  "max_input_tokens": 1048576,
  "max_output_tokens": 128000,
  "mode": "chat",
  "supports_function_calling": true,
  "supports_prompt_caching": true,
  "supports_reasoning": true,
  "supports_response_schema": true,
  "supports_tool_choice": true,
  "source": "https://docs.z.ai/guides/overview/pricing",
  "supports_vision": true
}