Z.ai: GLM-5.3-Flash

zai/glm-5.3-flash

The first native multimodal model in the GLM-5 series, delivering stronger intelligence than GLM-5.2 at very low cost.

ModalitiesTextImageText

In / out price$0.060 / $0.200 per 1M

Context—

Released—

Providers

Where this model runs, and what each route costs. Requests are sent to a healthy provider automatically; if one errors, the gateway retries against another serving the same model.

Provider	Input /M	Output /M	Cache read /M	Latency	Throughput
Z.ai	$0.060	$0.200	$0.030	16.61s	74 tps

Capabilities (9)

StreamingTool callingStructured outputThinkingReasoningVisionSystem promptPrompt cachingWeb search

Supported parameters (2)

toolsresponse_format

Any other parameter you send is ignored rather than rejected.

Pricing

What this model costs to run, next to the rate it is posted at. Caching and discounts mean the price actually paid is often below the listed one.

Effective input price

$0.060

/M tokens · listed $0.150

Effective output price

$0.200

/M tokens · listed $0.500

Rate	Listed	Charged	Unit
Input	$0.150	$0.060	per 1M tokens
Output	$0.500	$0.200	per 1M tokens
Cache read	$0.030	$0.030	per 1M tokens

UTC

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better). Throughput and TTFT are measured on streaming requests, which are the only ones with a first-token moment to time.

Throughput

74tok/s

P50, streaming requests

Latency

16.61s

P50, end to end

UTC

Throughput

P991573 tok/s

P95365 tok/s

P5056 tok/s

Latency

P5018.4s

P7525.1s

P9543.1s

P9948.9s

Time to first token

P5011.2s

P9519.9s

Cache hit rate

5.25%

Share of input tokens served from the prompt cache over the window.

Availability

The share of requests to this model that completed successfully. When an upstream provider errors, the gateway retries against another provider serving the same model, so a single provider incident does not necessarily show up here.

Success rate (30d)

53.10%

over 179 requests

Days with traffic

of the last 30

Days are UTC days. Days with no requests are omitted rather than drawn at 100% — no traffic is not evidence of availability.

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

1.Agnai.Chat 287.8K tokens
2.Oxyy Tester27.4K tokens

Activity

Token volume and request traffic to this model over time. Daily totals, UTC.

Prompt263.0K

Reasoning3.4K

Completion56.4K

Prompt tokens measure input size. Reasoning tokens show internal thinking before a response. Completion tokens reflect total output length.

Frequently asked questions

What is GLM-5.3-Flash?

The first native multimodal model in the GLM-5 series, delivering stronger intelligence than GLM-5.2 at very low cost.

How much does GLM-5.3-Flash cost?

GLM-5.3-Flash costs $0.150 per million input tokens and $0.500 per million output tokens. Cached prompt tokens are billed at $0.030 per million. You pay per request, with no subscription.

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

The context window for GLM-5.3-Flash is not published.

Does GLM-5.3-Flash support tool calling and structured outputs?

Yes — GLM-5.3-Flash supports both tool calling and structured outputs.

What inputs and outputs does GLM-5.3-Flash support?

GLM-5.3-Flash accepts text, image as input and returns text.

What other models does Z.ai have?

Z.ai also offers CogVideoX-3, CogView-4, GLM-4-32B-0414-128K, GLM-4.5 through Oxyy.

When was GLM-5.3-Flash released?

No release date is published for GLM-5.3-Flash.

Explore more models

Browse the full catalog Models Compare pricing Pricing

More models from Z.ai

CogVideoX-3Z.ai's video generation model.text to video · — context CogView-4Z.ai's CogView image generation model.image generation · — context GLM-4-32B-0414-128K32-billion-parameter GLM-4 model with a 128K context window, flat-priced on input and output.text · 128K context · $0.100 / $0.100 GLM-4.5GLM-4.5 base text model. The release that introduced interleaved reasoning to the GLM line.text · — context · $0.600 / $2.20 GLM-4.5-AirLightweight, low-cost variant of GLM-4.5.text · — context · $0.200 / $1.10 GLM-4.5-AirXHigh-throughput variant of GLM-4.5-Air.text · — context · $1.10 / $4.50

Provider

Input /M

Output /M

Cache read /M

Latency

Throughput

Z.ai

$0.060

$0.200

$0.030

16.61s

74 tps

Rate

Listed

Charged

Unit

Input

$0.150

$0.060

per 1M tokens

Output

$0.500

$0.200

per 1M tokens

Cache read

$0.030

per 1M tokens