New Sign up free, 10 calls on us. Up to $1, no card needed.

GLM-5.3-Flash

chatCodeReasoningVisionTool callingPrompt caching

GLM-5.3-Flash is the natively multimodal member of the GLM-5.3 line, positioned for efficient coding and long-horizon agent tasks.

Input
text image video $0.15/M
Output
text $0.5/M
Cache read
$0.03/M
Context
1M
vs GPT-4o
~97% cheaper

Benchmarks

Above averageNo peer higher5 / 61 / 6
GLM-5.3-Flash other models measured peer average no peer scored higher
Terminal-Bench 2.1
84.3%
GDPval-AA v2 Elo · 1504-1773 per Z.ai · 2026-09-04
no peer scored higher 1773
Humanity's Last Exam with tools
55.3%
Agents' Last Exam
26.3%

Vendor-published: Alibaba (Qwen) Anthropic DeepSeek Google Moonshot OpenAI Tencent Z.ai

Price in context

Where the price sits among 65 comparable models

Input$0.15/M
$0.05 · Qwen3 VL Flash GPT-5.4 Pro · $30
Output$0.5/M
$0.275 · DeepSeek V4 Flash GPT-5.4 Pro · $180
Cached read$0.03/M
$0.0028 · DeepSeek V4 Flash GPT-5.4 Pro · $15

The bar shows how this model’s price compares with every other model of the same kind on Synthorai. The cheapest and the most expensive are named at each end. These are base rates; batch, region and cache-write discounts are on the pricing page.

Specs & limits

Tokens

Context window (vendor spec) 1,000,000
Max output (vendor spec) 163,840

Prompt caching

How it caches automatic

Thinking

Vendor control reasoning_effort
Accepted values low · high · max
Default max applied when the request sets nothing
Can be turned off No
Thinking behaviour Same dial as GLM-5.3 with no documented way to switch thinking off; clear_thinking defaults to false.
Parameter reasoning_effort
Values minimal · low · medium · high the gateway's parameter surface - the vendor mapping above applies

Model

Modalities text + image + video → text
Parameters 320B total · 18B active MoE (hybrid sparse + linear attention, mHC)
  • Natively multimodal member of the GLM-5.3 line, taking image and video alongside text
  • the hybrid sparse-plus-linear attention architecture is credited with holding accurate long-context behaviour while cutting compute overhead

per Z.ai official docs ↗

One prompt, measured through the gateway

PROMPT Explain to a CFO, in exactly three sentences, why our LLM bill doubled after we enabled reasoning. CHECK exactly 3 sentences

GLM-5.3-Flash passed · 3 sentences

Enabling reasoning means the model now generates thousands of invisible "thinking" tokens before each visible answer, and we're billed for those hidden tokens at full output rates—our most expensive tier. Since output tokens cost 3–5x more than input tokens, that hidden thinking volume compounds across every request, which is why the bill doubled rather than edged up. If the spend concerns you, the fix is straightforward: route only complex queries to reasoning models and keep simple tasks on standard ones, which can reclaim a meaningful share of that cost without losing accuracy where it matters.

out 742 tok (+626 thinking) latency 23.2 s

Instruction following (exactly three sentences - countable), audience shaping (CFO register), and the hidden-thinking billing gap the token meters below expose.

PROMPT This function is supposed to return the longest run of consecutive equal items, but callers report it is off by one on single-element inputs and misses runs that end at the last index. Fix it and explain the bug in one paragraph. CHECK fix passes tests

GLM-5.3-Flash passed · 8/8 cases

```python def longest_run(xs): if not xs: return 0 best = cur = 1 for i in range(1, len(xs)): if xs[i] == xs[i - 1]: cur += 1 best = max(best, cur) else: cur = 1 return best ``` **The bug:** `cur` is supposed to hold the length of the current run, but it's seeded with `0` and reset to `0` on a mismatch instead of `1` — and since the loop starts at index 1, the first element of every run never passes through the `==` branch and so never gets counted at all. That means `cur` actually holds *run length minus 1* for every run, so every run is underreported by one: a single-element input never enters the loop and returns 0 instead of 1, and a run of length n returns n − 1 (e.g., `[3, 3, 3]` returns 2). […]

out 2462 tok (+2138 thinking) latency 29.1 s

Whether the fix is actually correct (runnable), explanation density, and token efficiency on a bounded task.

PROMPT Extract a JSON object with fields {company, quarter, revenue_usd_m, growth_pct, guidance} from this text. Use null for anything not stated; add no other fields. CHECK valid JSON, schema exact

GLM-5.3-Flash passed · 5/5 fields, guidance "Withheld pending the Q4 close"

```json { "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": 412, "growth_pct": 11, "guidance": "Withheld pending the Q4 close" } ``` Notes on judgment calls: revenue of 412 is on a constant-currency basis as stated; growth of "eleven and change" is approximated as 11 since no precise figure is given.

out 717 tok (+616 thinking) latency 9.1 s

Schema obedience (no invented fields), hallucination pressure (guidance is explicitly withheld), and structured-output path differences.

PROMPT Write a 120-word product announcement for an API gateway feature that caches prompts across providers. Forbidden words: "seamless", "unlock", "game-changer", "revolutionize", "empower". Exactly one sentence must be a question. CHECK 120 words, 0 banned words

GLM-5.3-Flash passed · 120 words, 0 banned, 1 question

Introducing Cross-Provider Prompt Cache, the newest feature in our API gateway. Today, teams send identical prompts to multiple LLM providers and pay full price each time. Why duplicate that work and cost? With Cross-Provider Prompt Cache, your gateway stores prompt-response pairs and serves repeated requests from cache, regardless of which provider handles the call. The result: lower latency, reduced spend, and consistent outputs across OpenAI, Anthropic, Google, and self-hosted models. Configure cache policies per route, set TTLs, and invalidate entries instantly through the dashboard or API. Built-in analytics show hit rates and savings in real time. Enable the cache with a single flag, no code changes required. Available today on all paid plans. Contact sales for enterprise volume pricing details.

out 2095 tok (+1937 thinking) latency 20.2 s

Constraint obedience (word budget, banned-word list, the single question), style fingerprint, and length control.

Use GLM-5.3-Flash in 30 seconds

OpenAI-compatible: swap the base_url, keep your SDK. POST /v1/chat/completions

from openai import OpenAI

client = OpenAI(
    base_url="https://synthorai.io/v1",
    api_key="sk-syn-...",
)

resp = client.chat.completions.create(
    model="glm-5.3-flash",
    messages=[{"role": "user", "content": "Summarize this diff"}],
    reasoning_effort="medium",
)
print(resp.choices[0].message.content)

About GLM-5.3-Flash

  • It accepts image and video alongside text and returns text, and its hybrid architecture, sparse attention combined with linear attention and Manifold-Constrained Hyper-Connections, is described as holding accurate long-context behaviour while reducing compute overhead.
  • The efficiency is visible in the shape of the model: 320B total parameters with just 18B active, against the 753B of GLM-5.3.
  • That is what makes it the low-cost tier, and it is worth being precise about what is not traded away, because it is served with the same 1M-token context window rather than a smaller one.
  • Thinking behaves as it does on GLM-5.3, with reasoning_effort at low, high or max and defaulting to max and no documented way to switch it off, so output budgets need to account for a reasoning trace on every call.
  • Tool calling, JSON and structured output, streaming and cached input are all supported, and the weights are published openly.
  • On Synthorai it is served through the OpenAI-compatible chat completions endpoint.

FAQ

Is the GLM-5.3-Flash API free to try?

Yes: new accounts get 10 trial calls and up to $1 in free credit, no card required. At $0.15/M input tokens, that credit alone covers roughly 833 requests of ~8K tokens against GLM-5.3-Flash.

What is GLM-5.3-Flash best at?

Natively multimodal with image and video input; 320B total parameters, just 18B active; the same 1M-token window at the low-cost tier. See the About section for the full picture from the vendor's own release notes.

How much does GLM-5.3-Flash cost?

GLM-5.3-Flash costs $0.15 per million input tokens and $0.5 per million output tokens on Synthorai. That is the provider's list price, with no platform markup. Cached input tokens bill at $0.03/M.

Does GLM-5.3-Flash support prompt caching?

Yes, automatically: Z.ai-served prompts cache with no code changes. Cached input tokens bill at $0.03/M vs $0.15/M uncached. Prompt caching guide →

How do I get access to GLM-5.3-Flash?

Point your existing OpenAI SDK at base_url="https://synthorai.io/v1", set model="glm-5.3-flash", and you're done. One API key covers every model on the gateway.

Related models

Compare

Every value on this page is transcribed from the vendor's own documentation, linked above, and carries the date it was checked. Prices are compared across the catalogue; specification values that vendors define differently are shown with the difference stated rather than charted. Nothing here is measured by us, and nothing is scored.

Get your API key Compare your cost →