Cheap GLM API: Compare GLM-5.3, Flash and FlashX Prices
GLM-5.3 Flash from $0.072/$0.24 and FlashX from $0.148/$0.50 per 1M tokens. Compare Z.ai and OpenRouter prices, task budgets and API key access.
Published
GLM-5.3 Flash starts at $0.072 / $0.24, FlashX at $0.148 / $0.50, and GLM-5.3 at $0.77 / $2.42. The lowest FlashX route is 60% below official standard token prices; Flash and 5.3 have separate discounts.
Checked 2026-11-04 03:32 UTC. Prices are USD per 1M input / output tokens; the table shows the lowest and highest input-priced public route as input / output pairs. Counts exclude client-only routes. The live marketplace card controls current price and availability.
| Model ID | Official reference price | APIMaster current price | Active routes | Discount | Model card |
|---|---|---|---|---|---|
glm-5.3 |
$1.4 / $4.4 | $0.77 / $2.42 – $1.4 / $4.4 | 8 | Up to 45% off | Compare routes |
glm-5.3-flash |
$0.15 / $0.5 | $0.072 / $0.24 – $0.15 / $0.5 | 7 | Up to 52% off | Compare routes |
glm-5.3-flashx |
$0.37 / $1.25 | $0.148 / $0.5 – $0.37 / $1.25 | 4 | Up to 60% off | Compare routes |
Z.ai's current uncached prices are $1.40/$4.40 for 5.3, $0.15/$0.50 for Flash and $0.37/$1.25 for FlashX. Lowest-route savings are 45%, 52% and 60% respectively. Switching from 5.3 to Flash is a model choice, not an additional same-model discount.
GPT Trial(GPT-6 Astra, GPT-6 Sol, GPT-5.6, GPT-5.5, gpt-5.6-luna, gpt-5.6-sol, gpt-5.6-terra, gpt-6.1-sol, gpt-6-astra, gpt-6-sol, and gpt-6-luna available)
Sign up and claim a $20 GPT trial
GLM API pricing: official vs OpenRouter vs APIMaster
| Provider / model | Input / output | Billing condition | APIMaster saving |
|---|---|---|---|
| APIMaster · glm-5.3-flashx | $0.148 / $0.5 | Standard, uncached | — |
| Z.ai · GLM-5.3-FlashX | $0.37 / $1.25 | Standard, uncached | At least 60% lower token rates |
| OpenRouter · z-ai/glm-5.3-flashx | $0.37 / $1.25 | Catalog snapshot; provider terms apply | At least 60% lower token rates |
| OpenRouter · z-ai/glm-5.3-flash | $0.0313 / $0.0846 | Different model; compare separately | — |
OpenRouter lists FlashX at $0.37/$1.25, but its Flash listing is $0.0313/$0.0846, below APIMaster's checked Flash rates. Compare the provider and supported features; do not treat Flash and FlashX as interchangeable. Official cache reads are $0.26/$0.03/$0.075 for 5.3/Flash/FlashX, with storage currently marked limited-time free.
What does a real token budget cost?
Budget: 100,000 uncached input tokens + 20,000 billed output tokens per task. Formula: input_tokens × input_rate / 1,000,000 + output_tokens × output_rate / 1,000,000. This is arithmetic, not a measured model benchmark.
| Model ID | Official reference / task | APIMaster from / task | APIMaster / 1,000 tasks |
|---|---|---|---|
glm-5.3 |
$0.228 | $0.1254 | $125.4 |
glm-5.3-flash |
$0.025 | $0.012 | $12 |
glm-5.3-flashx |
$0.062 | $0.0248 | $24.8 |
The 1,000-task column scales the same budget; it is not a bulk discount. Figures are rounded and exclude cache, storage, search/tools, taxes and retries. Include billed reasoning output and every agent call. Different models can consume different token counts; compare cost per accepted result.
Which GLM model or route should you buy?
Choose Flash for the lowest checked APIMaster token bill, FlashX if its serving profile fits your latency needs, and 5.3 when your task tests justify its higher cost. At the table's budget, 1,000 FlashX tasks cost $24.80 versus $62 at official Standard. This is a budget calculation, not a measured speed claim.
A GLM Coding Plan subscription and a token-priced API wallet use different limits and billing. Verify client endpoint support before buying for an agent. Upcoming GLM-5.5 or GLM-6 reports do not establish an available discounted API; use the exact listed 5.3-family ID.
Choose the route inside the same model card and confirm supported tools, streaming and limits. Fingerprint results are route-specific identity evidence; availability records are point-in-time checks, not an uptime guarantee. Missing test records do not count as passes.
How to get a discounted GLM API key
Compare the live model card → register → fund your wallet → create an API key. Use your APIMaster key, https://apimaster.ai/v1, and the exact model ID glm-5.3-flashx:
curl "https://apimaster.ai/v1/chat/completions" \
-H "Authorization: Bearer $APIMASTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"glm-5.3-flashx","max_tokens":512,"messages":[{"role":"user","content":"Return a JSON object with a short summary of: API costs depend on token usage."}]}'
This is a minimal integration example, not a new paid inference test. Check endpoint compatibility, returned usage and your first small bill before increasing traffic. An APIMaster key does not fund an account at the original vendor.
FAQ
Is this the cheapest API on the internet?
No universal lowest-price claim is made. This guide compares the checked public routes and named billing modes; another provider or specialized route can be cheaper.
Does an app subscription include these API credits?
Treat app subscriptions, coding plans and pay-as-you-go API wallets as separate products unless their terms explicitly include the same usage.
Does the headline discount also cover cache hits?
No. Compare cached reads, cache writes, storage, tools and timing separately; ordinary token discounts do not prove the same saving on every billing item.
Does the GPT trial promotion provide this model for free?
The GPT trial offer is separate. It does not promise free credits for the models in this guide; check the current trial catalog and eligibility.
Sources and related guides
Official pricing · OpenRouter model catalog
GLM-5.3 FlashX · GLM FlashX vs DeepSeek Flash · GLM-5.5 vs 5.3
Other cheap API guides: Claude Sonnet 5.5 · Gemini Flash · DeepSeek · Qwen
Get started: Compare the live model card → register → fund your wallet → create an API key. Use your APIMaster key, https://apimaster.ai/v1, and the exact model ID glm-5.3-flashx