GLM 5.3
Z.AI · Active · available in 31 of 31 regions
- Context window
- 1M
- 1,000,000 tokens
- Max output
- 128K
- Input / 1M
- $1.68
- us-east-1
- Output / 1M
- $5.28
What GLM 5.3 is good for
editorialGLM 5.3 offers a 1M-token context window with tool use and prompt caching, at the premium end of this provider’s range at $1.68 per 1M input tokens. Callable in 31 of 31 regions.
Suits
- Very long inputs. A 1M-token window holds an entire codebase or a day of transcripts in one call, so you can skip chunking.
- Repeated prompts. Supports prompt caching, so a re-sent prefix costs about 5× less than fresh input. On agentic loops that resend a long system prompt every step, this moves the bill more than the headline price does.
- Tool use. Can call functions, so it can drive retrieval, look things up, and take actions rather than only answering.
Think twice if
- Documents with layout. Text only. Scanned PDFs, screenshots and charts need a vision model or an OCR step first.
- High volume. At $1.68 per 1M input tokens it sits at the expensive end of the Z.AI range. Worth it for hard tasks, wasteful for bulk extraction.
- Invocation. Reachable only through a cross-region inference profile — calling the bare model ID returns a validation error. Use an ID such as global.zai.glm-5.3.
This section is judgement, not data from AWS. It is composed from the capabilities, context window, price position and region coverage shown elsewhere on this page — so it stays in step with the daily snapshot rather than going stale.
Model & inference profile IDs
Base model ID — direct on-demand invoke
Cross-region inference profiles (2)
Regions marked Inference profile only require a profile ID rather than the base model ID — invoking the base ID there returns a validation error. Regional (us., eu.) profiles carry a 10% premium over global.
Pricing by region
USD per 1M tokens| Region | Input | Output | Cache read | Cache write | Batch in | Batch out | Source |
|---|---|---|---|---|---|---|---|
| us-east-1 US East (N. Virginia) | $1.68 | $5.28 | $0.312 | $2.10 | — | — | curated |
| us-east-2 US East (Ohio) | $1.68 | $5.28 | $0.312 | $2.10 | — | — | curated |
| us-west-1 US West (N. California) | $1.68 | $5.28 | $0.312 | $2.10 | — | — | curated |
| us-west-2 US West (Oregon) | $1.68 | $5.28 | $0.312 | $2.10 | — | — | curated |
| ca-central-1 Canada (Central) | $1.68 | $5.28 | $0.312 | $2.10 | — | — | curated |
| ca-west-1 Canada West (Calgary) | $1.68 | $5.28 | $0.312 | $2.10 | — | — | curated |
| mx-central-1 Mexico (Central) | $1.68 | $5.28 | $0.312 | $2.10 | — | — | curated |
| eu-west-1 EU (Ireland) | $1.68 | $5.28 | $0.312 | $2.10 | — | — | curated |
| eu-west-2 EU (London) | $1.68 | $5.28 | $0.312 | $2.10 | — | — | curated |
| eu-west-3 EU (Paris) | $1.68 | $5.28 | $0.312 | $2.10 | — | — | curated |
| eu-central-1 EU (Frankfurt) | $1.68 | $5.28 | $0.312 | $2.10 | — | — | curated |
| eu-central-2 Europe (Zurich) | $1.68 | $5.28 | $0.312 | $2.10 | — | — | curated |
| eu-north-1 EU (Stockholm) | $1.68 | $5.28 | $0.312 | $2.10 | — | — | curated |
| eu-south-1 EU (Milan) | $1.68 | $5.28 | $0.312 | $2.10 | — | — | curated |
| eu-south-2 Europe (Spain) | $1.68 | $5.28 | $0.312 | $2.10 | — | — | curated |
| ap-east-2 Asia Pacific (Taipei) | $1.68 | $5.28 | $0.312 | $2.10 | — | — | curated |
| ap-northeast-1 Asia Pacific (Tokyo) | $1.68 | $5.28 | $0.312 | $2.10 | — | — | curated |
| ap-northeast-2 Asia Pacific (Seoul) | $1.68 | $5.28 | $0.312 | $2.10 | — | — | curated |
| ap-northeast-3 Asia Pacific (Osaka) | $1.68 | $5.28 | $0.312 | $2.10 | — | — | curated |
| ap-south-1 Asia Pacific (Mumbai) | $1.68 | $5.28 | $0.312 | $2.10 | — | — | curated |
| ap-south-2 Asia Pacific (Hyderabad) | $1.68 | $5.28 | $0.312 | $2.10 | — | — | curated |
| ap-southeast-1 Asia Pacific (Singapore) | $1.68 | $5.28 | $0.312 | $2.10 | — | — | curated |
| ap-southeast-2 Asia Pacific (Sydney) | $1.68 | $5.28 | $0.312 | $2.10 | — | — | curated |
| ap-southeast-3 Asia Pacific (Jakarta) | $1.68 | $5.28 | $0.312 | $2.10 | — | — | curated |
| ap-southeast-4 Asia Pacific (Melbourne) | $1.68 | $5.28 | $0.312 | $2.10 | — | — | curated |
| ap-southeast-5 Asia Pacific (Malaysia) | $1.68 | $5.28 | $0.312 | $2.10 | — | — | curated |
| ap-southeast-6 Asia Pacific (New Zealand) | $1.68 | $5.28 | $0.312 | $2.10 | — | — | curated |
| ap-southeast-7 Asia Pacific (Thailand) | $1.68 | $5.28 | $0.312 | $2.10 | — | — | curated |
| il-central-1 Israel (Tel Aviv) | $1.68 | $5.28 | $0.312 | $2.10 | — | — | curated |
| af-south-1 Africa (Cape Town) | $1.68 | $5.28 | $0.312 | $2.10 | — | — | curated |
| sa-east-1 South America (Sao Paulo) | $1.68 | $5.28 | $0.312 | $2.10 | — | — | curated |
Curated pricing. The AWS Price List API publishes no SKU for this model, so these figures are hand-maintained from AWS's public pricing page and verified on Oct 24, 2026. They are not machine-derived — confirm in the AWS console before committing spend. Access limited to eligible customers. Global endpoint; the US profile bills 10% more ($1.848 / $5.808). Cache writes are the 30-minute rate.
Region availability
TPM / RPM are default account quotas from AWS Service Quotas where a model-specific limit is published. They are per-account defaults and adjustable on request.
Where this model actually runs
Under a strict residency constraint, GLM 5.3 can be served without the request leaving 1 of the 25 jurisdictions with a Bedrock region.
GLM 5.3 appears in
Common questions
- How much does GLM 5.3 cost on Amazon Bedrock?
- $1.68 per 1M input tokens and $5.28 per 1M output tokens in us-east-1. Cached input reads at $0.312, 18.6% of the input rate, which dominates the bill on agentic workloads that re-send a long prefix.
- Which AWS regions support GLM 5.3?
- 31 of 31 regions: us-east-1, us-east-2, us-west-1, us-west-2, ca-central-1, ca-west-1, mx-central-1, eu-west-1, eu-west-2, eu-west-3, eu-central-1, eu-central-2, eu-north-1, eu-south-1, eu-south-2, ap-east-2, ap-northeast-1, ap-northeast-2, ap-northeast-3, ap-south-1, ap-south-2, ap-southeast-1, ap-southeast-2, ap-southeast-3, ap-southeast-4, ap-southeast-5, ap-southeast-6, ap-southeast-7, il-central-1, af-south-1, sa-east-1. Regions marked profile-only need a cross-region inference profile ID such as global.zai.glm-5.3 rather than the bare model ID.
- What is the context window of GLM 5.3?
- 1,000,000 tokens (1M), with up to 128K output tokens per request.
- What is the model ID for GLM 5.3 on Bedrock?
- zai.glm-5.3. In regions where it is only reachable through a cross-region inference profile, use a prefixed ID instead: global.zai.glm-5.3, us.zai.glm-5.3.