GLM 4.7 Pricing & Token Calculator (Zhipu AI (GLM))

Input / Prompt

$0.30/ 1M tokens

$0.0003 per 1K tokens

Output / Completion

$1.10/ 1M tokens

$0.0011 per 1K tokens

Prompt Cache Read

$0.07/ 1M tokens

Save 75% vs prompt

Batch Inference

$0.30/ 1M in

Save 0% via Batch API

Price Ratio

1 : 3.7

Prompt to completion factor

Regional Reach

13AWS Regions

Compare 13 regions ↓

GLM 4.7 Spend Estimator

Model inference spend by prompt volume, cache hit rate, and batch processing.

Prompt Tokens (Millions / month)

M tokens

Completion Tokens (Millions / month)

M tokens

Prompt Cache Hit Rate(75% discount on cached context)

30%

Batch API Mode50% discount on non-realtime async jobs via S3

Estimated Monthly Spend

$0.00

Fresh Prompts:$0.00

Cached Prompts:$0.00

Completions:$0.00

Active: Input: $0.30/1M · Output: $1.10/1M

Key Cost Levers & Architecture

Practical mechanisms to reduce inference costs with GLM 4.7 on AWS

Prompt CachingSave ~75%

Caches repetitive system instructions, schemas, and document prefixes in memory with a 5-minute TTL.

Read Rate: $0.07 / 1M tokens
Write Rate: $0.38 / 1M tokens
Ideal for: Multi-turn conversations, RAG document queries, structured schemas

Batch InferenceSave 0%

Asynchronous bulk processing submitted via Amazon S3 with a standard 24-hour turnaround SLA.

Batch Input: $0.30 / 1M tokens
Batch Output: $1.10 / 1M tokens
Ideal for: Offline classification, synthetic data generation, benchmark evals

Cross-Region & Tiers13 Regions

AWS Bedrock supports standard on-demand inference, priority reserved throughput, and cross-region routing.

Standard: Lowest latency, pay-per-token with zero commitments
Cross-Region Routing: Automatically burst traffic to available regional capacity
GovCloud: Dedicated isolated compliance partitions with +20% uplift

Regional Pricing Matrix

Live rates across all 13 available AWS cloud regions

Baseline: $0.30/1M inGovCloud: $1.26/1M in13 Global Regions

AWS Region	Prompt Input	Completion Output	Cache Read	Batch Input	Pricing Tier
US East (N. Virginia)`us-east-1`	$1.05/1M	$3.85/1M	—/1M	$0.30/1M	+250% vs Baseline
US West (Oregon)`us-west-2`	$0.30/1M	$1.10/1M	—/1M	$0.30/1M	Baseline
EU (Frankfurt)`eu-central-1`	$0.36/1M	$2.64/1M	—/1M	$0.36/1M	+20% vs Baseline
EU (Ireland)`eu-west-1`	$1.26/1M	$4.62/1M	—/1M	$0.36/1M	+320% vs Baseline
Asia Pacific (Tokyo)`ap-northeast-1`	$0.72/1M	$4.62/1M	—/1M	$0.36/1M	+140% vs Baseline
Asia Pacific (Jakarta)`ap-southeast-3`	$0.36/1M	$2.64/1M	—/1M	$0.36/1M	+20% vs Baseline
Asia Pacific (Mumbai)`ap-south-1`	$0.36/1M	$2.64/1M	—/1M	$0.36/1M	+20% vs Baseline
Asia Pacific (Sydney)`ap-southeast-2`	$0.62/1M	$2.27/1M	—/1M	$0.31/1M	+107% vs Baseline
EU (London)`eu-west-2`	$0.47/1M	$3.41/1M	—/1M	$0.47/1M	+55% vs Baseline
EU (Milan)`eu-south-1`	$0.36/1M	$1.32/1M	—/1M	$0.36/1M	+20% vs Baseline
EU (Stockholm)`eu-north-1`	$0.36/1M	$1.32/1M	—/1M	$0.36/1M	+20% vs Baseline
South America (Sao Paulo)`sa-east-1`	$1.26/1M	$2.64/1M	—/1M	$0.36/1M	+320% vs Baseline
US East (Ohio)`us-east-2`	$1.05/1M	$1.10/1M	—/1M	$0.30/1M	+250% vs Baseline

Developer Quickstart

Invoke GLM 4.7 via Amazon Bedrock Converse API

Python (boto3) · Amazon Bedrock Runtime

import boto3

# Amazon Bedrock Converse API invocation
client = boto3.client("bedrock-runtime", region_name="us-east-1")

response = client.converse(
    modelId="zhipu-ai.glm-4-7-v1:0",
    messages=[
        {
            "role": "user",
            "content": [{"text": "Summarize key features and cost levers of GLM 4.7."}]
        }
    ],
    inferenceConfig={
        "maxTokens": 1024,
        "temperature": 0.7
    }
)

output_text = response["output"]["message"]["content"][0]["text"]
usage = response["usage"]
print(f"Response: {output_text}")
print(f"Usage: {usage['inputTokens']} in, {usage['outputTokens']} out")