GLM 4.7 API Pricing 2026

Compare pricing, benchmarks, and providers for GLM 4.7. Find the best value for your use case.

8 Ways to Use Fewer Tokens
Last updated: November 21, 2026 at 08:43 AM

Overview

GLM 4.7 was released on December 22, 2025. Pricing starts at $0.320 per million input tokens and $1.40 per million output tokens. The model supports a context window of up to 203K tokens. API access is available through Z-ai.

Context Window
203K
tokens
Pricing
Input$0.320
Output$1.40
Cached$0.064
per 1M tokens
Speed
Output-
TTFT-
median latency
Capabilities
ReasoningToolsCaching

GLM 4.7 is priced at $0.320 per million input tokens and $1.40 per million output tokens. It has a context window of 202,752 tokens. It is available from 8 providers, with DeepInfra the cheapest at $0.320 per million input tokens (input prices range from $0.320 to $0.700). Over the past ~90 days its cheapest input price has fallen 20%, from $0.400 to $0.320 per million tokens.

Pricing Comparison

Compare GLM 4.7 with 10 similar models by price.

Current Pricing (per 1M tokens)

11 models

Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Model
Input $/M
Output $/M
Coding
MMLU
GPQA
Context
Actions
$0.320
$1.400
—
—
—
202,752
Try
$0.300
$1.200
—
—
—
196,608
Try
$0.300
$1.200
—
—
—
196,608
Try
$0.300
$0.500
—
—
—
8,000
Try
$0.300
$0.300
—
—
—
6,144
Try
$0.300
$0.300
—
—
—
4,096
Try
$0.300
$0.300
—
—
—
4,096
Try
$0.300
$0.300
—
—
—
32,768
Try
$0.300
$2.500
—
—
83.8
1,048,576
Try
$0.300
$0.900
—
—
—
131,072
Try
$0.300
$2.500
—
—
—
-
Try

* Some models use tiered pricing based on prompt length. Displayed prices are for prompts ≤ 200k tokens.

Compare Providers

GLM 4.7 is available from multiple providers with different pricing and availability.

8
Providers
$0.320
Cheapest Input/M
$1.400
Cheapest Output/M
DeepInfra
Best Price

Provider Pricing

8 models

Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Input $/M
Output $/M
Cache Read $/M
Cache Write $/M
Uptime
DeepInfra
DeepInfra
Best Price
$0.320
$1.400
$0.064
-
-
$0.400
$1.750
$0.080
-
-
V
Venice
$0.400
$1.929
$0.080
-
100.0%
$0.450
$2.000
-
-
-
Z
Z.AI
$0.600
$2.200
$0.110
-
100.0%
$0.600
$2.200
-
-
-
$0.600
$2.200
$0.110
-
100.0%
M
Mancer 2
$0.700
$2.500
$0.350
-
100.0%
Provider pricing data sourced from OpenRouter and Helicone

Community Rankings

How does GLM 4.7 perform? Vote based on your experience.

Cost vs. Quality

Compare GLM 4.7's benchmark performance against all models.

X-axis:
Y-axis:
Loading chart...
Other models

Try GLM 4.7

Use our Calculator

Estimate your costs based on expected token usage.

Open Cost Calculator

Try in Playground

Test GLM 4.7 directly in your browser.

Open Playground

Frequently Asked Questions

GLM 4.7 costs $0.000320 per 1,000 input tokens and $0.001400 per 1,000 output tokens.
GLM 4.7 is available from 8 providers. DeepInfra offers the best price.
DeepInfra offers GLM 4.7 at $0.320 per million input tokens, the lowest of 8 providers (input prices range from $0.320 to $0.700 per million tokens).
Yes. Over the past ~90 days, the cheapest input price for GLM 4.7 has dropped 20%, from $0.400 to $0.320 per million tokens.
We compare GLM 4.7 with 10 similarly-priced models. See the benchmark scatter plot above to compare quality vs cost.

All Z-ai Models

See pricing for all Z-ai models.

View all Z-ai models →