Compare the listed model data for GLM-4.7 by Zhipu AI and GLM-4.7 FP8 by Zhipu AI. Benchmark and pricing records are not a controlled test and may change.
Data last updated: 2026-10-16. Verify current model details with each provider.
What the listed data says
LITHOVEX lists GLM-4.7 at 128K tokens and GLM-4.7 FP8 at a large context window. Check provider documentation for current specifications. GLM-4.7 is listed for no specific capability flags; GLM-4.7 FP8 is listed for no specific capability flags. Shared catalog benchmark entries: CMMLU: GLM-4.7 84.3%; GLM-4.7 FP8 83.9%; MMLU: GLM-4.7 80.7%; GLM-4.7 FP8 80.2%. These records are reference data, not a controlled head-to-head test; verify current pricing and specifications with each provider.
Catalog source links
Use these model and provider links to verify current specifications, pricing, and availability.
A context-window ratio cannot be calculated from the catalog values (128K tokens for GLM-4.7; a large context window for GLM-4.7 FP8).
On shared numeric benchmark entries, CMMLU: GLM-4.7 − GLM-4.7 FP8 = +0.4 percentage points (84.3% vs 83.9%); MMLU: GLM-4.7 − GLM-4.7 FP8 = +0.5 percentage points (80.7% vs 80.2%).
A release-date gap cannot be calculated from the catalog values (GLM-4.7: 2025; GLM-4.7 FP8: 2025).
Cost example: 1M input and 1M output tokens
Using only the catalog's listed per-million-token rates, 1M input plus 1M output tokens costs about $0.9 for GLM-4.7 and $0.6 for GLM-4.7 FP8. This excludes provider-specific discounts, caching, and other fees.
Choose GLM-4.7 if…
Choose GLM-4.7 when your task aligns with catalog-listed uses or strengths such as Production Chinese-English enterprise deployment with latest GLM quality, GLM-4.7 — most recent stable GLM generation, Best overall Chinese-English performance in GLM 4.x line, Apache 2.0.
Choose GLM-4.7 FP8 if…
Choose GLM-4.7 FP8 when your task aligns with catalog-listed uses or strengths such as Efficient production GLM-4.7 deployment, GLM-4.7 quality at FP8 efficiency — reduced VRAM requirement.
Catalog specifications for GLM-4.7 and GLM-4.7 FP8
Specification
GLM-4.7
GLM-4.7 FP8
Provider
Zhipu AI
Zhipu AI
Parameters
32B
Not listed
Context window
128K tokens
Not listed
Maximum output
Not listed
Not listed
Catalog pricing
Apache 2.0 — free
Apache 2.0 — free
Listed input/output cost per 1M tokens
input $0.3, output $0.6 per 1M tokens
input $0.2, output $0.4 per 1M tokens
License
Apache 2.0
Apache 2.0
Coding support
Not listed
Not listed
Reasoning support
Not listed
Not listed
Vision input
Not listed
Not listed
Multimodal
Not listed
Not listed
Open weights
Yes
Yes
Benchmark: CMMLU
84.3%
83.9%
Benchmark: MMLU
80.7%
80.2%
Figures are transcribed from LITHOVEX model records. Benchmark versions and evaluation setups may differ; pricing and specifications can change. Check each provider's current documentation before making a decision.
Frequently Asked Questions
What is different between GLM-4.7 and GLM-4.7 FP8?
LITHOVEX lists GLM-4.7 at 128K tokens and GLM-4.7 FP8 at a large context window. Check provider documentation for current specifications. GLM-4.7 is listed for no specific capability flags; GLM-4.7 FP8 is listed for no specific capability flags. Shared catalog benchmark entries: CMMLU: GLM-4.7 84.3%; GLM-4.7 FP8 83.9%; MMLU: GLM-4.7 80.7%; GLM-4.7 FP8 80.2%. These records are reference data, not a controlled head-to-head test; verify current pricing and specifications with each provider.
What benchmark values are listed for GLM-4.7 and GLM-4.7 FP8?
CMMLU: GLM-4.7 84.3%; GLM-4.7 FP8 83.9%; MMLU: GLM-4.7 80.7%; GLM-4.7 FP8 80.2%. The catalog values may use different versions and evaluation setups, so they are reference points rather than a controlled head-to-head result.
Which model has the larger listed context window?
LITHOVEX lists GLM-4.7 at 128K tokens and GLM-4.7 FP8 at a large context window. Check provider documentation for current specifications.
What are the listed costs per million tokens for GLM-4.7 and GLM-4.7 FP8?
GLM-4.7: input $0.3, output $0.6 per 1M tokens (Apache 2.0 — free). GLM-4.7 FP8: input $0.2, output $0.4 per 1M tokens (Apache 2.0 — free). Where separate numeric input and output rates are available, the worked example uses 1M input plus 1M output tokens. Confirm current terms with each provider.
How far apart are the listed release dates for GLM-4.7 and GLM-4.7 FP8?
The catalog lists GLM-4.7 as 2025 and GLM-4.7 FP8 as 2025; a release-date gap cannot be calculated from both records.
When was the comparison data last updated?
The model catalog records 2026-10-16 as its data update date. Provider specifications and prices may have changed since then.
How should I choose between GLM-4.7 and GLM-4.7 FP8?
Compare the listed specifications and capabilities, review the benchmark notes, then test both with the same representative prompt for your task. This page does not claim a universal winner.