GLM 4 7 on Cerebras · ComputeLlama

Provider model ID: zai-glm-4.7
Protocol: openai chat completions
Region: global
Status: active
Base URL: https://api.cerebras.ai/v1

Current offers

Price components

Exact source values; no hidden currency conversion or inferred effort surcharge.

Developer tieron demand

$5.00

input tokens$2.25per million tokens

output tokens$2.75per million tokens

Reasoning effortExact supported efforts unknownPublished unit rates apply to billed token components. Total cost varies with the actual billed input and output tokens.

Provider assertions

Claims

compatibility · openai

supported · 1 source assertion

Independent checks

Observations

independent observations · probes begin in Stage 2

Independent inference performance

Scenario and region observations

Full JSON history

No independent aggregates match these filters yet. Raw scheduled probes remain visible only after the first immutable aggregate snapshot is published.

Immutable record

Pricing history

Newest observed values first.

Latest detected revisionDeveloper tierCerebras Models and Pricing

First detectedAug 02, 2026, 07:55 PM UTCConfirmed through Aug 17, 2026, 02:54 PM UTC · 296 raw observations

Evidence snapshot Raw JSON audit

Latest change vs previous

Exact component-rate changes

Unit rates are source evidence. A reasoning effort can change billed token use, so total cost still requires the actual input and output token counts.

input tokens · per million tokens: $2.25First observed rate
output tokens · per million tokens: $2.75First observed rate

Aug 02, 2026, 07:55 PM UTCDeveloper tierCerebras Models and Pricing · on demand
27d210c8a4…
input tokens · per million tokens
$2.25First observed rate
output tokens · per million tokens
$2.75First observed rate
Revision observed 296 times from Aug 02, 2026, 07:55 PM UTC to Aug 17, 2026, 02:54 PM UTC.