cloudflare:zhipu/glm-5.3-flash
Common Name: GLM-5.3-Flash
Z.ai's multimodal GLM-5.3 model for fast reasoning and visual coding workloads.
Specifications
Context
1048.6K
Maximum Output
131.1K
Inputtext, image
Outputtext
Performance (7-day Average)
Collecting…
Collecting…
Collecting…
Availability Trend (24h)
Pricing
Input$0.165/MTokens
Cached Input$0.033/MTokens
Output$0.55/MTokens
Performance Metrics (24h)
Similar Models
$1.54/$4.84/M
ctx1.0Mmax131Kavail—tps—
InOutCap
Z.ai's flagship reasoning model with a 1M-token context window and controllable thinking length.
$0.09/$0.45/M-10%
ctx1.1Mmax128Kavail—tps—
InOutCap
GPT-6 Luna is OpenAI's efficient GPT-6 model for high-volume workloads such as extraction, summarization, and request routing, succeeding GPT-5.6 Luna.
$0.09/$0.45/M-10%
ctx1.1Mmax128Kavail—tps—
InOutCap
GPT-6 Luna is OpenAI's efficient GPT-6 model for high-volume workloads such as extraction, summarization, and request routing, succeeding GPT-5.6 Luna.
$0.11/Free/M
ctx1.1Mmax—avail—tps—
InOut
GPT-6 Luna served through OpenAI's Decisions API (POST /v1/decisions). Evaluates text or image input against typed questions (predicate / choice / score) and returns typed answers with probabilities instead of generated text.