glm-5.3-flash in the catalog and in GET /v1/models, sent as model; its current version is glm-5.3-flash-1. Its page on the site, with its rate history: Z.ai: GLM 5.3 Flash. GLM 5.3 Flash is a fast, efficient hybrid-architecture model from Z.ai combining attention layers with linear-attention (KDA) layers for high-throughput serving. It supports text and image input with a 1M-token context window, and is suited for coding, agent workflows, and high-volume tool use.Reasoning is supported and enabled by default.
Fig. 1, sheet 06Model and task guides
What it takes and returns
Field
Value
Type and task
language, task chat
License and usage conditions
mit
Field
Type and task
Value
language, task chat
Field
License and usage conditions
Value
mit
Limits
Limit
Value
context_tokens
1,048,576
max_output_tokens
131,072
Limit
context_tokens
Value
1,048,576
Limit
max_output_tokens
Value
131,072
Pools
Pool
Lanes
Precision
Certified pool
Shared
fp4
Pool
Certified pool
Lanes
Shared
Precision
fp4
Rates
On demand, in US dollars per million tokens
Pool
Input
Cached input
Output
Certified pool
$0.105
Billed as input
$0.70
Pool
Certified pool
Input
$0.105
Cached input
Billed as input
Output
$0.70
Request parameters
In the Certified pool it takes frequency_penalty, presence_penalty, seed, stop, temperature, tools and top_p. A request carrying any other parameter is answered 400 unsupported_parameter, its param naming it, and nothing is charged (Request parameters).
Always taken as well: model, messages, stream, stream_options, max_tokens, max_completion_tokens, user, metadata, safety_identifier, store and prompt_cache_key and the hips object.