Z.ai: GLM 5.3 FlashX

Z.AI

zai/glm-5.3-flashx

GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and linear attention architecture...

Context

1.048576M

Input /1M

$0.37

Output /1M

$1.25

Latency (TTFT)

1,683ms

Pricing

Per 1M tokens, in USD

Input$0.37

Output$1.25

Cache read$0.09

Specs

text inimage invideo intext out

TokenizerOther

Max output tokens131,072

Supported parameters

include_reasoningmax_tokensreasoningreasoning_effortresponse_formattemperaturetool_choicetoolstop_ktop_p

Where it ranks on price

Against 165 routable models

Input$0.37

Cheaper than 64% of routable models

Output$1.25

Cheaper than 74% of routable models

Benchmarks

No third-party benchmark data available for this model yet.

Call this model

Swap in your Mizan key — the request/response bodies are OpenAI chat-completion shaped.

cURL

curl https://api.app-mizan.com/v1/chat/completions \
  -H "Authorization: Bearer mizan_rt_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zai/glm-5.3-flashx",
    "messages": [{ "role": "user", "content": "Say hi in five words." }]
  }'

Models

Z.ai: GLM 5.3 FlashX

Z.AI

zai/glm-5.3-flashx

GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and linear attention architecture...

Context

1.048576M

Input /1M

$0.37

Output /1M

$1.25

Latency (TTFT)

1,683ms

Pricing

Per 1M tokens, in USD

Input$0.37

Output$1.25

Cache read$0.09

Specs

text inimage invideo intext out

TokenizerOther

Max output tokens131,072

Supported parameters

include_reasoningmax_tokensreasoningreasoning_effortresponse_formattemperaturetool_choicetoolstop_ktop_p

Where it ranks on price

Against 165 routable models

Input$0.37

Cheaper than 64% of routable models

Output$1.25

Cheaper than 74% of routable models

Benchmarks

No third-party benchmark data available for this model yet.

Call this model

Swap in your Mizan key — the request/response bodies are OpenAI chat-completion shaped.

cURL

curl https://api.app-mizan.com/v1/chat/completions \
  -H "Authorization: Bearer mizan_rt_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zai/glm-5.3-flashx",
    "messages": [{ "role": "user", "content": "Say hi in five words." }]
  }'