SpaceXAI: Grok 4.3

xAI (Grok)

grok/grok-4.3

Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...

Context

1M

Input /1M

$1.25

Output /1M

$2.50

Latency (TTFT)

675ms

Pricing

Per 1M tokens, in USD

Input$1.25

Output$2.50

Cache read$0.20

Specs

text inimage infile intext out

TokenizerGrok

Max output tokens900,000

Supported parameters

include_reasoninglogprobsmax_tokensreasoningreasoning_effortresponse_formatseedstructured_outputstemperaturetool_choicetoolstop_logprobstop_p

Where it ranks on price

Against 157 routable models

Input$1.25

Cheaper than 30% of routable models

Output$2.50

Cheaper than 46% of routable models

Benchmarks

Intelligence25.4

Coding42.2

Agentic17.2

Composite scores (0–100) from Artificial Analysis, via OpenRouter's model catalog.

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": "grok/grok-4.3",
    "messages": [{ "role": "user", "content": "Say hi in five words." }]
  }'

Models

SpaceXAI: Grok 4.3

xAI (Grok)

grok/grok-4.3

Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...

Context

1M

Input /1M

$1.25

Output /1M

$2.50

Latency (TTFT)

675ms

Pricing

Per 1M tokens, in USD

Input$1.25

Output$2.50

Cache read$0.20

Specs

text inimage infile intext out

TokenizerGrok

Max output tokens900,000

Supported parameters

include_reasoninglogprobsmax_tokensreasoningreasoning_effortresponse_formatseedstructured_outputstemperaturetool_choicetoolstop_logprobstop_p

Where it ranks on price

Against 157 routable models

Input$1.25

Cheaper than 30% of routable models

Output$2.50

Cheaper than 46% of routable models

Benchmarks

Intelligence25.4

Coding42.2

Agentic17.2

Composite scores (0–100) from Artificial Analysis, via OpenRouter's model catalog.

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": "grok/grok-4.3",
    "messages": [{ "role": "user", "content": "Say hi in five words." }]
  }'