SpaceXAI
Grok 4.7
Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks and verifying its own work.
grok-4.7Catalog preview. Paid requests for this model are not enabled yet.
Pricing
~98%USD. No uRouter markup. Live prices can change.
- Input
- $0.041321 / 1,000,000 tokens
- Output
- $0.123964 / 1,000,000 tokens
- Cache read
- $0.01033 / 1,000,000 tokens
- Cache write
- $0.041321 / 1,000,000 tokens
Model details
- Input
- text, image, file
- Output
- text
- Context window
- 500,000 tokens
- Maximum output
- 250,000 tokens
- Availability
- $1.4KUncapped capacity
- Updated
- 11/8/2026, 1:49:20 AM UTC
Capacity is reserved when your request is accepted.
Price history
Observed best prices · Last 24 hours · UTC
$0.041321/ 1,000,000 tokens
Capabilities
chatstreamingweb searchvisiontoolsreasoningjson mode
Supported parameters
include_reasoninglogprobsmax_tokensreasoningreasoning_effortresponse_formatseedstructured_outputstemperaturetool_choicetoolstop_logprobstop_pListed capabilities describe the model. uRouter execution support is verified separately.