Model specifications
- Context
- 500,000 tokens
- Maximum output
- 450,000 tokens
- Architecture
- text+image+file->text
- Tokenizer
- Grok
- Knowledge cutoff
- Not provided
- Moderated
- No
Complete pricing
Synchronized OpenRouter rates. Token prices are shown per one million tokens.
- Input
- $2 per 1M tokens
- ≤200K$2
- >200K$4
- Output
- $6 per 1M tokens
- ≤200K$6
- >200K$12
- Cache read
- $0.5 per 1M tokens
- ≤200K$0.5
- >200K$1
- Web search
- $5 per 1,000 calls
Model configuration
Reasoning
- Reasoning required
- Yes
- Default parameters
- high
- Capabilities
- xhigh, high, medium, low
Quick start
Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.
curl --fail-with-body https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"x-ai/grok-4.6","messages":[{"role":"user","content":"Hello!"}]}'Input → Output
Yes · xhigh · high · medium · low
Supported API parameters
include_reasoninglogprobsmax_tokensreasoningreasoning_effortresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p5 providers
Checked: September 21, 2026
Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.
xAI
Not provided- Context
- 500K
- Maximum output
- 450K
- Input
- $2
- Output
- $6
- Cache read
- $0.5
- Cache write
- Not provided
xAI
Not provided- Context
- 500K
- Maximum output
- 450K
- Input
- $2
- Output
- $6
- Cache read
- $0.5
- Cache write
- Not provided
Amazon Bedrock
Not provided- Context
- 500K
- Maximum output
- 450K
- Input
- $2.2
- Output
- $6.6
- Cache read
- $0.55
- Cache write
- Free
xAI
Not provided- Context
- 500K
- Maximum output
- 450K
- Input
- $4
- Output
- $12
- Cache read
- $1
- Cache write
- Not provided
xAI
Not provided- Context
- 500K
- Maximum output
- 450K
- Input
- $4
- Output
- $12
- Cache read
- $1
- Cache write
- Not provided