Grok 4.6
xAI's flagship reasoning model for long-running agents and interactive visual work.
- Input price
- $2.20
- Output price
- $6.60
- Context
- 500K
- Max output
- 128K
- Capability
- 158 (#28 of 82)
- Human preference
- 1430
- 30-day uptime
- —
- Knowledge cutoff
- 2026-02-01
InputTextImageOutputText
Providers
Providers that serve this model. With Auto, each request goes to the best available provider. Prices in USD per 1M tokens; stats cover the last 30 days.
Pricing
All prices for this model, by service tier.
Prompt ≤ 200K tokens
- Input
- $2.20
- per 1M tokens
- Output
- $6.60
- per 1M tokens
- Cache read
- $0.55
- per 1M tokens
- Reasoning output
- $6.60
- per 1M tokens
- Web search
- $0.0055
- per request
Prompt > 200K tokens
- Input
- $4.40
- per 1M tokens
- Output
- $13.20
- per 1M tokens
- Cache read
- $1.10
- per 1M tokens
- Reasoning output
- $13.20
- per 1M tokens
- Web search
- $0.0055
- per request
Estimated cost of common use (500 output tokens each)
- One chat message
- $0.0099
- 3K input tokens
- Agent first turn
- $0.223
- 100K tokens of context, none cached
- Each later agent turn
- $0.0627
- context read from cache, plus 2K new tokens
- 20-turn agent task
- $1.41
- first turn plus 19 more
Try it
Runs on your balance and is billed like any API request.
Similar models
Other models with the same output types at a similar price.
Human preference ratings are from the LMArena Text Arena (CC BY 4.0, as of 2026-11-18): Elo ratings from blind votes, on a different scale from capability scores. lmarena.ai/leaderboard/text