xAI: Grok 4.6
xAI's frontier model for long-running agents, coding, knowledge work, and visual projects
Price changes
Cheapest list input/output only. Rates move rarely, so this is an event log. Down means cheaper. Showing the 8 latest changes.
- ↑ higherInput $1.25 → $2
- ↓ lowerInput $2 → $1.25
Sources
Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number. Free/$0 listings are hidden by default (1 omitted). Show free/$0 listings.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| tokenstatcheapestcursor/cursor-grok-4.6 | Cursor | $2 | $6 | $0.5 | 500K |
| models.devxai/grok-4.6 | Cloudflare | $2 | $6 | $0.5 | 500K |
| models.devxai/grok-4.6 | Eden AI | $2 | $6 | $0.5 | 500K |
| models.devxai/grok-4.6 | Google Vertex AI | $2 | $6 | $0.5 | 524K |
| models.devvertex-openai/grok-4-6 | LLM Gateway | $2 | $6 | $0.5 | 500K |
| models.devxai/grok-4.6 | Merge Gateway | $2 | $6 | $0.5 | 500K |
| models.devxai/grok-4.6 | Perplexity | $2 | $6 | $0.5 | 500K |
| models.devxai/grok-4.6 | Tempr Gateway | $2 | $6 | $0.5 | 500K |
| models.devgrok-4.6 | xAI | $2 | $6 | $0.5 | 500K |
| models.devgrok-4.6 | 302.AI | $2 | $6 | $0 | 500K |
| models.devgrok-4.6 | Abacus | $2 | $6 | $0.5 | 500K |
| models.devgrok-4.6 | AIHubMix | $2 | $6 | $0.5 | 500K |
| models.devgrok-4.6 | Azure | $2 | $6 | $0.5 | 200K |
| models.devgrok-4.6 | GitHub Copilot | $2 | $6 | $0.5 | 500K |
| models.devgrok-4-6 | DevPass (LLM Gateway) | $2 | $6 | $0.5 | 500K |
| models.devgrok-4-6 | Neon | $2 | $6 | $0.5 | 500K |
| models.devgrok-4.6 | OpenCode Go | $2 | $6 | $0.5 | 500K |
| models.devgrok-4.6 | OpenCode Zen | $2 | $6 | $0.5 | 500K |
| models.devgrok-4.6 | Opper | $2 | $6 | $0.5 | 500K |
| models.devgrok-4.6 | Requesty | $2 | $6 | $0.5 | 500K |
| models.devglobal.xai.grok-4.6 | Amazon Bedrock | $2 | $6 | $0.5 | 500K |
| models.devxai.grok-4.6 | OCI Generative AI | $2 | $6 | $0.5 | 500K |
| models.devx-ai/grok-4.6 | CrossModel | $2 | $6 | $0.5 | 500K |
| models.devx-ai/grok-4.6 | Kilo Gateway | $2 | $6 | $0.5 | 500K |
| models.devx-ai/grok-4.6 | NanoGPT | $2 | $6 | $0.5 | 500K |
| models.devx-ai/grok-4.6 | Ofox | $2 | $6 | $0.5 | 500K |
| OpenRouterx-ai/grok-4.6 | OpenRouter | $2 | $6 | $0.5 | 500K |
| models.devx-ai/grok-4.6 | ZenMux | $2 | $6 | $0.5 | 500K |
| models.devgrok/grok-4.6 | OrcaRouter | $2 | $6 | $0.5 | 500K |
| models.devspacexai/grok-4.6 | Vercel AI Gateway | $2 | $6 | $0.5 | 500K |
| LiteLLMgrok-4.6 | N/A | $2 | $6 | $0.5 | N/A |
| LiteLLMglobal.xai.grok-4.6 | N/A | $2 | $6 | $0.5 | N/A |
| LiteLLMazure_ai/grok-4.6 | N/A | $2 | $6 | $0.5 | N/A |
| LiteLLMperplexity/xai/grok-4.6 | N/A | $2 | $6 | $0.5 | N/A |
| LiteLLMvertex_ai/xai/grok-4.6 | N/A | $2 | $6 | $0.5 | N/A |
| LiteLLMcursor/cursor-grok-4.6 | N/A | $2 | $6 | $0.5 | N/A |
| LiteLLMcursor-grok-4.6 | N/A | $2 | $6 | $0.5 | N/A |
| models.devus.xai.grok-4.6 | Amazon Bedrock | $2.20 | $6.60 | $0.55 | 500K |
| models.devxai.grok-4.6 | Amazon Bedrock | $2.20 | $6.60 | $0.55 | 500K |
| LiteLLMus.xai.grok-4.6 | N/A | $2.20 | $6.60 | $0.55 | N/A |
| LiteLLMxai.grok-4.6 | N/A | $2.20 | $6.60 | $0.55 | N/A |
| LiteLLMbedrock_mantle/xai.grok-4.6 | N/A | $2.20 | $6.60 | $0.55 | N/A |
| models.devgrok-4-6 | Venice AI | $2.27 | $6.80 | $0.57 | 500K |
| LiteLLMdatabricks-grok-4-6 | N/A | $2.50 | $7.50 | $0.625 | N/A |
| LiteLLMdatabricks/databricks-grok-4-6 | N/A | $2.50 | $7.50 | $0.625 | N/A |
| LiteLLMbedrock_mantle/us-gov-east-1/xai.grok-4.6 | N/A | $2.64 | $7.92 | $0.66 | N/A |
| LiteLLMus-gov-east-1/xai.grok-4.6 | N/A | $2.64 | $7.92 | $0.66 | N/A |
| LiteLLMus-gov-west-1/xai.grok-4.6 | N/A | $2.64 | $7.92 | $0.66 | N/A |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Attachments
- In: text
- In: image
- In: pdf
- In: file
- Out: text
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.
- AA intelligence44.3i
- AA coding76.8i
- AA agentic53i
- GDPVal-AA v21753i
- CursorBench v3.269.9i
- DeepSWE v1.165.9i
- FrontierCode v1.1 (Extended)61.3i
- APEX-Agents57.5i
- Terminal-Bench v3.026i
- APEX-SWE56.4i
- AA-Briefcase1577i
- Harvey LAB (Vals)15.8i
Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.
See what this model costs you
The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.