xAI: Grok 4.5
xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk
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.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| tokenstatcheapestxai/grok-4.5 | xAI | $2 | $6 | $0.3 | 1M |
| tokenstatcursor/cursor-grok-4.5 | Cursor | $2 | $6 | $0.3 | 500K |
| models.devxai/grok-4.5 | Cloudflare | $2 | $6 | $0.3 | 500K |
| models.devxai/grok-4.5 | CommandCode | $2 | $6 | $0.5 | 500K |
| models.devxai/grok-4.5 | Eden AI | $2 | $6 | $0.3 | 500K |
| models.devxai/grok-4.5 | Impossibl | $2 | $6 | $0.3 | 500K |
| models.devxai/grok-4-5 | LLM Gateway | $2 | $6 | $0.3 | 500K |
| models.devxai/grok-4.5 | Merge Gateway | $2 | $6 | $0.5 | 500K |
| models.devxai/grok-4.5 | Perplexity | $2 | $6 | $0.3 | 500K |
| models.devxai/grok-4.5 | Tempr Gateway | $2 | $6 | $0.3 | 500K |
| models.devgrok-4.5 | xAI | $2 | $6 | $0.3 | 500K |
| models.devgrok-4.5 | 302.AI | $2 | $6 | $0.5 | 500K |
| models.devgrok-4.5 | Abacus | $2 | $6 | $0.3 | 500K |
| models.devgrok-4.5 | DaoXE | $2 | $6 | $0.5 | 500K |
| models.devgrok-4.5 | GitHub Copilot | $2 | $6 | $0.5 | 500K |
| models.devgrok-4-5 | DevPass (LLM Gateway) | $2 | $6 | $0.3 | 500K |
| models.devgrok-4.5 | OpenCode | $2 | $6 | $0.3 | 500K |
| models.devgrok-4.5 | Opper | $2 | $6 | $0.5 | 500K |
| models.devgrok-4.5 | Requesty | $2 | $6 | $0.5 | 500K |
| models.devx-ai/grok-4.5 | CrossModel | $2 | $6 | $0.3 | 500K |
| models.devx-ai/grok-4.5 | Kilo Gateway | $2 | $6 | $0.3 | 500K |
| models.devx-ai/grok-4.5 | NanoGPT | $2 | $6 | $0.3 | 500K |
| models.devx-ai/grok-4.5 | Ofox | $2 | $6 | $0.3 | 500K |
| OpenRouterx-ai/grok-4.5 | OpenRouter | $2 | $6 | $0.3 | 500K |
| models.devx-ai/grok-4.5 | ZenMux | $2 | $6 | $0.5 | 500K |
| models.devgrok/grok-4.5 | OrcaRouter | $2 | $6 | $0.3 | 500K |
| models.devspacexai/grok-4.5 | Vercel AI Gateway | $2 | $6 | $0.3 | 500K |
| LiteLLMgrok-4.5 | N/A | $2 | $6 | $0.3 | N/A |
| LiteLLMperplexity/xai/grok-4.5 | N/A | $2 | $6 | $0.3 | N/A |
| LiteLLMcursor/cursor-grok-4.5 | N/A | $2 | $6 | $0.3 | N/A |
| LiteLLMcursor-grok-4.5 | N/A | $2 | $6 | $0.3 | N/A |
| models.devgrok-4.5 | AIHubMix | $2.20 | $6.60 | $0.55 | 500K |
| models.devgrok-4-5 | Venice AI | $2.27 | $6.80 | $0.34 | 500K |
| models.devgrok-4-5 | Kenari | $2.29 | $6.86 | $0.3429 | 500K |
| LiteLLMkyma/grok-4.5 | N/A | $2.73 | $8.19 | $0.273 | 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 intelligence38.8i
- AA coding72.4i
- AA agentic41.2i
- DeepSWE v1.153i
- Terminal Bench 2.183.3i
- SWE-Bench Pro64.7i
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.