xAI: Grok 4.3
xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk
Cheapest input
$1.25
$/MTok · models.dev
Cheapest output
$2.50
$/MTok
Context
1M
tokens
Offers
23
3 sources
Offers
Same model, different listings. First-party, 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 |
|---|---|---|---|---|---|
| models.devcheapestxai/grok-4.3 | Impossibl | $1.25 | $2.50 | $0.2 | 1M |
| models.devxai/grok-4.3 | Merge Gateway | $1.25 | $2.50 | $0.2 | 1M |
| models.devxai/grok-4.3 | Vercel AI Gateway | $1.25 | $2.50 | $0.2 | 1M |
| models.devgrok-4.3 | xAI | $1.25 | $2.50 | $0.2 | 1M |
| models.devgrok-4.3 | Abacus | $1.25 | $2.50 | $0.2 | 1M |
| models.devgrok-4.3 | AIHubMix | $1.25 | $2.50 | $0.2 | 1M |
| models.devgrok-4.3 | Auriko | $1.25 | $2.50 | $0.2 | 1M |
| models.devgrok-4.3 | DaoXE | $1.25 | $2.50 | $0.2 | 1M |
| models.devgrok-4-3 | FrogBot | $1.25 | $2.50 | $0.2 | 1M |
| models.devgrok-4-3 | LLM Gateway | $1.25 | $2.50 | $0.3125 | 1M |
| models.devxai.grok-4.3 | Amazon Bedrock | $1.25 | $2.50 | $0.2 | 1M |
| models.devx-ai/grok-4.3 | CrossModel | $1.25 | $2.50 | $0.2 | 1M |
| models.devx-ai/grok-4.3 | FastRouter | $1.25 | $2.50 | $0 | 1M |
| models.devx-ai/grok-4.3 | Kilo Gateway | $1.25 | $2.50 | $0.2 | 1M |
| models.devx-ai/grok-4.3 | NanoGPT | $1.25 | $2.50 | $0.2 | 1M |
| models.devx-ai/grok-4.3 | Ofox | $1.25 | $2.50 | $0.2 | 1M |
| OpenRouterx-ai/grok-4.3 | OpenRouter | $1.25 | $2.50 | $0.2 | 1M |
| models.devx-ai/grok-4.3 | ZenMux | $1.25 | $2.50 | $0.2 | 1M |
| models.devgrok/grok-4.3 | OrcaRouter | $1.25 | $2.50 | $0.2 | 1M |
| LiteLLMgrok-4.3 | — | $1.25 | $2.50 | $0.2 | — |
| LiteLLMxai.grok-4.3 | — | $1.25 | $2.50 | $0.2 | — |
| LiteLLMbedrock_mantle/xai.grok-4.3 | — | $1.25 | $2.50 | $0.2 | — |
| models.devgrok-4-3 | Venice AI | $1.42 | $2.83 | $0.23 | 1M |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Attachments
- In: text
- In: image
- In: pdf
- In: video
- In: file
- Out: text
Knowledge cutoff: 2024-11Released: 2026-04-17Family: grok
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.
- AA intelligence37.6
- AA coding42.2
- AA agentic24.1
Sources: Arena AI, Artificial Analysis. See /benchmarks.