Capabilities
7-day heat trend
−31.3%Pricing breakdown
Typical 3:1 output-to-input mix, per 1M tokens
Estimated monthly cost by workload
Market position
- Cheaper than 9% of tracked models
- Faster than 0% of tracked models
- Efficiency rank: #60 of 1105
Best suited for
General-purpose text generation, chat, summarization and content workloads where broad capability and low cost matter most.
About xai/grok-4.3
Vercel AI Gateway route for Grok 4.3, preserving routed reasoning-model metadata and fallback controls.
xai/grok-4.3 is a Text model from Vercel AI Gateway (US). HotON.ai tracks it at $1.25 per 1M input tokens and $2.50 per 1M output tokens, with a 1000K-token context window, ~118 tokens/sec throughput and 97.4% availability. Its composite efficiency score is 95/100 at an estimated $0.004 per successful task.
Compare xai/grok-4.3
Related market news
Frequently asked questions
How much does xai/grok-4.3 cost per 1M tokens?+
xai/grok-4.3 is tracked at $1.25 per 1M input tokens and $2.50 per 1M output tokens. A typical 3:1 output-to-input workload blends to roughly $2.19 per 1M tokens. Figures are illustrative demo data.
What is xai/grok-4.3 best for?+
General-purpose text generation, chat, summarization and content workloads where broad capability and low cost matter most.
How fast is xai/grok-4.3?+
xai/grok-4.3 delivers about 118 tokens/sec with 97.4% tracked availability, suitable for latency-sensitive, real-time applications.
Is xai/grok-4.3 cheaper than other AI models?+
Within the HotON.ai tracked set, xai/grok-4.3 is cheaper than 9% of models on input price and ranks #60 of 1105 by overall efficiency.
Related models
Pricing is real (via the TestKey catalog, updated daily). Quality (Arena Elo) is real where the model is ranked on LMArena. Speed, availability and efficiency are modeled estimates.