CURRENT GROK1M CONTEXTPROMPT CACHINGCONFIGURABLE REASONING
Grok 4.3 API Pricing
xAI's current Grok API model for text and tool-calling workloads: $1.25/M input, $0.20/M cached input, and $2.50/M output. Pulled directly from docs.x.ai.
Input - per 1M tokens
$1.25/M
Current Grok 4.3 live
Output - per 1M tokens
$2.50/M
Reasoning tokens billed as output live
Cached input
$1.25/M
No separate cache row N/A
Effective - agentic blend
$1.35/M
92/8 split - 82% cache
§ 01 / TERMINAL
Run the numbers.
Live calculator pre-loaded with current Grok 4.3 rates. xAI lists $1.25/M input, $0.20/M cached input, and $2.50/M output on the pricing page.
$ /mo
Workload split
Prompt cache hit rate
Tokens you can process
—
Words equivalent (English)
—
Effective rate
—
§ 02 / SCENARIOS
Real-world presets.
AGENT
Tool-calling agent
$0.120/task
LONG CONTEXT
Research pack synthesis
$0.275/pack
CHAT
Power-user chat
$0.065/turn
RAG
Knowledge base RAG
$0.217/answer
§ 03 / TAPE
Price history.
Input · $1.3/M
Output · $2.5/M
Cached · $1.3/M
MAY 12 Listed as the current Grok 4.3 model in xAI docsMAY 18 Verified live on xAI pricing page
§ 04 / TOKENIZER
Paste text. See tokens. See cost.
Estimate · grok-tokenizer-estimate · ≈3.85 chars/token Auto-counts as you type
This is a chars-per-token approximation, not a real tokenizer. Actual tokens vary by language, code density, and tool-call overhead — counts are typically ±10–20% off for English prose, more for code or non-Latin scripts. For exact billing, use the vendor's official tokenizer.
Characters —
Words —
Tokens (estimated) —
Cost as input · uncached —
Cost as output · uncached —
Cost as cached input —
| Model | Input /M | Output /M | Effective blended | Context | Best for |
|---|---|---|---|---|---|
| Grok 4.3 Current | $1.25 | $2.50 | $1.35 agentic 92/8 | 1M | Current Grok API default |
| Gemini 2.5 Pro | $1.25 cache $0.13 | $10.00 | $1.10 Gemini Pro | 2M | Stable Google frontier |
| GPT-5.4 | $2.50 cache $0.25 | $15.00 | $1.80 OpenAI frontier | 1.05M | Affordable OpenAI frontier |
| Claude Sonnet 4.6 | $3.00 cache $0.30 | $15.00 | $1.92 Anthropic agent | 1M | Daily-driver Claude agents |
| DeepSeek V4 Pro | $0.43 cache $0.00 | $0.87 | $0.14 budget reasoning | 1M | Low-cost reasoning alternative |
| Gemini 2.5 Flash | $0.30 cache $0.03 | $2.50 | $0.27 budget Gemini | 1M | Low-cost multimodal work |
Frequently asked.
Grok 4.3 pricing questions, with xAI token rates separated from workload assumptions.
Q · 01 What is Grok 4.3's API price? +
xAI lists
grok-4.3 at $1.25/M input, $0.20/M cached input, and $2.50/M output. These are USD prices per 1M tokens.Q · 02 Does Grok 4.3 support prompt caching? +
Yes. The xAI pricing page lists cached input at
$0.20/M, versus $1.25/M for fresh input. This page uses an 82% cache-hit assumption only for the effective blend tile.Q · 03 What happened to older Grok slugs? +
xAI says several older model slugs retired on
2026-05-15 and now redirect to grok-4.3. Requests through those deprecated slugs are billed at Grok 4.3 pricing.Q · 04 Is Batch API cheaper? +
xAI says Batch API requests can receive
20%-50% off standard token rates depending on the model detail page. This page keeps the headline calculator on standard realtime rates.Q · 05 Are tool calls included in token pricing? +
No. xAI prices server-side tools separately, for example Web Search and X Search at
$5 / 1k calls. Token usage from those requests is still billed at the selected model rate.Q · 06 How accurate is the tokenizer estimate? +
The widget uses a GPT-class planning estimate of
4.875 characters per token. Exact xAI billing can vary with language, hidden reasoning tokens, tool use, and cached prompt boundaries.