Prices per 1M tokens.

API prices by model
ModelInputCache readOutputCapability (Epoch AI)
grok-4.3 (prompts <200K tokens)$1.25$0.20$2.50Capable · 149.9

Rates, billing conditions and sources

grok-4.3

Model ID: grok-4.3 · Context window: 1M tokens

All rates, conditions and sources

Conditions of every rate below:

  • xAI API standard price on the global endpoint ("Text API Pricing"), USD per 1M tokens. Batch API discounts, Priority Processing (2x), the US regional endpoint (1.1x), Grok 4.7 Fast, server-side tool invocations, Imagine, Voice, and files and collections storage are out of scope.
  • The table's Context column lists 1M for grok-4.3; quoted from the pricing page, not asserted as the offer's context window.

Input: $1.25 per 1M tokens · Standard tier · Prompts <200K tokens · Region: global · Global endpoint

  • Model ID grok-4.3; prompt-length price row "grok-4.3 (< 200k prompt tokens)". The source states: "Models listed with two rows use long context pricing: requests whose prompt reaches the listed token threshold are billed at the higher rate for all tokens in the request."
  • Input tokens ("Input / 1M tokens").

Cache read: $0.20 per 1M tokens · Standard tier · Prompts <200K tokens · Region: global · Global endpoint

  • Model ID grok-4.3; prompt-length price row "grok-4.3 (< 200k prompt tokens)". The source states: "Models listed with two rows use long context pricing: requests whose prompt reaches the listed token threshold are billed at the higher rate for all tokens in the request."
  • Prompt tokens served from cache ("Cached input / 1M tokens"). The source states no cache-write price or cache TTL.

Output: $2.50 per 1M tokens · Standard tier · Prompts <200K tokens · Region: global · Global endpoint

  • Model ID grok-4.3; prompt-length price row "grok-4.3 (< 200k prompt tokens)". The source states: "Models listed with two rows use long context pricing: requests whose prompt reaches the listed token threshold are billed at the higher rate for all tokens in the request."
  • Output tokens ("Output / 1M tokens"). The source lists reasoning tokens as a billed token type but does not say which column prices them.

Input: $2.50 per 1M tokens · Standard tier · Prompts ≥200K tokens · Region: global · Global endpoint

  • Model ID grok-4.3; prompt-length price row "grok-4.3 (≥ 200k prompt tokens)". The source states: "Models listed with two rows use long context pricing: requests whose prompt reaches the listed token threshold are billed at the higher rate for all tokens in the request."
  • Input tokens ("Input / 1M tokens").

Cache read: $0.40 per 1M tokens · Standard tier · Prompts ≥200K tokens · Region: global · Global endpoint

  • Model ID grok-4.3; prompt-length price row "grok-4.3 (≥ 200k prompt tokens)". The source states: "Models listed with two rows use long context pricing: requests whose prompt reaches the listed token threshold are billed at the higher rate for all tokens in the request."
  • Prompt tokens served from cache ("Cached input / 1M tokens"). The source states no cache-write price or cache TTL.

Output: $5.00 per 1M tokens · Standard tier · Prompts ≥200K tokens · Region: global · Global endpoint

  • Model ID grok-4.3; prompt-length price row "grok-4.3 (≥ 200k prompt tokens)". The source states: "Models listed with two rows use long context pricing: requests whose prompt reaches the listed token threshold are billed at the higher rate for all tokens in the request."
  • Output tokens ("Output / 1M tokens"). The source lists reasoning tokens as a billed token type but does not say which column prices them.

Capability (Epoch AI): ECI 149.9 (90% range 147.9–151.9) · range spans bands · Epoch AI score for Grok 4.3 Beta, model dated Apr 17, 2026

Price observed:

API availability: listed as available when checked (not a live service check)

Collection record

Primary source ↗ · provider documentation · Claims: xai-grok-4-3: specifications · Retrieved · Checked · Reviewed · Freshness: unknown · Confidence: A

  • Official xAI models page (markdown), "Text API Pricing" table, "Context" column for grok-4.3, raw SHA-256 245e47205ea068e933131ca9f604ef50f74db6d204bb5793fab73c140545f1f7: "| grok-4.3 (< 200k prompt tokens) | 1M |".
  • Visible shorthand recorded as stated (#504); not converted to an exact token count.
  • Specifications only: no pricing, availability, capability or release-date assertion.

Primary source ↗ · provider documentation · Claims: xai-grok-4-3: pricing · xai-grok-4-3: availability · 12 more claims about 6 other catalog entries · Retrieved · Checked · Review due · Confidence: A

  • Raw SHA-256: 0b43e5abe317859bc78937b9dca6093f5ff9ee03832d5fb131955b337e1c42ed; collector xai-markdown-1.
  • Pricing and listing observation only; no checkpoint, license, context-window, modality or release-date assertions. API models are not linked to downloadable checkpoints.
  • The source states that model access might vary by geographical location and account limitations; no account or regional eligibility claim.
About capability scores (Epoch AI)

Capability scores: Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks' [online resource], epoch.ai/benchmarks. Accessed Nov 18, 2026. Licensed CC BY 4.0; values here are rounded to one decimal place and grouped into bands.

The Epoch Capabilities Index (ECI) combines many benchmarks on a scale where Claude 3.5 Sonnet is 130 and GPT-5 is 150. Bands, on the displayed one-decimal score: Frontier 160+, Strong 150–159.9, Capable 140–149.9, Entry below 140. Each score has a 90% range, listed with each model's rates and sources; a range that crosses a band boundary is flagged there. Models are not ranked: neighbouring scores often overlap.

A benchmark is not your workload. Epoch's scores mostly reflect runs at the highest reasoning effort, which use more output tokens than default settings. Scores are dated and can shift between Epoch releases. A score belongs to the developer's model; a host listing shows the same model's score, but hosts may serve different versions or quantizations.

How headline rates are chosen

Headline rates use the directory's shared rule: the rate a buyer meets by default, chosen by billing, tier and context dimensions and never by price. Context caps, the bracket starting at zero and short-context variants are labeled. Every price is a listed price, not a service guarantee; each offer's details say what its source states about availability. Batch, off-peak and other variants remain in the details; where no single rate is the default, the table shows a dash.

No currency conversion is performed. Missing cache prices are unknown, not zero. Equal units do not establish equivalent models or service conditions. See the methodology and source register.