BroadRouter

xAI API pricing

Updated

xAI lists standard prices for 8 models. The cheapest is Grok Build 0.1 at USD 1 input and USD 2 output per 1M tokens; the dearest is Grok 4.7 at USD 2 / USD 6. It publishes cached-input prices for all of them; batch, flex or priority pricing is published as a rule rather than per-model prices (see tiers below).

xAI is a model maker: 8 of the 8 models here are its own. By maker: xAI 8. 8 prices, each read from xAI's own pricing page, checked 2026-11-14. BroadRouter is BroadNet's own site and does not sell xAI's services. Automated re-check 2026-11-16: 8 of 8 prices still matched the provider's page.

Models with a standard price
8
Median input / output
USD 1.25 / USD 2.50
Cached-input prices
8 of 8
Cheapest host for
6 of 6 shared models

Which models is xAI the cheapest provider for?

Of the 6 models that xAI and at least one other provider both price at the standard tier, xAI has the lowest price for 6, ranked on a blend of 3 input tokens to 1 output token (all of them tied with another provider at the same price; the maker's own API is listed first on a tie). Another 2 models have a standard price from xAI only.

Models where xAI is the cheapest provider
ModelxAI input / outputNext cheapestSaving on 3:1 blendProviders
Grok 4.6USD 2 / USD 6GMI Cloud USD 2 / USD 6tie6
Grok 4.7USD 2 / USD 6GMI Cloud USD 2 / USD 6tie6
Grok 4.3USD 1.25 / USD 2.50Amazon Bedrock USD 1.25 / USD 2.50tie4
Grok 4.20 (reasoning)USD 1.25 / USD 2.50Google Vertex AI USD 1.25 / USD 2.50tie3
Grok 4.5USD 2 / USD 6GMI Cloud USD 2 / USD 6tie3
Grok 4.20 (non-reasoning)USD 1.25 / USD 2.50Google Vertex AI USD 1.25 / USD 2.50tie2

The 6 models xAI sells that the most other providers also sell, with xAI's rank among them on the 3:1 blend.

xAI on the most widely hosted models
ModelxAIRankCheapest
Grok 4.6USD 2 / USD 61 of 6xAI (this page)
Grok 4.7USD 2 / USD 61 of 6xAI (this page)
Grok 4.3USD 1.25 / USD 2.501 of 4xAI (this page)
Grok 4.20 (reasoning)USD 1.25 / USD 2.501 of 3xAI (this page)
Grok 4.5USD 2 / USD 61 of 3xAI (this page)
Grok 4.20 (non-reasoning)USD 1.25 / USD 2.501 of 2xAI (this page)

xAI price list

USD per 1M tokens: 8 prices for 8 models, one row per model with any other service tiers stacked under the standard price. Sources checked 2026-11-14 unless a row says otherwise. "vs maker" compares a standard price with the model maker's own API on the 3:1 blend; a minus means xAI is cheaper. xAI is the maker of every model here, so there is no maker price to compare with.

xAI API prices by model
ModelTierInputCachedOutputContextvs makerSource
Grok 4.20 (non-reasoning)standardUSD 1.25USD 0.20USD 2.501,000,000own modelsource
Grok 4.20 (reasoning)standardUSD 1.25USD 0.20USD 2.501,000,000own modelsource
Grok 4.20 Multi-AgentstandardUSD 1.25USD 0.20USD 2.501,000,000own modelsource
Grok 4.3standardUSD 1.25USD 0.20USD 2.501,000,000own modelsource
Grok 4.5standardUSD 2USD 0.30USD 6500,000own modelsource
Grok 4.6standardUSD 2USD 0.50USD 6500,000own modelsource
Grok 4.7standardUSD 2USD 0.50USD 6500,000own modelsource
Grok Build 0.1standardUSD 1USD 0.20USD 2256,000own modelsource
  • Cached "—" means xAI's page shows no cache price for that row; budget cached tokens at the input price.

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

What service tiers does xAI publish?

xAI publishes no per-model batch, flex or priority prices, but states these rules: Batch API is 20% off standard for grok-4.7, 4.6, 4.5, 4.3 and the grok-4.20-0309 models (no discount for grok-build-0.1); Priority Processing bills 2x; the US regional endpoint bills 1.1x.

Cached input: 8 of 8 standard prices include a cache-read price, a median 16% of the input price. What cached input means.

What we recorded about xAI's pricing page: Global endpoint; the US regional endpoint bills 1.1x. Batch API is 20% off standard for grok-4.7, 4.6, 4.5, 4.3 and the grok-4.20-0309 models (no discount for grok-build-0.1); Priority Processing bills 2x. Those are published as multipliers, not prices, so no separate rows. Image, video and voice models left out.

BroadNet Inference and xAI

BroadRouter is BroadNet's own site, so BroadNet is never ranked on this page. BroadNet Inference serves none of the models xAI prices. BroadNet Inference pricing.

More on xAI

Quick answers

Is xAI OpenAI-compatible?

Yes, through the Responses API. xAI's chat guide says "The Responses API is the preferred way of interacting with our models" (xAI API reference and chat guide, checked 2026-11-15).

What is xAI's API base URL?

https://api.x.ai/v1, as xAI documents it (xAI API reference and chat guide, checked 2026-11-15).

Does xAI have a free tier?

No free credit or data-sharing programme mentioned on the rate-limits page. Default limits (Tier 0 (0 USD cumulative spend, the default), grok-4.7): 50,000,000 tokens a minute. Tier 0: 150 requests per second and 50M TPM on grok-4.7; 37 RPS and 10M TPM on grok-4.3. "Your per-second limit is derived from your per-minute request budget (RPM / 48, with a minimum of 2)" (xAI rate limits docs, checked 2026-11-14).

Does xAI have a batch API?

Yes. xAI's pricing page puts the Batch API at 20% off standard for grok-4.7, 4.6, 4.5, 4.3 and the grok-4.20-0309 models, with no discount for grok-build-0.1 (xAI pricing, checked 2026-11-14).

Questions

How much does the xAI API cost per token?

xAI's standard prices run from USD 1 input and USD 2 output per 1M tokens (Grok Build 0.1) to USD 2 / USD 6 (Grok 4.7). The median across 8 standard prices is USD 1.25 input and USD 2.50 output per 1M, which is USD 0.00000125 per input token. Input, cached input and output are billed separately.

What is the cheapest model on xAI?

Grok Build 0.1, at USD 1 input and USD 2 output per 1M tokens (USD 1.25 on a 3:1 input-to-output blend).

Is xAI cheaper than other providers?

It depends on the model. Of 6 models that other providers also price, xAI is the cheapest standard price for 6 (all of them tied with another provider), for example Grok 4.6, Grok 4.7 and Grok 4.3; another provider is cheaper for none; and it is the dearest for none. Its median rank is 1 of a median 3.5 providers, on a 3:1 input-to-output blend.

Does xAI have batch, cached or priority pricing?

Cached input: yes, for 8 of 8 standard prices, at a median 16% of the input price. No batch, flex or priority prices are listed per model, but xAI states: Batch API is 20% off standard for grok-4.7, 4.6, 4.5, 4.3 and the grok-4.20-0309 models (no discount for grok-build-0.1); Priority Processing bills 2x; the US regional endpoint bills 1.1x.

How much does a chatbot cost per month on xAI?

For 2,000 requests a day, 1,500 input tokens (60% cached), 300 output, over 30 days: USD 82.80 on Grok Build 0.1, USD 100.80 on Grok 4.20 Multi-Agent (the middle of xAI's list) and USD 207.00 on Grok 4.7. Try your own numbers.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity