BroadRouter

Grok 4.20 (reasoning) API pricing

Updated

Among the 3 providers we checked (prices read 2026-11-14), 3 tie for the lowest blended standard price for Grok 4.20 (reasoning); xAI charges USD 1.25 per 1M input tokens and USD 2.50 per 1M output tokens. The median across 3 standard prices is USD 1.25 / USD 2.50. That is xAI's own API. Each price is read from the provider's own pricing page.

xAI · slug grok-4.20 · up to 1,000,000 tokens of context · 3 providers with a standard price. Every price is read from the provider's own pricing page and linked in its row, checked 2026-11-14. No aggregator feed. Download all prices (every provider and model, with sources, CSV or JSON). How it compares with the market: the LLM API price index.

What does xAI charge for Grok 4.20 (reasoning)?

Input
USD 1.25
Cached input
USD 0.20
Output
USD 2.50
Blended 3:1
USD 1.563

USD per 1M tokens on xAI, model grok-4.20-0309-reasoning, standard tier. Source, checked 2026-11-14.

Is a host cheaper than xAI? They tie. Google Vertex AI and xAI's own API both work out at USD 1.563 per 1M tokens on the 3:1 blend.

Grok 4.20 (reasoning) price per provider

USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first; the dearest standard price is 0% above the cheapest.

Grok 4.20 (reasoning) API prices by provider
#ProviderInputCached inputOutputBlended 3:1ContextPrecisionSource
1xAI tied cheapest maker
grok-4.20-0309-reasoning
Notes and source quote

Prompts under 200K tokens; once a prompt reaches 200K tokens, all tokens in the request bill at the long-context rate (double).

“| grok-4.20-0309-reasoning (< 200k prompt tokens) | 1M | $1.25 | $0.20 | $2.50 |”
USD 1.25USD 0.20USD 2.50USD 1.5631,000,000not statedxAI page
checked 2026-11-14
re-checked 2026-11-16
2Google Vertex AI tied cheapest
grok-4.20
Notes and source quote

Prompts under 200K tokens; longer prompts bill at long-context rates.

“Grok 4.20 Reasoning Input $1.25 … Output $2.50 … Cache Hit $0.20”
USD 1.25USD 0.20USD 2.50USD 1.563not statednot statedGoogle Vertex AI page
checked 2026-11-14
re-checked 2026-11-16
3Microsoft Azure tied cheapest
Notes and source quote

Foundry Models serverless (pay-as-you-go), Global deployment. Listed as "Grok-4.2"; mapped to Grok 4.20.

“Grok-4.2 Global $1.25 $2.50”
USD 1.25not publishedUSD 2.50USD 1.563not statednot statedMicrosoft Azure page
checked 2026-11-14
re-checked 2026-11-16

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

What does Grok 4.20 (reasoning) cost for a real workload?

Monthly cost over 30 days at each standard price, using the presets of the LLM API cost calculator. Providers without a cached price bill cached input at the input price.

  • Support chatbot: 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
  • RAG over documents: 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
  • Coding agent (one developer): 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.
Monthly cost of three workloads on Grok 4.20 (reasoning), by provider
ProviderSupport chatbotRAG over documentsCoding agent (one developer)
xAI (maker)USD 100.80USD 261.90USD 868.50
Google Vertex AIUSD 100.80USD 261.90USD 868.50
Microsoft AzureUSD 157.50USD 337.50USD 2,475

For the support chatbot, the cheapest price (xAI and 1 other, tied, USD 100.80 a month) saves USD 0 against the median (USD 100.80). For the coding agent the gap is USD 0 a month.

Which Grok 4.20 (reasoning) provider is cheapest for your traffic?

All 3 providers charge the same standard price, USD 1.25 input and USD 2.50 output per 1M tokens, so the per-token price does not decide between them: compare the cache and context lines below.

Grok 4.20 (reasoning): price per 1M tokens at 3 input to 1 output, by share of input served from cache
ProviderNo cache hits50% cached90% cached
xAI (maker)USD 1.563 cheapestUSD 1.169 cheapestUSD 0.8538 cheapest
Google Vertex AIUSD 1.563 cheapestUSD 1.169 cheapestUSD 0.8538 cheapest
Microsoft Azure (no cache price)USD 1.563 cheapestUSD 1.563USD 1.563

USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row. A provider without a cached price bills cached input at the input price. Any charge for writing to the cache, which some providers add, is not included.

2 of 3 providers publish a cached-input price below the input price: xAI (84% off), Google Vertex AI (84% off). Microsoft Azure publishes none, so cached tokens there bill at the input price.

xAI states a context window of 1,000,000 tokens; Google Vertex AI and Microsoft Azure do not state one.

Estimate your own bill

The xAI models whose cheapest standard price is closest to Grok 4.20 (reasoning)'s (USD 1.563 blended):

xAI models priced closest to Grok 4.20 (reasoning)
ModelCheapest inputCheapest outputMax contextProviders
Grok 4.20 (non-reasoning)USD 1.25USD 2.501,000,0002
Grok 4.3USD 1.25USD 2.501,000,0004
Grok 4.5USD 2USD 62,000,0003
Grok 4.6USD 2USD 62,000,0006
Grok 4.7USD 2USD 6524,2886

Priced closest from other makers: Gemini 3.6 Flash (Google, USD 1.50) · Gemini 3.7 Flash (Google, USD 1.50) · Gemini 3.8 Flash (Google, USD 1.50).

All 428 models: API prices compared · Cheapest LLM APIs right now · LLM API price index (open data) · Download all prices (CSV, JSON) · Price change log

Questions

How much does the Grok 4.20 (reasoning) API cost per token?

From USD 1.25 per 1M input tokens (USD 0.00000125 per token) and USD 2.50 per 1M output tokens (USD 0.0000025 per token) at the lowest standard prices we found. The median of 3 standard prices is USD 1.25 input and USD 2.50 output. Each price was read from the provider's own pricing page; the source is linked in its row.

Which provider is cheapest for Grok 4.20 (reasoning)?

Among the 3 providers we checked (prices read 2026-11-14), 3 are tied for the lowest price: xAI, Google Vertex AI and Microsoft Azure, each USD 1.563 per 1M on a blend of 3 input tokens to 1 output token. For input alone the lowest price is USD 1.25 (xAI and 2 others, tied); for output alone, USD 2.50 (xAI and 2 others, tied). Batch, flex, priority and fast tiers are shown in the table but not ranked.

Is Grok 4.20 (reasoning) cheaper from a host than from xAI?

They tie. Google Vertex AI and xAI's own API both work out at USD 1.563 per 1M tokens on the 3:1 blend.

Does Grok 4.20 (reasoning) have cached input pricing?

2 of 3 standard prices include one. The lowest is USD 0.20 per 1M at xAI; the median is USD 0.20. Providers without one bill cached input at the input price. What cached input means.

What is the Grok 4.20 (reasoning) context window?

1,000,000 tokens on every provider that states it.

How much does a coding agent cost per month on Grok 4.20 (reasoning)?

For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 868.50 a month at xAI, USD 868.50 at the median price and USD 2,475 at Microsoft Azure. Try your own numbers.

Is Grok 4.20 (reasoning) free to use through an API?

No provider in our data lists a free price for Grok 4.20 (reasoning) as of 2026-11-14. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model; all free LLM API models are on one page.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity