InferIndex
Language, English, EN
Account

ModelsxAIGrok 4.6

Grok 4.6

x-ai/grok-4.6500k context Compare →
MedianThe median blended price among comparable offers: one price per provider (its cheapest route), standard tier, current prices only. Priority tiers and prices converted from points are not counted.
$3.00
Most expensiveThe highest blended price among comparable offers: one price per provider (its cheapest route), standard tier, current prices only. Priority tiers and prices converted from points are not counted.
$3.40
Offers
33
Providers
18

Cheapest right now

AtlasCloud

hosted APISold by a provider other than the lab that made the model. · 500k

$3.00 blended / 1M tokens

No change7D
in
$2.00
out
$6.00
Cached input
$0.50

Public leaderboards

  • Text Arena, style controlThe series the source publishes by default for text since 16 May 2025: ranks corrected for the style of the answers (style control).High setting #57 of 419Best rank in the source's rank spread, 57th to 86th, given the confidence intervals of all ranked models. 72nd by score. 1,455 1,451 to 1,460Arena Score · 33,824 votes listed as “Grok 4.6 (High)”
  • Code Arena (WebDev)The Code Arena ranking (WebDev). The source publishes no style-corrected series (as read on 9 October 2026).High setting #23 of 152Best rank in the source's rank spread, 23rd to 33rd, given the confidence intervals of all ranked models. 30th by score. 1,616 1,609 to 1,623Arena Score · 11,966 votes listed as “Grok 4.6 (High)”
  • Agent Arena aggregateThe Agent Arena aggregate score: a score of another kind (not an Arena score), on a scale of its own; it cannot be compared with the other series.xHigh setting #22 of 57Best rank in the source's rank spread, 22nd to 34th, given the confidence intervals of all ranked models. 30th by score. 0.005 −0.006 to 0.016IPS score · 3,647,053 observations listed as “Grok 4.6 (xHigh)”

Source: Arena (opens in a new tab) · Data under the CC BY 4.0 license (creativecommons.org/licenses/by/4.0) · CC BY 4.0 (opens in a new tab) · scores and ranks as published on 28 Oct 2026; the presentation is ours

Grok 4.6 costs from $3.00 per million tokens (at a 3:1 input:output mix): the lowest current price, at 9 providers, checked on ; 33 offers are listed.

Listed offers, by price

Comparable offersOther offersSolid steps are comparable offers; dashed steps are the other offers, which are not counted in cheapest, median or most expensive.

Offers not counted in cheapest, median or most expensive (20)

  • $3.00 · xAI via Eden AI · cannot be designated the cheapest
  • $3.00 · xAI via Kilo Gateway · cannot be designated the cheapest
  • $3.00 · xAI via LLM API · cannot be designated the cheapest
  • $3.00 · Abacus RouteLLM via Abacus RouteLLM · cannot be designated the cheapest
  • $3.00 · FastRouter via FastRouter · cannot be designated the cheapest
  • $3.00 · Glama via Glama · cannot be designated the cheapest
  • $3.00 · Martian via Martian · cannot be designated the cheapest
  • $3.00 · Nous Portal via Nous Portal · cannot be designated the cheapest
  • $3.00 · OrcaRouter via OrcaRouter · cannot be designated the cheapest
  • $3.00 · xAI via Requesty · another route of the same provider
  • $3.03 · Poe via Poe · price converted from points
  • $3.16 · ShengSuanYun via ShengSuanYun · cannot be designated the cheapest
  • $3.30 · xAI via Kilo Gateway · cannot be designated the cheapest
  • $3.30 · Amazon Bedrock via Eden AI · cannot be designated the cheapest
  • $3.30 · Amazon Bedrock via Eden AI · cannot be designated the cheapest
  • $3.30 · Amazon Bedrock via Kilo Gateway · cannot be designated the cheapest
  • $6.00 · xAI via Kilo Gateway · cannot be designated the cheapest
  • $6.00 · xAI via Kilo Gateway · cannot be designated the cheapest
  • $6.00 · xAI via OpenRouter · priority tier
  • $6.00 · xAI via OpenRouter · priority tier

Cheapest that confirms no training on your prompts. The provider's published policy: prompts are not used for training.

$3.00 blended / 1M tokens

in
$2.00
out
$6.00
Cached input
$0.50

Price historyThe cheapest offer each day, against the lab's official list price when it publishes one. Each day at 00:00 UTC, the offer the API would have selected as the cheapest, with the same exclusions as /cheapest. Blended price, promotions included.

Cheapest offer and official list price, by day, 30 days
DayCheapest offerOfficial list price
2026-10-02$3.00, Abacus RouteLLM–
2026-10-03$3.00, Abacus RouteLLM–
2026-10-04$3.00, Abacus RouteLLM–
2026-10-05$3.00, Abacus RouteLLM–
2026-10-06$3.00, xAI–
2026-10-07$3.00, xAI–
2026-10-08$3.00, xAI–
2026-10-09$3.00, xAI–
2026-10-10$3.00, xAI–
2026-10-11$3.00, xAI–
2026-10-12$3.00, xAI–
2026-10-13$3.00, xAI–
2026-10-14$3.00, xAI–
2026-10-15$3.00, xAI–
2026-10-16$3.00, xAI–
2026-10-17$3.00, xAI–
2026-10-18$3.00, xAI–
2026-10-19$3.00, xAI–
2026-10-20$3.00, xAI–
2026-10-21$3.00, xAI–
2026-10-22$3.00, xAI–
2026-10-23$3.00, xAI–
2026-10-24$3.00, xAI–
2026-10-25$3.00, AtlasCloud–
2026-10-26$3.00, AtlasCloud–
2026-10-27$3.00, AtlasCloud–
2026-10-28$3.00, AtlasCloud–
2026-10-29$3.00, AtlasCloud–
2026-10-30$3.00, AtlasCloud–
2026-10-31$3.00, AtlasCloud–

Cheapest offerOfficial list price

Offers

33 of 33 offers

Offers for Grok 4.6, one row per offer, sorted by blended price.
RankProvider · viaYou buy access through an aggregator: one account and one API that forward your requests to other providers. "Via" names the aggregator; the price is the one it charges you. When "via" says "hosted API", no aggregator is involved: the model belongs to a lab and another provider sells it.Input $/1MOutput $/1MBlended $/1MA single price that mixes input and output: 3 input tokens for 1 output token, per million tokens. It makes offers easy to rank; your real cost depends on your own mix. ContextThe maximum amount of text, counted in tokens, the model can take in and write in a single request. Past this limit, the request is refused or cut.ConditionsWhat a provider says about how it handles your data and who can sign up: training on prompts, processing region, sign-up requirements. Each comes from the provider's published documents; when nothing is published, it stays unknown.SignalsOffer
1 AtlasCloudhosted APISold by a provider other than the lab that made the model. 2.00 6.00 3.00 500k
2 NanoGPT 2.00 6.00 3.00 500k
3 xAIvia Eden AI 2.00 6.00 3.00 500k Unverified. No public page for this offer: listed, not designated cheapest
4 xAIvia Kilo Gateway 2.00 6.00 3.00 500k Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
5 xAIvia LLM API 2.00 6.00 3.00 – Unconfirmed. Last checked 18 October 2026: the last published value, not a confirmed one Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
6 InferenceNethosted APISold by a provider other than the lab that made the model. 2.00 6.00 3.00 500k
7 NEAR AIhosted APISold by a provider other than the lab that made the model. 2.00 6.00 3.00 500k
8 Abacus RouteLLM 2.00 6.00 3.00 500k United States Unverified. No public page for this offer: listed, not designated cheapest
9 FastRouter 2.00 6.00 3.00 500k Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
10 Glama 2.00 6.00 3.00 500k Unverified. No public page for this offer: listed, not designated cheapest
11 Martian 2.00 6.00 3.00 – worldwide Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
12 Nous Portal 2.00 6.00 3.00 500k Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
13 OrcaRouter 2.00 6.00 3.00 500k Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
14 Vercel AI Gateway 2.00 6.00 3.00 –
15 ZenMux 2.00 6.00 3.00 500k prompt up to 200K tokens: up to 200K: $2.00 / $6.00; above that: $4.00 / $12.00 (Input / Output, per million tokens)
16 xAIvia LLM Gateway 2.00 6.00 3.00 – Fee 5%: LLM Gateway adds a 5% fee on credit usage, plus 1.5% for cards issued outside the US (read on llmgateway.io/pricing on Oct 31). Offers are ranked with the 5% included.
17 Amazon Bedrockvia LLM Gateway 2.00 6.00 3.00 – Fee 5%: LLM Gateway adds a 5% fee on credit usage, plus 1.5% for cards issued outside the US (read on llmgateway.io/pricing on Oct 31). Offers are ranked with the 5% included.
18 Google Vertexvia LLM Gateway 2.00 6.00 3.00 – Fee 5%: LLM Gateway adds a 5% fee on credit usage, plus 1.5% for cards issued outside the US (read on llmgateway.io/pricing on Oct 31). Offers are ranked with the 5% included.
19 xAIvia Requesty 2.00 6.00 3.00 500k Fee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Oct 31). Offers are ranked with this fee included.prompt up to 200K (199,999) tokens: up to 200K (199,999): $2.00 / $6.00; above that: $4.00 / $12.00 (Input / Output, per million tokens)
20 xAIvia OpenRouter 2.00 6.00 3.00 500k Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 31). Offers are ranked with this fee included.prompt up to 200K tokens: up to 200K: $2.00 / $6.00; above that: $4.00 / $12.00 (Input / Output, per million tokens)
21 Poe 2.02 6.06 3.03 500k Unverified. No public page for this offer: listed, not designated cheapestpriced in points: Converted from points or credits: the amount paid depends on how points are bought.
No public offer page
22 ShengSuanYun 2.10 6.31 3.16 200k Unverified. No public page for this offer: listed, not designated cheapest
23 xAIvia Kilo Gateway 2.20 6.60 3.30 500k United States Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
24 Amazon Bedrockvia Eden AI 2.20 6.60 3.30 500k Unverified. No public page for this offer: listed, not designated cheapest
25 Amazon Bedrockvia Eden AI 2.20 6.60 3.30 500k United States Unverified. No public page for this offer: listed, not designated cheapest
26 Amazon Bedrockvia Kilo Gateway 2.20 6.60 3.30 500k United States Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
27 xAIvia OpenRouter 2.20 6.60 3.30 500k United States Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 31). Offers are ranked with this fee included.prompt up to 200K tokens: up to 200K: $2.20 / $6.60; above that: $4.40 / $13.20 (Input / Output, per million tokens)
28 Amazon Bedrockvia OpenRouter 2.20 6.60 3.30 500k United States Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 31). Offers are ranked with this fee included.prompt up to 200K tokens: up to 200K: $2.20 / $6.60; above that: $4.40 / $13.20 (Input / Output, per million tokens)
29 Venicehosted APISold by a provider other than the lab that made the model. 2.27 6.80 3.40 500k
30 xAIvia Kilo Gateway 4.00 12.00 6.00 500k Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapestPriority tier: A different service tier, with its own speed and availability conditions.
31 xAIvia Kilo Gateway 4.00 12.00 6.00 500k Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapestPriority tier: A different service tier, with its own speed and availability conditions.
32 xAIvia OpenRouter 4.00 12.00 6.00 500k Priority tier: A different service tier, with its own speed and availability conditions.Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 31). Offers are ranked with this fee included.prompt up to 200K tokens: up to 200K: $4.00 / $12.00; above that: $8.00 / $24.00 (Input / Output, per million tokens)
33 xAIvia OpenRouter 4.00 12.00 6.00 500k Priority tier: A different service tier, with its own speed and availability conditions.Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 31). Offers are ranked with this fee included.prompt up to 200K tokens: up to 200K: $4.00 / $12.00; above that: $8.00 / $24.00 (Input / Output, per million tokens)

No training on promptsPrompts may be used for trainingTraining terms not published

backend not named. The router bills this price itself without naming who serves the model.

  • hosted APISold by a provider other than the lab that made the model.

    in
    $2.00
    out
    $6.00
    Context
    500k

    Training terms not published

  • NanoGPT

    $3.00

    NanoGPT

    in
    $2.00
    out
    $6.00
    Context
    500k

    No training on prompts

  • xAI

    $3.00

    Eden AI

    in
    $2.00
    out
    $6.00
    Context
    500k

    Prompts may be used for trainingUnverified. No public page for this offer: listed, not designated cheapest

    Seller's site: Eden AI (opens in a new tab)No public price page for this model
  • xAI

    $3.00

    Kilo Gateway

    in
    $2.00
    out
    $6.00
    Context
    500k

    Training terms not publishedUnverified. The source page shows one price per model, not this seller's: listed, not designated cheapest

  • xAI

    $3.00

    LLM API

    in
    $2.00
    out
    $6.00
    Context
    –

    No training on promptsUnconfirmed. Last checked 18 October 2026: the last published value, not a confirmed oneUnverified. The source page shows one price per model, not this seller's: listed, not designated cheapest

  • hosted APISold by a provider other than the lab that made the model.

    in
    $2.00
    out
    $6.00
    Context
    500k

    No training on prompts

  • NEAR AI

    $3.00

    hosted APISold by a provider other than the lab that made the model.

    in
    $2.00
    out
    $6.00
    Context
    500k

    No training on prompts

  • Abacus RouteLLM

    in
    $2.00
    out
    $6.00
    Context
    500k

    No training on promptsUnited StatesUnverified. No public page for this offer: listed, not designated cheapest

    Seller's site: Abacus RouteLLM (opens in a new tab)No public price page for this model
  • FastRouter

    in
    $2.00
    out
    $6.00
    Context
    500k

    Training terms not publishedUnverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapestbackend not named: The router bills this price itself without naming who serves the model.

  • Glama

    $3.00

    Glama

    in
    $2.00
    out
    $6.00
    Context
    500k

    No training on promptsUnverified. No public page for this offer: listed, not designated cheapestbackend not named: The router bills this price itself without naming who serves the model.

    Seller's site: Glama (opens in a new tab)No public price page for this model
  • Martian

    $3.00

    Martian

    in
    $2.00
    out
    $6.00
    Context
    –

    Training terms not publishedworldwideUnverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapestbackend not named: The router bills this price itself without naming who serves the model.

  • Nous Portal

    in
    $2.00
    out
    $6.00
    Context
    500k

    Prompts may be used for trainingUnverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapestbackend not named: The router bills this price itself without naming who serves the model.

  • OrcaRouter

    in
    $2.00
    out
    $6.00
    Context
    500k

    Training terms not publishedUnverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapestbackend not named: The router bills this price itself without naming who serves the model.

  • Vercel AI Gateway

    in
    $2.00
    out
    $6.00
    Context
    –

    No training on prompts

  • ZenMux

    $3.00

    ZenMux

    in
    $2.00
    out
    $6.00
    Context
    500k

    Prompts may be used for trainingprompt up to 200K tokens: up to 200K: $2.00 / $6.00; above that: $4.00 / $12.00 (Input / Output, per million tokens)

  • xAI

    $3.00

    LLM Gateway

    in
    $2.00
    out
    $6.00
    Context
    –

    No training on promptsFee 5%: LLM Gateway adds a 5% fee on credit usage, plus 1.5% for cards issued outside the US (read on llmgateway.io/pricing on Oct 31). Offers are ranked with the 5% included.

  • LLM Gateway

    in
    $2.00
    out
    $6.00
    Context
    –

    No training on promptsFee 5%: LLM Gateway adds a 5% fee on credit usage, plus 1.5% for cards issued outside the US (read on llmgateway.io/pricing on Oct 31). Offers are ranked with the 5% included.

  • LLM Gateway

    in
    $2.00
    out
    $6.00
    Context
    –

    No training on promptsFee 5%: LLM Gateway adds a 5% fee on credit usage, plus 1.5% for cards issued outside the US (read on llmgateway.io/pricing on Oct 31). Offers are ranked with the 5% included.

  • xAI

    $3.00

    Requesty

    in
    $2.00
    out
    $6.00
    Context
    500k

    Prompts may be used for trainingFee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Oct 31). Offers are ranked with this fee included.prompt up to 200K (199,999) tokens: up to 200K (199,999): $2.00 / $6.00; above that: $4.00 / $12.00 (Input / Output, per million tokens)

  • xAI

    $3.00

    OpenRouter

    in
    $2.00
    out
    $6.00
    Context
    500k

    No training on promptsFee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 31). Offers are ranked with this fee included.prompt up to 200K tokens: up to 200K: $2.00 / $6.00; above that: $4.00 / $12.00 (Input / Output, per million tokens)

  • Poe

    $3.03

    Poe

    in
    $2.02
    out
    $6.06
    Context
    500k

    Prompts may be used for trainingUnverified. No public page for this offer: listed, not designated cheapestpriced in points: Converted from points or credits: the amount paid depends on how points are bought.

    No public offer page
  • ShengSuanYun

    in
    $2.10
    out
    $6.31
    Context
    200k

    Training terms not publishedUnverified. No public page for this offer: listed, not designated cheapest

    Seller's site: ShengSuanYun (opens in a new tab)No public price page for this model
  • xAI

    $3.30

    Kilo Gateway

    in
    $2.20
    out
    $6.60
    Context
    500k

    Training terms not publishedUnited StatesUnverified. The source page shows one price per model, not this seller's: listed, not designated cheapest

  • Eden AI

    in
    $2.20
    out
    $6.60
    Context
    500k

    Prompts may be used for trainingUnverified. No public page for this offer: listed, not designated cheapest

    Seller's site: Eden AI (opens in a new tab)No public price page for this model
  • Eden AI

    in
    $2.20
    out
    $6.60
    Context
    500k

    Prompts may be used for trainingUnited StatesUnverified. No public page for this offer: listed, not designated cheapest

    Seller's site: Eden AI (opens in a new tab)No public price page for this model
  • Kilo Gateway

    in
    $2.20
    out
    $6.60
    Context
    500k

    Training terms not publishedUnited StatesUnverified. The source page shows one price per model, not this seller's: listed, not designated cheapest

  • xAI

    $3.30

    OpenRouter

    in
    $2.20
    out
    $6.60
    Context
    500k

    No training on promptsUnited StatesFee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 31). Offers are ranked with this fee included.prompt up to 200K tokens: up to 200K: $2.20 / $6.60; above that: $4.40 / $13.20 (Input / Output, per million tokens)

  • OpenRouter

    in
    $2.20
    out
    $6.60
    Context
    500k

    No training on promptsUnited StatesFee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 31). Offers are ranked with this fee included.prompt up to 200K tokens: up to 200K: $2.20 / $6.60; above that: $4.40 / $13.20 (Input / Output, per million tokens)

  • Venice

    $3.40

    hosted APISold by a provider other than the lab that made the model.

    in
    $2.27
    out
    $6.80
    Context
    500k

    No training on prompts

  • xAI

    $6.00

    Kilo Gateway

    in
    $4.00
    out
    $12.00
    Context
    500k

    Training terms not publishedUnverified. The source page shows one price per model, not this seller's: listed, not designated cheapestPriority tier: A different service tier, with its own speed and availability conditions.

  • xAI

    $6.00

    Kilo Gateway

    in
    $4.00
    out
    $12.00
    Context
    500k

    Training terms not publishedUnverified. The source page shows one price per model, not this seller's: listed, not designated cheapestPriority tier: A different service tier, with its own speed and availability conditions.

  • xAI

    $6.00

    OpenRouter

    in
    $4.00
    out
    $12.00
    Context
    500k

    No training on promptsPriority tier: A different service tier, with its own speed and availability conditions.Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 31). Offers are ranked with this fee included.prompt up to 200K tokens: up to 200K: $4.00 / $12.00; above that: $8.00 / $24.00 (Input / Output, per million tokens)

  • xAI

    $6.00

    OpenRouter

    in
    $4.00
    out
    $12.00
    Context
    500k

    No training on promptsPriority tier: A different service tier, with its own speed and availability conditions.Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 31). Offers are ranked with this fee included.prompt up to 200K tokens: up to 200K: $4.00 / $12.00; above that: $8.00 / $24.00 (Input / Output, per million tokens)

Show the 25 cheapest only

Blended = (3 × input + output) / 4, per million tokens. Prices in USD, converted at the ECB rate when the provider bills in another currency.

Method

Monthly cost for your workload

Computed by the API for the three cheapest offers, per 30-day month.
  1. AtlasCloud$210.00per month
  2. NanoGPT$210.00per month+$0.00 vs the cheapest
  3. InferenceNet$210.00per month+$0.00 vs the cheapest

Compare Grok 4.6 with

Related models

More from xAI

All xAI models

Same index family

Use this data

The index is queryable. The API is free to use.
Free API
curl https://api.inferindex.dev/cheapest?model=x-ai/grok-4.6
MCP server
claude mcp add --transport http inferindex https://mcp.inferindex.dev/mcp

Also works in Cursor and Codex: see the MCP page.