InferIndex
Language, English, EN
Account

ModelsOpenAIGPT-6 Luna

GPT-6 Luna

openai/gpt-6-luna1.1M 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.
$0.20
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.
$0.24
Offers
48
Providers
21

Cheapest right now

OpenAI

The provider's published policy: prompts are not used for training.

1.1M

$0.20 blended / 1M tokens

No change7D
in
$0.10
out
$0.50
Cached input
$0.01

prompt up to 272K tokens: up to 272K: $0.10 / $0.50; above that: $0.20 / $0.75 (Input / Output, per million tokens)

See pricing See pricing at OpenAI (opens in a new tab)via OpenAI

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).Max setting #80 of 419Best rank in the source's rank spread, 80th to 113th, given the confidence intervals of all ranked models. 97th by score. 1,441 1,437 to 1,445Arena Score · 86,478 votes listed as “GPT-6 Luna (Max)”
  • Code Arena (WebDev)The Code Arena ranking (WebDev). The source publishes no style-corrected series (as read on 9 October 2026).Max setting #34 of 152Best rank in the source's rank spread, 34th to 42nd, given the confidence intervals of all ranked models. 41st by score. 1,579 1,574 to 1,585Arena Score · 27,808 votes listed as “GPT-6 Luna (Max)”
  • 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.Max setting #15 of 57Best rank in the source's rank spread, 15th to 27th, given the confidence intervals of all ranked models. 22nd by score. 0.022 0.018 to 0.026IPS score · 34,619,592 observations listed as “GPT-6 Luna (Max)”
  • 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.Low setting #40 of 57Best rank in the source's rank spread, 40th to 48th, given the confidence intervals of all ranked models. 44th by score. −0.062 −0.070 to −0.055IPS score · 2,438,006 observations listed as “GPT-6 Luna (Low)”

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

GPT-6 Luna costs from $0.20 per million tokens (at a 3:1 input:output mix): the lowest current price, at 9 providers, checked on ; 48 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.Official list price

Offers not counted in cheapest, median or most expensive (30)

  • $0.20 · OpenAI via Eden AI · cannot be designated the cheapest
  • $0.20 · OpenAI via Kilo Gateway · cannot be designated the cheapest
  • $0.20 · OpenAI via LLM API · cannot be designated the cheapest
  • $0.20 · Amazon Bedrock via Eden AI · cannot be designated the cheapest
  • $0.20 · Amazon Bedrock via Eden AI · cannot be designated the cheapest
  • $0.20 · Azure via Eden AI · cannot be designated the cheapest
  • $0.20 · Azure via Kilo Gateway · cannot be designated the cheapest
  • $0.20 · Azure via LLM API · cannot be designated the cheapest
  • $0.20 · Novita via LLM API · cannot be designated the cheapest
  • $0.20 · Abacus RouteLLM via Abacus RouteLLM · cannot be designated the cheapest
  • $0.20 · FastRouter via FastRouter · cannot be designated the cheapest
  • $0.20 · Glama via Glama · cannot be designated the cheapest
  • $0.20 · Martian via Martian · cannot be designated the cheapest
  • $0.20 · Neosantara via Neosantara · cannot be designated the cheapest
  • $0.20 · Nous Portal via Nous Portal · cannot be designated the cheapest
  • $0.20 · OrcaRouter via OrcaRouter · cannot be designated the cheapest
  • $0.20 · OpenAI via LLM Gateway · another route of the same provider
  • $0.20 · OpenAI via Requesty · another route of the same provider
  • $0.20 · OpenAI via OpenRouter · another route of the same provider
  • $0.20 · Azure via OpenRouter · another route of the same provider
  • $0.21 · ShengSuanYun via ShengSuanYun · cannot be designated the cheapest
  • $0.22 · Amazon Bedrock via Kilo Gateway · cannot be designated the cheapest
  • $0.22 · Azure via Eden AI · cannot be designated the cheapest
  • $0.22 · Azure via Kilo Gateway · cannot be designated the cheapest
  • $0.22 · Azure via Kilo Gateway · cannot be designated the cheapest
  • $0.24 · Azure via Eden AI · cannot be designated the cheapest
  • $0.241 · Cortecs via Cortecs · cannot be designated the cheapest
  • $0.40 · OpenAI via Kilo Gateway · cannot be designated the cheapest
  • $0.40 · Vercel AI Gateway via Vercel AI Gateway · priority tier
  • $0.40 · OpenAI via OpenRouter · priority tier

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$0.20, Abacus RouteLLM$0.20
2026-10-03$0.20, Abacus RouteLLM$0.20
2026-10-04$0.20, Abacus RouteLLM$0.20
2026-10-05$0.20, Abacus RouteLLM$0.20
2026-10-06$0.20, OpenAI$0.20
2026-10-07$0.20, OpenAI$0.20
2026-10-08$0.20, OpenAI$0.20
2026-10-09$0.20, OpenAI$0.20
2026-10-10$0.20, OpenAI$0.20
2026-10-11$0.20, OpenAI$0.20
2026-10-12$0.20, OpenAI$0.20
2026-10-13$0.20, OpenAI$0.20
2026-10-14$0.20, OpenAI$0.20
2026-10-15$0.20, OpenAI$0.20
2026-10-16$0.20, OpenAI$0.20
2026-10-17$0.20, OpenAI$0.20
2026-10-18$0.20, OpenAI$0.20
2026-10-19$0.20, OpenAI$0.20
2026-10-20$0.20, OpenAI$0.20
2026-10-21$0.20, OpenAI$0.20
2026-10-22$0.20, OpenAI$0.20
2026-10-23$0.20, OpenAI$0.20
2026-10-24$0.20, OpenAI$0.20
2026-10-25$0.20, OpenAI$0.20
2026-10-26$0.20, OpenAI$0.20
2026-10-27$0.20, OpenAI$0.20
2026-10-28$0.20, OpenAI$0.20
2026-10-29$0.20, OpenAI$0.20
2026-10-30$0.20, OpenAI$0.20
2026-10-31$0.20, OpenAI$0.20

Cheapest offerOfficial list price

Offers

The 25 cheapest of 48 offers

Offers for GPT-6 Luna, 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 OpenAI 0.10 0.50 0.20 – prompt up to 272K tokens: up to 272K: $0.10 / $0.50; above that: $0.20 / $0.75 (Input / Output, per million tokens)
See pricing at OpenAI (opens in a new tab)
2 AtlasCloudhosted APISold by a provider other than the lab that made the model. 0.10 0.50 0.20 1.1M
See pricing at AtlasCloud (opens in a new tab)
3 Venicehosted APISold by a provider other than the lab that made the model. 0.10 0.50 0.20 1.1M Price drop observed: The blended price is 22% lower than before this drop; possibly temporary. · Price drop observed since Oct 27, 2026
Go to offer at Venice (opens in a new tab)
4 NanoGPT 0.10 0.50 0.20 1.1M
Go to offer at NanoGPT (opens in a new tab)
5 OpenAIvia Eden AI 0.10 0.50 0.20 1.1M Unverified. No public page for this offer: listed, not designated cheapest
: Eden AI (opens in a new tab). No public price page for this model
6 OpenAIvia Kilo Gateway 0.10 0.50 0.20 1.1M Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
Go to offer at Kilo Gateway (opens in a new tab)
7 OpenAIvia LLM API 0.10 0.50 0.20 – 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
See pricing at LLM API (opens in a new tab)
8 Amazon Bedrockvia Eden AI 0.10 0.50 0.20 922k Unverified. No public page for this offer: listed, not designated cheapest
: Eden AI (opens in a new tab). No public price page for this model
9 Amazon Bedrockvia Eden AI 0.10 0.50 0.20 922k United States Unverified. No public page for this offer: listed, not designated cheapest
: Eden AI (opens in a new tab). No public price page for this model
10 Azurevia Eden AI 0.10 0.50 0.20 922k Unverified. No public page for this offer: listed, not designated cheapest
: Eden AI (opens in a new tab). No public price page for this model
11 Azurevia Kilo Gateway 0.10 0.50 0.20 1.1M Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
Go to offer at Kilo Gateway (opens in a new tab)
12 Azurevia LLM API 0.10 0.50 0.20 – 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 cheapestPrice drop observed: The blended price is 56% lower than before this drop; possibly temporary. · Price drop observed since Oct 2, 2026
See pricing at LLM API (opens in a new tab)
13 InferenceNethosted APISold by a provider other than the lab that made the model. 0.10 0.50 0.20 922k
Go to offer at InferenceNet (opens in a new tab)
14 NEAR AIhosted APISold by a provider other than the lab that made the model. 0.10 0.50 0.20 1.1M
See pricing at NEAR AI (opens in a new tab)
15 Novitavia LLM API 0.10 0.50 0.20 – 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
See pricing at LLM API (opens in a new tab)
16 Abacus RouteLLM 0.10 0.50 0.20 1M United States Unverified. No public page for this offer: listed, not designated cheapest
: Abacus RouteLLM (opens in a new tab). No public price page for this model
17 FastRouter 0.10 0.50 0.20 400k Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
Go to offer at FastRouter (opens in a new tab)
18 Glama 0.10 0.50 0.20 1.1M Unverified. No public page for this offer: listed, not designated cheapest
: Glama (opens in a new tab). No public price page for this model
19 Martian 0.10 0.50 0.20 – worldwide Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
See pricing at Martian (opens in a new tab)
20 Neosantara 0.10 0.50 0.20 1M Singapore, Indonesia, United States
See pricing at Neosantara (opens in a new tab)
21 Nous Portal 0.10 0.50 0.20 1.1M Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
See pricing at Nous Portal (opens in a new tab)
22 OrcaRouter 0.10 0.50 0.20 1.1M Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
Go to offer at OrcaRouter (opens in a new tab)
23 RedPill 0.10 0.50 0.20 272k
Go to offer at RedPill (opens in a new tab)
24 Vercel AI Gateway 0.10 0.50 0.20 –
Go to offer at Vercel AI Gateway (opens in a new tab)
25 ZenMux 0.10 0.50 0.20 1.1M prompt up to 272K tokens: up to 272K: $0.10 / $0.50; above that: $0.20 / $0.75 (Input / Output, per million tokens)
Go to offer at ZenMux (opens in a new tab)

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.

  • OpenAI

    $0.20

    OpenAI

    in
    $0.10
    out
    $0.50
    Context
    –

    No training on promptsprompt up to 272K tokens: up to 272K: $0.10 / $0.50; above that: $0.20 / $0.75 (Input / Output, per million tokens)

    See pricing See pricing at OpenAI (opens in a new tab)via OpenAI

  • AtlasCloud

    $0.20

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

    in
    $0.10
    out
    $0.50
    Context
    1.1M

    Training terms not published

    See pricing See pricing at AtlasCloud (opens in a new tab)at AtlasCloud

  • Venice

    $0.20

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

    in
    $0.10
    out
    $0.50
    Context
    1.1M

    No training on promptsPrice drop observed: The blended price is 22% lower than before this drop; possibly temporary. · Price drop observed since Oct 27, 2026

    Go to offer Go to offer at Venice (opens in a new tab)at Venice

  • NanoGPT

    $0.20

    NanoGPT

    in
    $0.10
    out
    $0.50
    Context
    1.1M

    No training on prompts

    Go to offer Go to offer at NanoGPT (opens in a new tab)via NanoGPT

  • OpenAI

    $0.20

    Eden AI

    in
    $0.10
    out
    $0.50
    Context
    1.1M

    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

  • OpenAI

    $0.20

    Kilo Gateway

    in
    $0.10
    out
    $0.50
    Context
    1.1M

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

    Go to offer Go to offer at Kilo Gateway (opens in a new tab)via Kilo Gateway

  • OpenAI

    $0.20

    LLM API

    in
    $0.10
    out
    $0.50
    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

    See pricing See pricing at LLM API (opens in a new tab)via LLM API

  • Amazon Bedrock

    $0.20

    Eden AI

    in
    $0.10
    out
    $0.50
    Context
    922k

    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

  • Amazon Bedrock

    $0.20

    Eden AI

    in
    $0.10
    out
    $0.50
    Context
    922k

    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

  • Azure

    $0.20

    Eden AI

    in
    $0.10
    out
    $0.50
    Context
    922k

    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

  • Azure

    $0.20

    Kilo Gateway

    in
    $0.10
    out
    $0.50
    Context
    1.1M

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

    Go to offer Go to offer at Kilo Gateway (opens in a new tab)via Kilo Gateway

  • Azure

    $0.20

    LLM API

    in
    $0.10
    out
    $0.50
    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 cheapestPrice drop observed: The blended price is 56% lower than before this drop; possibly temporary. · Price drop observed since Oct 2, 2026

    See pricing See pricing at LLM API (opens in a new tab)via LLM API

  • InferenceNet

    $0.20

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

    in
    $0.10
    out
    $0.50
    Context
    922k

    No training on prompts

    Go to offer Go to offer at InferenceNet (opens in a new tab)at InferenceNet

  • NEAR AI

    $0.20

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

    in
    $0.10
    out
    $0.50
    Context
    1.1M

    No training on prompts

    See pricing See pricing at NEAR AI (opens in a new tab)at NEAR AI

  • Novita

    $0.20

    LLM API

    in
    $0.10
    out
    $0.50
    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

    See pricing See pricing at LLM API (opens in a new tab)via LLM API

  • Abacus RouteLLM

    $0.20

    Abacus RouteLLM

    in
    $0.10
    out
    $0.50
    Context
    1M

    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

    $0.20

    FastRouter

    in
    $0.10
    out
    $0.50
    Context
    400k

    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.

    Go to offer Go to offer at FastRouter (opens in a new tab)via FastRouter

  • Glama

    $0.20

    Glama

    in
    $0.10
    out
    $0.50
    Context
    1.1M

    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

    $0.20

    Martian

    in
    $0.10
    out
    $0.50
    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.

    See pricing See pricing at Martian (opens in a new tab)via Martian

  • Neosantara

    $0.20

    Neosantara

    in
    $0.10
    out
    $0.50
    Context
    1M

    Training terms not publishedSingapore, Indonesia, United States

    See pricing See pricing at Neosantara (opens in a new tab)via Neosantara

  • Nous Portal

    $0.20

    Nous Portal

    in
    $0.10
    out
    $0.50
    Context
    1.1M

    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.

    See pricing See pricing at Nous Portal (opens in a new tab)via Nous Portal

  • OrcaRouter

    $0.20

    OrcaRouter

    in
    $0.10
    out
    $0.50
    Context
    1.1M

    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.

    Go to offer Go to offer at OrcaRouter (opens in a new tab)via OrcaRouter

  • RedPill

    $0.20

    RedPill

    in
    $0.10
    out
    $0.50
    Context
    272k

    Training terms not published

    Go to offer Go to offer at RedPill (opens in a new tab)via RedPill

  • Vercel AI Gateway

    $0.20

    Vercel AI Gateway

    in
    $0.10
    out
    $0.50
    Context
    –

    No training on prompts

    Go to offer Go to offer at Vercel AI Gateway (opens in a new tab)via Vercel AI Gateway

  • ZenMux

    $0.20

    ZenMux

    in
    $0.10
    out
    $0.50
    Context
    1.1M

    Prompts may be used for trainingprompt up to 272K tokens: up to 272K: $0.10 / $0.50; above that: $0.20 / $0.75 (Input / Output, per million tokens)

    Go to offer Go to offer at ZenMux (opens in a new tab)via ZenMux
Show all 48 offers

5 flex or batch offers hidden (lower priority, variable latency).

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. OpenAI$13.50per month
  2. AtlasCloud$13.50per month+$0.00 vs the cheapest
  3. Venice$13.50per month+$0.00 vs the cheapest

Compare GPT-6 Luna with

Related models

More from OpenAI

All OpenAI 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=openai/gpt-6-luna
MCP server
claude mcp add --transport http inferindex https://mcp.inferindex.dev/mcp

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