InferIndex
Language, English, EN
Account

ModelsNous ResearchHermes 4 405B

Hermes 4 405B

nousresearch/hermes-4-405b128k context Compare →
Offers
8
Providers
5

Cheapest right now

Nebius

via Requesty

fp8 · 128k

$1.50 blended / 1M tokens

No change7D
in
$1.00
out
$3.00
Cached input
$1.00

Fee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Oct 30). Offers are ranked with this fee included.

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

Hermes 4 405B costs from $1.50 per million tokens (at a 3:1 input:output mix): the cheapest current offer, at Nebius, checked on ; 8 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 (7)

  • $0.525 · NanoGPT via NanoGPT · cannot be designated the cheapest
  • $1.50 · Cortecs via Cortecs · cannot be designated the cheapest
  • $1.50 · Nebius via Eden AI · cannot be designated the cheapest
  • $1.50 · Nebius via Kilo Gateway · cannot be designated the cheapest
  • $1.50 · Glama via Glama · cannot be designated the cheapest
  • $1.50 · Martian via Martian · cannot be designated the cheapest
  • $1.50 · Nebius via OpenRouter · another route of the same provider

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

$0.525 blended / 1M tokens

in
$0.30
out
$1.20
Cached input
–

Thinking: Thinking: a mode of the model. Designated cheapest because no standard offer exists

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

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$0.525, NanoGPT–
2026-10-03$0.525, NanoGPT–
2026-10-04$0.525, NanoGPT–
2026-10-05$0.525, NanoGPT–
2026-10-06$0.525, NanoGPT–
2026-10-07$0.525, NanoGPT–
2026-10-08$0.525, NanoGPT–
2026-10-09$0.525, NanoGPT–
2026-10-10$0.525, NanoGPT–
2026-10-11$0.525, NanoGPT–
2026-10-12$0.525, NanoGPT–
2026-10-13$0.525, NanoGPT–
2026-10-14$0.525, NanoGPT–
2026-10-15$0.525, NanoGPT–
2026-10-16$0.525, NanoGPT–
2026-10-17$0.525, NanoGPT–
2026-10-18$0.525, NanoGPT–
2026-10-19$1.50, Nebius–
2026-10-20$1.50, Nebius–
2026-10-21$1.50, Nebius–
2026-10-22$1.50, Nebius–
2026-10-23$1.50, Nebius–
2026-10-24$1.50, Nebius–
2026-10-25$1.50, Nebius–
2026-10-26$1.50, Nebius–
2026-10-27$1.50, Nebius–
2026-10-28$1.50, Nebius–
2026-10-29$1.50, Nebius–
2026-10-30$1.50, Nebius–
2026-10-31$1.50, Nebius–

Cheapest offer

Offers

8 of 8 offers

Offers for Hermes 4 405B, 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.PrecisionHow finely the model's numbers are stored on the provider's servers. Lower precision (fp8, fp4) is cheaper to run and can slightly change answer quality; "unknown" means the provider doesn't say. 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 NanoGPT 0.30  1.20 0.525 – 128k Thinking: Thinking: a mode of the model, not its standard offer. Never designated cheapest while a standard offer exists
Go to offer at NanoGPT (opens in a new tab)
2 Cortecs 0.999 3.00 1.50  – 128k worldwide Unverified. No public page for this offer: listed, not designated cheapest
: Cortecs (opens in a new tab). No public price page for this model
3 Nebiusvia Eden AI 1.00  3.00 1.50  fp8 131k worldwide 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
4 Nebiusvia Kilo Gateway 1.00  3.00 1.50  fp8 131k worldwide Unverified. No public page for this offer: listed, not designated cheapest
: Kilo Gateway (opens in a new tab). No public price page for this model
5 Glama 1.00  3.00 1.50  – 131k Unverified. No public page for this offer: listed, not designated cheapest
: Glama (opens in a new tab). No public price page for this model
6 Martian 1.00  3.00 1.50  – – 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)
7 Nebiusvia Requesty 1.00  3.00 1.50  fp8 128k worldwide Fee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Oct 30). Offers are ranked with this fee included.
Go to offer at Requesty (opens in a new tab)
8 Nebiusvia OpenRouter 1.00  3.00 1.50  fp8 131k worldwide Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.
Go to offer at OpenRouter (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.

  • NanoGPT

    $0.525

    NanoGPT

    in
    $0.30 
    out
    $1.20
    Precision
    –
    Context
    128k

    No training on promptsThinking: Thinking: a mode of the model, not its standard offer. Never designated cheapest while a standard offer exists

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

  • Cortecs

    $1.50

    Cortecs

    in
    $0.999
    out
    $3.00
    Precision
    –
    Context
    128k

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

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

  • Nebius

    $1.50

    Eden AI

    in
    $1.00 
    out
    $3.00
    Precision
    fp8
    Context
    131k

    Prompts may be used for trainingworldwideUnverified. 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

  • Nebius

    $1.50

    Kilo Gateway

    in
    $1.00 
    out
    $3.00
    Precision
    fp8
    Context
    131k

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

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

  • Glama

    $1.50

    Glama

    in
    $1.00 
    out
    $3.00
    Precision
    –
    Context
    131k

    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

    $1.50

    Martian

    in
    $1.00 
    out
    $3.00
    Precision
    –
    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

  • Nebius

    $1.50

    Requesty

    in
    $1.00 
    out
    $3.00
    Precision
    fp8
    Context
    128k

    Prompts may be used for trainingworldwideFee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Oct 30). Offers are ranked with this fee included.

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

  • Nebius

    $1.50

    OpenRouter

    in
    $1.00 
    out
    $3.00
    Precision
    fp8
    Context
    131k

    Training terms not publishedworldwideFee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.

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

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. NanoGPT$36.00per month

Host it yourself instead? See the break-even

Compare Hermes 4 405B with

Related models

More from Nous Research

All Nous Research 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=nousresearch/hermes-4-405b
MCP server
claude mcp add --transport http inferindex https://mcp.inferindex.dev/mcp

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