InferIndex
Language, English, EN
Account

ModelsGoogleGemma 2 27B

Gemma 2 27B

google/gemma-2-27b-it33k 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.
$0.65
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.
$0.65
Offers
4
Providers
3

Cheapest right now

Featherless

directYou buy access straight from the company that runs the model on its servers. · 33k

$0.65 blended / 1M tokens

No change7D
in
$0.65
out
$0.65
Cached input
–
Go to offer Go to offer at Featherless (opens in a new tab)at Featherless

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). #289 of 419Best rank in the source's rank spread, 289th to 305th, given the confidence intervals of all ranked models. 296th by score. 1,289 1,286 to 1,293Arena Score · 75,754 votes

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

Gemma 2 27B costs from $0.65 per million tokens (at a 3:1 input:output mix): the lowest current price, at 2 providers, checked on ; 4 offers are listed.

Cheapest, no training on prompts

No offer with a published no-training policy for this model.

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$0.65, Featherless–
2026-10-03$0.65, Featherless–
2026-10-04$0.65, Featherless–
2026-10-05$0.65, Featherless–
2026-10-06$0.65, Featherless–
2026-10-07$0.65, Featherless–
2026-10-08$0.65, Featherless–
2026-10-09$0.65, Featherless–
2026-10-10$0.65, Featherless–
2026-10-11$0.65, Featherless–
2026-10-12$0.65, Featherless–
2026-10-13$0.65, Featherless–
2026-10-14$0.65, Featherless–
2026-10-15$0.65, Featherless–
2026-10-16$0.65, Featherless–
2026-10-17$0.65, Featherless–
2026-10-18$0.65, Featherless–
2026-10-19$0.65, Featherless–
2026-10-20$0.65, Featherless–
2026-10-21$0.65, Featherless–
2026-10-22$0.65, Featherless–
2026-10-23$0.65, Featherless–
2026-10-24$0.65, Featherless–
2026-10-25$0.65, Featherless–
2026-10-26$0.65, Featherless–
2026-10-27$0.65, Featherless–
2026-10-28$0.65, Featherless–
2026-10-29$0.65, Featherless–
2026-10-30$0.65, Featherless–
2026-10-31$0.65, Featherless–

Cheapest offer

Offers

4 of 4 offers

Offers for Gemma 2 27B, 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 Featherless 0.65 0.65 0.65 – 33k
Go to offer at Featherless (opens in a new tab)
2 NextBitvia Kilo Gateway 0.65 0.65 0.65 int4 8k 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)
3 Glama 0.65 0.65 0.65 – 8k Unverified. No public page for this offer: listed, not designated cheapest
: Glama (opens in a new tab). No public price page for this model
4 NextBitvia OpenRouter 0.65 0.65 0.65 int4 8k 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.
Go to offer at OpenRouter (opens in a new tab)

No training on promptsTraining terms not published

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

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. Featherless$48.75per month
  2. NextBit$48.75per month+$0.00 vs the cheapest

Host it yourself instead? See the break-even

Compare Gemma 2 27B with

Related models

More from Google

All Google 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=google/gemma-2-27b-it
MCP server
claude mcp add --transport http inferindex https://mcp.inferindex.dev/mcp

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