Get started

Gemma 2 27B

Timed at 46.5 tok/s, with results on 1 openly licensed board, and not scored by Artificial Analysis.

retrieved sha256 · 0bb53a77713f

Models/Google/Gemma 2 27BUSD per 1M tokens · as OpenRouter routes it
google/gemma-2-27b-itGoogle · base listing · Gemini tokenizer
OpenRouter list price · the routed rate, as the catalog carried itretrieved 17 Nov 16:29 UTC from openrouter.ai ↗
Input$0.65per 1M tokens
Output$0.65per 1M tokens
Cached inputnot listedper 1M tokens
Context8k8,192 tokens
What the list says · the fields OpenRouter publishes for this id9 fields
AuthorGoogle
Listed
Context8,192 tokens
Max output2,048 tokens
Modalitiestext → text
TokenizerGemini
Moderationnot moderated by OpenRouter
Knowledge cutoff2024-06-30
What the weights say · read from the model's own repository on Hugging Faceretrieved from huggingface.co ↗
Licencegemma
Parameters27.2B · 27,227,128,320 declared
Model classGemma2ForCausalLM
Downloadgated, each request approved by the maker
Published

Measured speed

17 requests · 1 endpoint · 30-minute window
Throughput46.5 tok/sMedian output rate, weighted across the one endpoint serving it by the requests each answered.the speed board
First token385msMedian wait before the first token, over the same window and weighted the same way.how Vitna reads a figure
Endpoint spreadone routeOne endpoint served this model in the window, so the headline is that endpoint's own figure rather than a blend.the board, fastest first

OpenRouter's own timing of its routed traffic, weighted by requests, over one 30-minute window read . Every route is on the endpoint ledger below.

Every endpoint

1 priced · 1 timed · cheapest first
  1. NextBitnextbit/int4 · listed$0.65$0.65not listedint42k46.5 tok/s32385ms17 req100%

Uptime is OpenRouter's own figure for each seller over the trailing day, read once a day, and the column prints the latest reading, taken . The one seller with a reading was at 99% or better on each of the 23 days held. Source: OpenRouter's public endpoints API, one reading a day for each seller: 1,211 sellers carried one on the latest of the 23 days held.

Source: OpenRouter's public endpoints API. 1257 sellers across 359 models when the mirror ran, 186 of them served by more than one. List prices, not what anybody paid; a discount is the seller's own. Read . Speed is OpenRouter's own timing over one 30-minute window, read .

What each seller accepts

10 parameters · 1 seller
  1. frequency_penaltyevery seller
  2. max_tokensevery seller
  3. presence_penaltyevery seller
  4. repetition_penaltyevery seller
  5. response_formatevery seller
  6. seedevery seller
  7. stopevery seller
  8. structured_outputsevery seller
  9. temperatureevery seller
  10. top_pevery seller

The one seller that publishes a list accepts these 10. Each list is the seller's own declaration in OpenRouter's endpoints API, read , and nothing here tested one.

Price position

342 priced models

Blended $0.65 per million tokens, 3 in to 1 out: cheaper than 189 of the 342 priced models in the catalog. Each bar is one stretch of the catalog on a logarithmic price scale; the mark is this listing.

Measured quality

145 models with an index · 132 on a design arena board
Intelligence Indexnot scoredArtificial Analysis has not scored this model on its Intelligence Index.the intelligence leaderboard
Coding Indexnot scoredArtificial Analysis has not scored this model on its Coding Index.the coding leaderboard
Agentic Indexnot scoredArtificial Analysis has not scored this model on its Agentic Index.the agentic leaderboard

Not ranked in any Design Arena category.

Epoch Capabilities Index · a fit by a third party over every benchmark this model has results onthe whole index, with intervals
Index118.6114.2 to 122.4
Position191 of 258above 26% of the models placed
Results behind it6benchmark results
As Epoch names itGemma 2 27Breleased 24 Jun 2024

Position 191 of the 258 models Epoch has placed, which is not the population of either board above, on a scale anchored at Claude 3.5 Sonnet 130 and GPT-5 150. Epoch states that absolute values are meaningless by themselves and that comparisons between models are what the index is for, that values are not linearly related to benchmark accuracy, and that a highly specialised model may score low while being capable in its own domain.

Benchmark results

1 of 6 boards · 3 results
Epoch AI Benchmarking Hub · publisher-run, CC-BY-4.03 of 22 tasks · effort unstated
TaskAll runsScore
GPQA diamond3420.36
MATH level 51080.28
OTIS Mock AIME 2024-20253190.01

Mean accuracy, 0 to 1, on the task the row names, as Epoch AI runs it and averaged over repeated runs. All eighteen of their tasks, including the held-out FrontierMath tiers, named as they name them. The model id carries the effort setting the run used. Epoch AI Benchmarking Hub names this run gemma-2-27b-it, with no effort setting written on it. All runs is how many runs the publisher scored on the task, every model's. Read from epoch.ai ↗, which dates its own data . Epoch AI Benchmarking Hub data, by Epoch AI, under CC BY 4.0.

1 of the 6 openly licensed boards Vitna mirrors carries a result for Gemma 2 27B, each printed as its publisher published it and none added to another. MTEB, LiveBench, HELM, Vectara hallucination leaderboard and Aider polyglot have not published one under a name that matches its listing, and names are matched to the catalog exactly and never guessed. A task that is a link opens its column on /capability, with every run scored on it; an effort that is a link opens its run's row there, where the run is ranked on Vitna's scale. Every board, with its licence and what its publisher measures, is on /benchmarks.

Sources

Source: OpenRouter (openrouter.ai/models), as of 17 Nov 16:29 UTC. sha256 0bb53a77713f over 853,270 bytes.
Catalog: OpenRouter's public model list.
Intelligence, coding and agentic indexes: Artificial Analysis, as published by OpenRouter.
Elo, win rate and rank: Design Arena, as published by OpenRouter.
Source: each model's own Hugging Face repository (huggingface.co), as of 20 Nov 2026. 162 repositories read, 4 did not answer.
Licence, parameter count, model class and gating: each model's own Hugging Face repository, the one OpenRouter names for the listing.
A licence is the tag the uploader put on the repository, read from nothing else and verified by nobody.
A parameter count is the total the repository's safetensors files declare; for a mixture of experts that is every expert, not the share one token runs through.
Source: the Epoch AI Capabilities Index (epoch.ai/eci), as of 20 Nov 2026. 258 models placed over 2917 benchmark results.
Epoch AI Benchmarking Hub data, by Epoch AI, under CC BY 4.0.
Vitna ran none of these evaluations and adjusted none of these figures.