Groq

Qwen3.8 27B

Qwen3.8 27B is listed by Groq at $0.8 input and $4 output per million tokens. The recorded context window is 131,072 tokens. Release date on file: 2026-08-14. LMArena's text board published 2026-10-20 gives it an overall rating of 1439.7 (rank 76, 25,103 votes). Price source: models.dev (MIT).

  • Context12
  • Inverse price99
  • Arena77
  • GPQA—
  • Tools100
  • Modalities50

List price

Input / 1M$0.80Output / 1M$4.00Cache read / 1M—Blended$3.200Value index77.6Last move—

models.dev · MIT · retrieved Oct 25, 2026

Price history

Input and output list price. A missing day stays a gap in the line. The series is not a quality history.

$3.00 / 1M2026-08-312026-10-18
Input Output25 observationsModelPriceWatch LLM Token Price History · CC-BY-4.0

Benchmarks

LMArena is CC-BY-4.0. Epoch scores, including LiveBench where Epoch publishes it, are CC-BY-4.0. A blank cell means this snapshot has no match. Nothing here is estimated.

BenchmarkScoreDetailSource
LMArena overall1439.7rank 76 · 25,103 votesLMArena leaderboard dataset · CC-BY-4.0
LMArena coding1483.4rank 50 · 6,853 votesLMArena leaderboard dataset · CC-BY-4.0
LMArena math1454.6rank 69 · 1,250 votesLMArena leaderboard dataset · CC-BY-4.0
GPQA Diamond———
LiveBench———
SWE-bench Verified———
Epoch Capability Index———

Provider prices

The list row is the price used for the value index. Other rows are the same model id on models.dev, plus the LiteLLM catalog price when we have one. A split quote is kept beside the list price.

QuoteProviderInput / 1MOutput / 1MBlendedSource
ListGroq$0.80$4.00$3.200models.dev · MIT
Also listedHetzner$0.00$0.00$0.000models.dev · MIT
Also listedStandard Compute$0.43$2.55$2.019models.dev · MIT
Also listedRegolo AI$0.58$2.42$1.960models.dev · MIT
LiteLLMgroq$0.80$4.00$3.200LiteLLM model_prices_and_context_window.json · MIT

Spec

Context131,072Max output16,384Inputtext, imageOutputtextReleased2026-08-14Open weightsYes

Spec fields are from the models.dev row for Groq.

Also from Groq