Qwen3.8 27B

AlibabaKey qwen3.8-27bAlso reported as qwen3.8:27b, qwen/qwen3.8-27b, obsidian/qwen3.8-27b, command-code/qwen/qwen3.8-27b, nutaraline/qwen3.8-27b, @cf/qwen/qwen3.8-27b, self-dploy/qwen3.8-27b, /models/qwen3.8-27b, Qwen/Qwen3.8-27B

Rank
#122
by active users
Active users
8
Down 13 from 21 active users in the previous 30 days. vs previous 30 days
Adoption
0.8%
of 967 accounts
Tokens
1.4B
cache included
Est. cost
$851
at public list prices
First seen
Aug 14, 2026
in any submission

Oct 15 – Nov 13, 2026 (UTC)967 accounts100% of tokens from an identified modelData through Nov 13, 2026, 07:02 UTCHow we count

Daily active users

Distinct accounts that used this model on each UTC day.

0 active users on Nov 13, 2026

Daily active users for Qwen3.8 27B, Oct 15, 2026 to Nov 13, 2026. Peak 3. Use the left and right arrow keys to read each day.320
Show daily values
Daily active users and tokens for Qwen3.8 27B
Date (UTC)Active usersTokens
Oct 15, 2026146.8K
Oct 16, 202600
Oct 17, 202600
Oct 18, 20261119.6M
Oct 19, 202600
Oct 20, 2026173.7M
Oct 21, 202600
Oct 22, 202600
Oct 23, 202600
Oct 24, 202600
Oct 25, 202600
Oct 26, 202600
Oct 27, 202600
Oct 28, 202600
Oct 29, 202600
Oct 30, 202600
Oct 31, 202619.5K
Nov 1, 202600
Nov 2, 202600
Nov 3, 202600
Nov 4, 202600
Nov 5, 202600
Nov 6, 202600
Nov 7, 202600
Nov 8, 20261241
Nov 9, 2026175.4M
Nov 10, 20261792.2M
Nov 11, 20263302.6M
Nov 12, 2026110.1M
Nov 13, 202600

Token mix

How the 1.4B tokens split. Cache reads are usually most of an agent's tokens and are priced far below input.

  • Input79%
  • Output7.8%
  • Cache read13%
  • Cache write0%
  • Reasoning<0.1%

Agents that carry Qwen3.8 27B

Each agent's share of this model's tokens, and how many accounts used the model through it.

  1. Oh My Pi85% of this model's tokens1active users
  2. OpenCode8.7% of this model's tokens1active users
  3. ZCode5.4% of this model's tokens1active users
  4. Claude Code0.4% of this model's tokens1active users
  5. DeepSeek Harness<0.1% of this model's tokens1active users
  6. LM Studio<0.1% of this model's tokens1active users
  7. Pi<0.1% of this model's tokens1active users
  8. cc-mirror/curl<0.1% of this model's tokens1active users

Benchmarks

The best result for Qwen3.8 27B in each benchmark Tokscale tracks. Each benchmark has its own unit, run conditions and source, so compare a score only with other models on the same benchmark. Rank is among the models Tokscale matched in that benchmark.

All benchmarks
  • Epoch Capabilities IndexOverall · Epoch AI
    152.6
    Rank #56 of 158 matched modelsNo conditions reportedModel released Aug 14, 2026Source: epoch.ai (opens in a new tab)
  • WebDev ArenaWeb development · LMArena
    1,593
    Rank #27 of 110 matched modelsNo conditions reportedPublished Oct 19, 2026Source: huggingface.co (opens in a new tab)
  • Agent ArenaAgents · LMArena
    −0.04
    Rank #36 of 48 matched modelsArena Agent ModePublished Oct 19, 2026Source: huggingface.co (opens in a new tab)

Not evaluated: GPQA Diamond, Humanity's Last Exam, FrontierMath Tiers 1–3 (v2), SimpleQA Verified, Terminal-Bench 4.1, CursorBench, DeepSWE, FrontierSWE. A missing result is not a score of zero.

Pricing

List prices from models.dev in US dollars per 1M tokens, retrieved Nov 12, 2026. OpenRouter is the reference price for the estimates below. It is the first provider listed; models.dev lists no price from the lab's own API.

Price at real agent usageEstimate at list prices

What 1M tokens cost at the reference list price when they split into input, output and cache the way Tokscale users' agents used them. It is not what anyone paid.

At this model's mix
$0.27
Est. per 1M tokens
13% cache reads
At the community mix
$0.05
Est. per 1M tokens
96% cache reads
3:1 input/output blend
$0.58
Per 1M tokens at list prices
No cache

Cache reads were 13% of Qwen3.8 27B tokens in the last 30 days and 96% of all tokens. The 3:1 blend, (3 × input + output) ÷ 4, is the usual comparison and ignores cache.

Assumptions

  • OpenRouter list prices per 1M tokens: input $0.15, output $1.88, cache read $0.04.
  • This model's mix is its own input, output, cache and reasoning tokens in the last 30 days.
  • The community mix is the tokens of every identified model in the last 30 days.
  • This is an estimate at list prices, not what anyone paid.
  • Reasoning tokens are priced as output.
  • Long-context tiers, batch pricing and discounts are not applied.
  • Token mixes come from public Tokscale submissions. Hidden accounts are excluded.
  • No cache-write price is listed, so cache writes are priced as input.

List prices by provider

  • OpenRouterReferenceqwen/qwen3.8-27b
    $0.15 input per 1M tokens$1.88 output per 1M tokens$0.04 cache read per 1M tokensCache write not listed1.05M tokens of context
  • Vercel AI Gatewayalibaba/qwen3.8-27b
    $0.06 input per 1M tokens$2.20 output per 1M tokens$0.06 cache read per 1M tokensCache write not listed262K tokens of context
  • Deep InfraQwen/Qwen3.8-27B
    $0.20 input per 1M tokens$2.50 output per 1M tokens$0.05 cache read per 1M tokensCache write not listed262K tokens of context
  • Groqqwen/qwen3.8-27b
    $0.80 input per 1M tokens$4 output per 1M tokensCache read not listedCache write not listed131K tokens of context
  • Cerebrasqwen-3.8-27b
    $0.99 input per 1M tokens$1.49 output per 1M tokens$0.99 cache read per 1M tokensCache write not listed131K tokens of context

Specs

From models.dev (MIT), retrieved Nov 12, 2026, as the lab or the first listed provider reports them. A dash means models.dev does not list the value.

Context window
262K tokens
Max output
33K tokens
Input
Text, Image, Video
Output
Text
Knowledge cutoff
— not listed
Release date
Aug 14, 2026
Open weights
Yes
Reasoning
Yes
Tool calling
Yes

Top public profiles

Public profiles that used Qwen3.8 27B most in this period, by tokens. Hidden accounts are never listed.

  1. 1SeaL773@SeaL7731.2Btokens$851est. cost4active days$851 est. cost · 4 active days
  2. 2René R.@Rene-Roscher119.6Mtokens—est. cost1active daysno price · 1 active days
  3. 3siddicky@siddicky73.7Mtokens—est. cost1active daysno price · 1 active days
  4. 4Chalie AI@chalie-ai5.1Mtokens—est. cost1active daysno price · 1 active days
  5. 5ParkMyeongCheol_박명철@pinion05952Ktokens—est. cost1active daysno price · 1 active days
  6. 6seoyoung@b1ueseoyoung46.8Ktokens—est. cost1active daysno price · 1 active days
  7. 7Sunghyun Cho@anaclumos9.5Ktokens<$1est. cost1active days<$1 est. cost · 1 active days
  8. 8如是@MiFaZhan241tokens<$1est. cost1active days<$1 est. cost · 1 active days

More from Alibaba

Other Alibaba models in the same period, by active users.

  1. Qwen3.8 Max1.8% adoption17active users
  2. Qwen3.8 Flash1.8% adoption17active users
  3. Qwen3.8 Flash Next0.6% adoption6active users
  4. Qwen3 Coder Next0.4% adoption4active users
  5. Qwen3.5 9B0.3% adoption3active users
  6. Qwen3.5 4B0.3% adoption3active users
All models

Sources and attribution

Each score keeps its own source, unit and run conditions. Tokscale does not combine benchmarks into one score, and a missing score means the model was not evaluated, not that it scored zero.

  • Epoch AIEpoch Capabilities Index, Epoch's own runs and the external results it collects.CC BY 4.0 · Retrieved Nov 12, 2026 · Data through Nov 9, 2026Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from https://epoch.ai/benchmarks.
  • LMArenaWebDev Arena and Agent Arena leaderboards.CC BY 4.0 · Retrieved Oct 21, 2026 · Data through Oct 19, 2026LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), Hugging Face.
  • models.devSpecs and list prices per provider.MIT · Retrieved Nov 12, 2026models.dev, an open catalog of AI models (github.com/anomalyco/models.dev).
  • TokscaleActive users, tokens and token mix from public Tokscale submissions. Hidden accounts are excluded.How we count