tokenstat
tokenstat
Alibaba / Qwen

Qwen3.8 27B

Qwen/Qwen3.8-27B · rates as of · Benchmarks · AI plans · Calculator

Dense 27B vision-language model for coding, agent tasks, and image and video understanding

Cheapest input
$0.08
$/MTok · models.dev
Cheapest output
$0.35
$/MTok
Context
1.1M
tokens
Sources
3
37 listings

Price changes

Cheapest list input/output only. Rates move rarely, so this is an event log. Down means cheaper. Showing the 8 latest changes.

Input $/MTok over sampled dates
Output $/MTok
  • ↓ lowerOutput $0.4 → $0.35
  • ↓ lowerInput $0.1 → $0.08

Sources

Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number. Free/$0 listings are hidden by default (6 omitted). Show free/$0 listings.

SourceProviderInputOutputCache readContext
models.devcheapestQwen3.8-27BDevPass (LLM Gateway)$0.08$0.35$0.0533K
models.devconsensusprotocol/Qwen3.8-27BLLM Gateway$0.08$0.35$0.0533K
models.devQwen/Qwen3.8-27BRunInfra$0.1$0.4$0.01262K
models.devqwen3.8-27bCortecs$0.1$0.4$0.04262K
models.devqwen/qwen3.8-27bNanoGPT$0.15$0.7$0.04262K
models.devqwen/qwen3.8-27b:thinkingNanoGPT$0.15$0.7$0.04262K
models.devqwen3-8-27bEmpirioLabs AI$0.17$0.5$0.08262K
models.devqwen3.8-27bCrofAI$0.2$1.50$0.03262K
models.devQwen/Qwen3.8-27BDeepInfra$0.2$2.50$0.05262K
LiteLLMopenrouter/qwen/qwen3.8-27bN/A$0.214$2.55$0.15N/A
models.devqwen3.8-27bAKI.IO$0.3$2.20$0.1262K
models.devqwen/qwen3.8-27bIteraCompute$0.3$2.50$0.03328K
models.devqwen/qwen3.8-27bOrcaRouter$0.33$2.40$0262K
models.devqwen/qwen3.8-27bKosmik Compute$0.35$2.20$0.09262K
models.devqwen/qwen3.8-27bTensorX$0.4$2.40$0.1262K
models.devqwen/qwen3.8-27bAi&$0.4$3$0.2262K
models.devQwen/Qwen3.8-27BHugging Face$0.4$3$0262K
models.devQwen/Qwen3.8-27BCoreWeave$0.4$3$0.15262K
models.devTEE/qwen3.8-27bNanoGPT$0.4$3$0.15262K
LiteLLMQwen/Qwen3.8-27BN/A$0.4$3$0.15N/A
LiteLLMdeepinfra/Qwen/Qwen3.8-27BN/A$0.4$3$0.04N/A
LiteLLMQwen3.8-27BN/A$0.4$3$0.15N/A
OpenRouterqwen/qwen3.8-27bOpenRouter$0.42$3$0.0851M
models.devnovita/qwen3.8-27bLLM Gateway$0.42$3$0.0851M
models.devqwen/qwen3.8-27bKilo Gateway$0.425$2.55$0.0851M
models.dev@cf/qwen/qwen3.8-27bCloudflare$0.45$3.20$0.05262K
models.devbailian/qwen3.8-27bOfox$0.45$3.20$0.051.1M
models.devqwen3.8-27bOVHcloud AI Endpoints$0.47$3.19$0262K
models.devqwen/qwen3.8-27bOfox$0.5$1.71$0.0431.1M
models.devqwen/qwen3.8-27bEden AI$0.5$3$0.11M
models.devqwen3.8-27bCharm Hyper$0.5$3$0.11M
models.devalibaba/qwen3.8-27bVercel AI Gateway$0.5$3$0.11M
models.devqwen3.8-27bRegolo AI$0.58$2.42$0120K
models.devqwen/qwen3.8-27bGroq$0.8$4$0.08131K
LiteLLMqwen/qwen3.8-27bN/A$0.8$4$0.08N/A
LiteLLMqwen3.8-27bN/A$0.8$4$0.08N/A
models.devQwen/Qwen3.8-27BEvroc$0.87$3.50$0262K

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Attachments
  • Open weights
  • In: text
  • In: image
  • In: video
  • In: pdf
  • Out: text
Released: 2026-09-02Family: qwen

Scores

Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.

Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.

Run this model in a real workspace

Launch agents from the project they work in, use remote management to reach another machine, and see this model's sessions and token usage in your own history. Free to use, runs on your device.

Download for macOS

CLI for macOS, Linux, and Windows

Data and list-price estimates may contain mistakes. Not investment advice.