Qwen 3.8 27B

New
Beta

Dense multimodal coding with thinking control

Chat
Multi-Modal
Thinking
JSON Mode
Tool Calling

Pricing

Run instantly. Pay only for what you use.

Input
$0.10/ M
Output
$0.40/ M
Cache read
$0.04/ M

About Qwen 3.8 27B

Qwen 3.8 27B is Alibaba's dense open-weight vision-language model under Apache 2.0: all 27B parameters active on every token, a 262K-token native context, and native multimodal input — text, images, and video. Thinking is on by default, with per-request enable_thinking, preserve_thinking, and reasoning_effort (xhigh / medium / low).

The 3.8 generation sits on Qwen3.5 hybrid attention — Gated DeltaNet mixed with gated attention, plus multi-token prediction — so a compact dense model can hold long agent loops without MoE routing variance.

Qwen-reported scores with thinking enabled: 61.7 on SWE-bench Pro, 73.0 on Terminal-Bench 2.1, and 42.2 on DeepSWE 1.1 (vs 13.3 for Qwen 3.6 27B), with strict function calling and JSON output.

27Bdense parameters

Every parameter is active on every token — consistent quality with no routing variance.

262Ktoken native context

Native window, extendable to 1M tokens via YaRN for whole-repo prompts.

84.3on OSWorld-Verified

Qwen-reported autonomous desktop computer use — screenshots in, actions out.

Key capabilities

Qwen 3.8 27B is strongest on agentic coding and long-horizon computer-use work — repository patches, visual front-end tickets, and multi-turn agents that keep earlier reasoning.

Agentic coding

Qwen reports 61.7 on SWE-bench Pro and 73.0 on Terminal-Bench 2.1 with thinking enabled — plans, edits, and verifies real repositories.

Long-horizon coding endurance

Qwen reports DeepSWE 1.1 jumping 13.3 → 42.2 over the previous generation — multi-step fixes hold to the end of the run.

Thinking control

On by default and switchable per request — reasoning_effort (xhigh, medium, low) and preserve_thinking tune depth and carry traces across turns.

Native multimodal input

Screenshots, diagrams, and hour-scale video are first-class inputs — front-end bugs and visual tickets stay in one model.

Where this model fits

Best for
  • Repository-level coding agents and refactors

    Qwen reports 61.7 on SWE-bench Pro and 42.2 on DeepSWE 1.1 with thinking on — dense weights, no expert-routing variance.

  • Front-end work from screenshots and recordings

    Screenshots, UI recordings, and hour-scale video are native inputs, so visual bugs and design-to-code stay in one model.

  • Multi-turn agent loops

    preserve_thinking keeps chain-of-thought across turns; reasoning_effort trades depth for speed and token cost per request.

  • Long-horizon terminal and computer-use tasks

    73.0 on Terminal-Bench 2.1 and 84.3 on OSWorld-Verified (Qwen-reported) for autonomous terminal and desktop work.

Avoid for
  • Cost-first, high-volume agent fleets

    Every token runs all 27B parameters. When per-token cost dominates, use Qwen 3.6 35B-A3B — near-peer quality at 3B-active pricing.

  • Tight output-token budgets with thinking on

    Thinking is on by default and verbose. Disable it or drop reasoning_effort to medium/low for cost-sensitive replies.

  • Audio input or speech understanding

    Inputs are text, image, and video only. Transcribe audio upstream before sending it to the model.

Estimate your Savings

Compare Entrim’s pricing, powered by an optimized inference runtime, against other providers using the same token counts per request.

Performance and
benchmarks

Entrim performance for Qwen 3.8 27B under production load in the past few days.

Throughput (tokens / sec)

avg. 105tokens/s

Time to first token (TTFT)

avg. 780ms

Public model benchmarks

61.7SWE-bench Pro

Harder, contamination-resistant software engineering tasks.

73.0Terminal-Bench 2.1

Autonomous work in a real terminal — builds, debugging, ops tasks.

42.2DeepSWE 1.1

Long-horizon agentic coding with environment feedback.

Run Qwen 3.8 27B in minutes

Test this model with $25 free credit. Use Entrim's OpenAI-compatible API to call Qwen 3.8 27B, compare output quality, latency, and request cost, then decide if it fits your workload.

Code examples

curl -X POST "https://api.entrim.ai/v1/chat/completions" \  -H "Content-Type: application/json" \  -H "Authorization: Bearer $ENTRIM_API_KEY" \  -d '{    "model": "Qwen/Qwen3.8-27B",    "messages": [      {        "role": "user",        "content": "Why do they call it a building if it is already built?"      }    ]  }'

SDKs & docs

Use familiar SDK patterns with quickstart examples for common production setups.

OpenAI-compatible

Keep the request format your team already knows.

No cold starts

Production requests are served without model spin-up delays.

Not sure this is the right model?

Explore related models that may be a better fit for your workload.

Tool-heavy coding at 3B-active cost

262K
FP8
Vision
Multimodal
Video
Input / M
$0.05
Output / M
$0.25
Cached / M
$0.025

DeepSeek V4 Flash

Version 0731

High-throughput agentic work with 1M context

1M
FP8
Thinking
Tool Calling
Input / M
$0.09
Output / M
$0.17
Cached / M
$0.015

Multimodal long-context work with thinking control

256K
FP8
Vision
Multilingual
Input / M
$0.10
Output / M
$0.30
Cached / M
$0.04

Run Qwen 3.8 27B with the Most Cost-Effective LLM Inference

Use $25 free credits to test prompts, token sizes, latency, throughput, output quality, and request cost before moving traffic.
All services are online

© 2026. Entrim. All Rights Reserved.

Privacy policyTerms of service