Qwen3.8 27B (free)

qwen/qwen3.8-27b-free
FREENew
ToolsJSONReasoning
by Qwen · 2026-08-13

Qwen3.8-27B is Alibaba's open-weight 27B dense model, released under Apache-2.0 and self-hosted on OrcaRouter's own infrastructure. This deployment is text-in, text-out, with a 64K-token context window (65,536 positions) built on the Qwen3.5 architecture - 64 layers, 5120 hidden size. Despite its 27B size it posts unusually strong agentic and coding results on Qwen's own model card, including 90.3 on LiveCodeBench v6, 89.2 on GPQA Diamond, and 79.0 on QwenSWEBench - competitive with far larger closed models on several axes. It supports native tool calling, structured outputs, reasoning mode, and the full sampling surface. Because the weights are open and we run them ourselves, there is no per-token vendor cost to pass through. That makes Qwen3.8-27B a strong default for high-volume text workloads: coding agents, long-document analysis, structured extraction, and agentic automation.

ctx65K tokens
Inputtext
Outputtext
p50 TTFT971 ms
PRICEFreerate-limited · model usage at $0
p50 TTFT971 ms7d
p95 TTFT10.00 s7d
TRAFFIC2518.5Mtokens / 7d

Code samples

Call from any SDK

OpenAI-compatible — keep the SDK you already use

  • OpenAI SDKhttps://api.orcarouter.ai/v1
import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key=os.environ["ORCAROUTER_API_KEY"],
)

response = client.chat.completions.create(
    model="qwen/qwen3.8-27b-free",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Supported parameters

  • frequency_penalty
  • include_reasoning
  • logprobs
  • max_tokens
  • min_p
  • presence_penalty
  • reasoning
  • repetition_penalty
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_k
  • top_p

Pricing

$0
Per request$0
BillingModel usage is never charged to your balance
Over the limitHTTP 429 when a limit is hit

Need it without the limits? qwen/qwen3.8-27b·How free-tier limits work

Performance

p50 TTFT
971 ms
Output speed
56.6 tok/s
p95 TTFT
10.00 s
Error rate
18.8%

Public benchmarks

AndroidWorld
81.9
CharXiv (RQ)
78.8
CoWorkBench
70.7
DeepSWE 1.1
42.2
ERQA
65.5
GPQA Diamond
89.2
HLE
30.8
IFBench
79.5
JobBench
33.4
LiveCodeBench v6
90.3
NL2Repo-Bench
42.3
OmniDocBench 1.5
91.1
OSWorld-Verified
84.3
QwenSWEBench
79.0
RealWorldQA
85.9
RecreationBench
47.1
SWE-bench Pro
61.7
SWE-MM
38.6
Terminal Bench 2.1 (Terminus)
73.0
Vision2Web
62.9
WebArena-Verified
64.8
Source: huggingface.co/Qwen

Community buzz

What developers are saying this week

Hacker News0 mentions · 7ddown 1 vs the previous week

FAQ

How much does Qwen: Qwen3.8 27B (free) cost on OrcaRouter?
Qwen: Qwen3.8 27B (free) is priced at $0.0000 per request via OrcaRouter (flat per-call fee, charged per generation rather than per token).
What is Qwen: Qwen3.8 27B (free)'s context window?
Qwen: Qwen3.8 27B (free) supports a context window of 66K tokens. Use long-context features (RAG, summarisation) up to that limit.
How do I call Qwen: Qwen3.8 27B (free) via the OpenAI SDK?
Set OpenAI base_url to https://api.orcarouter.ai/v1, supply your OrcaRouter API key, and pass model="qwen/qwen3.8-27b-free" in the chat.completions.create call.
Does OrcaRouter rate-limit Qwen: Qwen3.8 27B (free)?
Per-model rate limits follow your OrcaRouter plan. Free tiers ship with conservative caps; paid tiers lift them. Check /pricing for current quotas.

Embed this badge

Qwen: Qwen3.8 27B (free)pricing pending971ms p50via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/qwen/qwen3.8-27b-free" target="_blank"> <img src="https://www.orcarouter.ai/embed/qwen/qwen3.8-27b-free.svg" alt="Qwen: Qwen3.8 27B (free) on OrcaRouter" /> </a>
Markdown [![Qwen: Qwen3.8 27B (free)](https://www.orcarouter.ai/embed/qwen/qwen3.8-27b-free.svg)](https://www.orcarouter.ai/models/qwen/qwen3.8-27b-free)

Model card as data

GET /api/public/models/qwen/qwen3.8-27b-freeOpen
Machine-readable:/llms.txt/llms-full.txt