Qwen3.5-27B

Name: Qwen: Qwen3.5-27B API
Brand: Qwen

qwen/qwen3.5-27b

VisionToolsJSONReasoning

by Qwen · 2026-02-25

Qwen3.5 27B — open-weight dense multimodal (text/image/video), 27B params, 32k context (vision mode).

Endpoints:/v1/chat/completions

ctx32.8K tokens

Max output65.5K

Inputtext + image + video

Outputtext

p50 TTFT6.67 s

from openai import OpenAI

client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key="$ORCAROUTER_API_KEY",
)

INPUT$0.09/ 1M tokens

OUTPUT$0.69/ 1M tokens

p50 TTFT6.67 s7d

p95 TTFT10.00 s7d

TRAFFIC269.9Ktokens / 7d

Get the Qwen3.5-27B API →▶ Try in playground </> Use via API

Code samples

Call from any SDK

OpenAI-compatible — keep the SDK you already use

OpenAI SDKhttps://api.orcarouter.ai/v1

from openai import OpenAI

client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key="$ORCAROUTER_API_KEY",
)

response = client.chat.completions.create(
    model="qwen/qwen3.5-27b",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Supported parameters

enable_search
enable_thinking
include_reasoning
logprobs
max_tokens
n
parallel_tool_calls
presence_penalty
reasoning
repetition_penalty
response_format
seed
stop
stream
stream_options
temperature
thinking_budget
tool_choice
tools
top_k
top_logprobs
top_p

Pricing

Tier	Input / 1M tokens	Output / 1M tokens
≤ 128K	$0.086	$0.688
≤ 256K	$0.258	$2.064
Tier selected by input token count of each request

Cost calculator

Tokens / month10MM

70%

Estimate based on list price

Tiered pricing — this estimate uses base-tier rates.

Token & cost estimator

Expected output tokens

Input tokens: 20Cost per request: $0.000346

Estimate only — actual token counts depend on the provider's tokenizer.

Performance

last 7 days

p50 TTFT

6.67 s

Output speed

56.4 tok/s

p95 TTFT

10.00 s

Error rate

Public benchmarks

Last evaluated 2026-06-25

59.3

AA Coding

Better than 88% of models compared

#13 of 106

62.3

AA Intelligence

Better than 89% of models compared

#12 of 110

62.3

AA Math

Better than 48% of models compared

#42 of 81

GPQA Diamond

54.3 index

Humanity's Last Exam

22.2

IFBench

75.6

Long-Context Recall

67.3

MMLU-Pro

65.3 index

SciCode

39.5

TerminalBench Hard

32.6

τ²-Bench

52.3 index

Source: artificialanalysis.ai

How it compares

	Qwen3.5-27B	qwen/qwen3-max-preview	Qwen3.5 397B A17B	qwen/qwen3.5-plus
Input $/M	$0.09	$0.86	$0.17	$0.12
Output $/M	$0.69	$3.44	$1.03	$0.69
Context	33K	262K	33K	1.0M
Quality	6/10	8/10	8/10	8/10
Compare side-by-side		Compare side-by-side	Compare side-by-side	Compare side-by-side

More from Qwen

See all models from qwen →

Qwen3.6 35B A3BCheapest

qwen/qwen3.6-35b-a3b

$0.25 in · $1.49 out / 1M

262.1K ctx· quality 8/10

Compare side-by-side

Qwen3.6 Plus

qwen/qwen3.6-plus

$0.50 in · $3.00 out / 1M

1.05M ctx· quality 8/10

Compare side-by-side

Qwen3.7 Plus

qwen/qwen3.7-plus

$0.35 in · $1.42 out / 1M

1M ctx· quality 8/10

Compare side-by-side

FAQ

How much does Qwen: Qwen3.5-27B cost on OrcaRouter?

Qwen: Qwen3.5-27B is priced at $0.09 per 1M input tokens and $0.69 per 1M output tokens via OrcaRouter. Pricing is pulled live from the routing layer.

What is Qwen: Qwen3.5-27B's context window?

Qwen: Qwen3.5-27B supports a context window of 33K tokens. Use long-context features (RAG, summarisation) up to that limit.

How do I call Qwen: Qwen3.5-27B via the OpenAI SDK?

Set OpenAI base_url to https://api.orcarouter.ai/v1, supply your OrcaRouter API key, and pass model="qwen/qwen3.5-27b" in the chat.completions.create call.

Does OrcaRouter rate-limit Qwen: Qwen3.5-27B?

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

Paste into your blog post

Qwen: Qwen3.5-27B•$0.09/M in•6666ms p50•via OrcaRouter

HTML <a href="https://www.orcarouter.ai/models/qwen/qwen3.5-27b" target="_blank"> <img src="https://www.orcarouter.ai/embed/qwen/qwen3.5-27b.svg" alt="Qwen: Qwen3.5-27B on OrcaRouter" /> </a>

Markdown [![Qwen: Qwen3.5-27B](https://www.orcarouter.ai/embed/qwen/qwen3.5-27b.svg)](https://www.orcarouter.ai/models/qwen/qwen3.5-27b)

Model card as data

GET /api/public/models/qwen/qwen3.5-27bOpen

Machine-readable:/llms.txt /llms-full.txt