Qwen/Qwen3.5-27BDeepInfra Inc.
- api
- chat
- hosting
- US
- model lab
- Alibaba (Qwen)
- weights
- open
- added
- February 2026
- model id
- deepinfra/Qwen/Qwen3.5-27B
capabilities 4/8
- input
- $0.26
- output
- $2.60
- cache write
- -
- cache read
- -
worked cost
| volume | cost |
|---|---|
| 100K in + 10K out | $0.0520 |
| 1M in + 100K out | $0.52 |
| 10M in + 1M out | $5.20 |
Requesty charges what the upstream provider charges, with no markup and no per-request fee. Prompt caching and smart routing cut the effective cost further on repeated context. Gateway pricing
no measured traffic for this endpoint yet. pricing above is the provider's own
| eval | Score as a share of 100 | /100 |
|---|---|---|
| τ²-Bench | 93.9 | |
| GPQA Diamond | 85.8 | |
| Terminal-Bench Hard | 32.6 | |
| Humanity's Last Exam | 23.9 | |
| Intelligence Index | 22.9 | |
| 5 evals | mean | 51.8 |
Scores from Artificial Analysis and public leaderboards, normalised to 100. Bar colour is the band, not the rank: green 80 and up, blue 55 and up, amber 30 and up. Benchmarks measure narrow skills, so test on your own workload before committing. Released 2026-02-24.
- retention
- none
- trains on prompts
- no
- hosted in
- US
Terms are the provider's, not Requesty's: routing a request here puts it under them. DeepInfra Privacy Policy
Need every request to stay in one jurisdiction? EU hosting routes only through EU-hosted providers.
deepinfra/Qwen/Qwen3.5-27Bthis id pins the deepinfra inc. deployment, with no routing and no failover. the managed id on the canonical page routes across all 1 providers instead
from openai import OpenAI client = OpenAI( api_key="YOUR_REQUESTY_API_KEY", base_url="https://router.requesty.ai/v1",) response = client.chat.completions.create( model="deepinfra/Qwen/Qwen3.5-27B", messages=[ {"role": "user", "content": "Explain quantum computing in one paragraph."}, ],) print(response.choices[0].message.content)
Change the base url to https://router.requesty.ai/v1, use your Requesty key, set the model to the id above. Existing OpenAI SDK code needs no other edit, and the same key reaches every other model in the catalog. Browse all models
Qwen3.5-27B is Alibaba's largest dense Qwen3.5 model, delivering near-frontier quality across reasoning, coding, and instruction following. It features a 262K token context window (extensible to 1M), thinking/reasoning mode, tool calling, multi-token prediction, and support for 201 languages. Best suited for production deployments and complex enterprise tasks requiring top-tier performance.
questions 6
How much does Qwen/Qwen3.5-27B cost?
What is the context window of Qwen/Qwen3.5-27B?
How does Qwen/Qwen3.5-27B perform on benchmarks?
What can Qwen/Qwen3.5-27B do?
How do I use Qwen/Qwen3.5-27B with the OpenAI SDK?
Can I run Qwen/Qwen3.5-27B through Requesty?
more from deepinfra inc. 8
| endpoint | ctx | in /M |
|---|---|---|
| glm-5.3-flash | 1.0M | $0.15 |
| glm-5.3 | 1.0M | $1.20 |
| deepseek-v4-pro-0813 | 1.0M | $1.30 |
| qwen3.8 | 262K | $2.00 |
| deepseek-v4-flash-0731 | 1.0M | $0.09 |
| deepseek-v4-flash-0731:flex | 1.0M | $0.07 |
| glm-5.2 | 262K | $0.75 |
| glm-5.2:flex | 1M | $0.60 |
call qwen/qwen3.5-27b through one endpoint
One key for this endpoint and 600+ other models. No markup on provider prices, automatic failover when a provider degrades, and prompt caching built in. Methodology