Qwen2-VL (72B) Instruct
oah/qwen2-vlDeploy Qwen2-VL (72B) Instruct with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
Together.ai
Input: $1.20/MOutput: $1.20/M
Why deploy Qwen through OpenSourceAIHub?
Automatic PII Redaction
Every Qwen request is scanned for 28+ PII entity types — SSNs, credit cards, emails, API keys, and more — before it reaches any provider.
Smart Cost Routing
Qwen is available across 3 providers. Our Smart Router picks the cheapest one per-request. 25% managed markup / 0% on Pro BYOK.
Zero Code Changes
Change two lines in your OpenAI SDK — base_url and api_key — and every request flows through the Hub. Full backward compatibility.
Full Observability
Per-request logging of token counts, latency, DLP violations, and cost. Never wonder what your AI spend is again.
Qwen Strengths
- Best-in-class Chinese and Asian language support
- Competitive English performance in Qwen 2.5 series
- Open-weights for transparency and fine-tuning
- Strong coding variants (Qwen-Coder)
- Multiple sizes from 0.5B to 72B for flexible deployment
Available Qwen Models (18)
Qwen 2.5 14B Instruct
oah/qwen2.5Deploy Qwen 2.5 14B Instruct with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
Together.aiDeepInfra
Input: $0.12/MOutput: $0.30/M
Qwen/Qwen3-235B-A22B
oah/qwen3Deploy Qwen/Qwen3-235B-A22B with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
Together.aiGroqDeepInfra
ReasoningInput: Free/MOutput: Free/M
Qwen3 235B A22B Instruct 2507 FP8 Throughput
oah/qwen3-235b-a22b-instruct-2507-tputDeploy Qwen3 235B A22B Instruct 2507 FP8 Throughput with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
Together.ai
ReasoningInput: $0.20/MOutput: $0.60/M
Qwen3 235B A22B Thinking 2507 FP8
oah/qwen3-235b-a22b-thinkingDeploy Qwen3 235B A22B Thinking 2507 FP8 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
Together.aiDeepInfra
ReasoningInput: $0.30/MOutput: $2.90/M
Qwen3 Coder 480B A35B Instruct Fp8
oah/qwen3-coderDeploy Qwen3 Coder 480B A35B Instruct Fp8 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
Together.aiDeepInfra
ReasoningInput: $0.29/MOutput: $1.20/M
Qwen3 Coder Next Fp8
oah/qwen3-coder-nextDeploy Qwen3 Coder Next Fp8 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
Together.ai
ReasoningInput: $0.50/MOutput: $1.20/M
Qwen3 Next 80B A3b Instruct
oah/qwen3-nextDeploy Qwen3 Next 80B A3b Instruct with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
Together.aiDeepInfra
ReasoningInput: $0.14/MOutput: $1.40/M
Qwen3-VL-8B-Instruct
oah/qwen3-vlDeploy Qwen3-VL-8B-Instruct with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
Together.aiDeepInfra
ReasoningInput: $0.18/MOutput: $0.68/M
Qwen3.5 35B A3b
oah/qwen3.5Deploy Qwen3.5 35B A3b with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
Together.aiDeepInfra
ReasoningInput: Free/MOutput: Free/M
Arize AI Qwen 2 1.5B Instruct
oah/qwen-2-1.5bDeploy Arize AI Qwen 2 1.5B Instruct with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
Together.ai
Input: $0.10/MOutput: $0.10/M
Qwen/Qwen-Image-Edit
oah/qwen-image-editDeploy Qwen/Qwen-Image-Edit with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
DeepInfra
Input: Free/MOutput: Free/M
Qwen/Qwen-Image-Edit-Max
oah/qwen-image-edit-maxDeploy Qwen/Qwen-Image-Edit-Max with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
DeepInfra
Input: Free/MOutput: Free/M
Qwen/Qwen-Image-Max
oah/qwen-image-maxDeploy Qwen/Qwen-Image-Max with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
DeepInfra
Input: Free/MOutput: Free/M
Qwen/Qwen2.5-VL-32B-Instruct
oah/qwen2.5-vlDeploy Qwen/Qwen2.5-VL-32B-Instruct with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
DeepInfra
Input: $0.20/MOutput: $0.60/M
Qwen/Qwen3-Max
oah/qwen3-maxDeploy Qwen/Qwen3-Max with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
DeepInfra
ReasoningInput: Free/MOutput: Free/M
Qwen/Qwen3-Max-Thinking
oah/qwen3-max-thinkingDeploy Qwen/Qwen3-Max-Thinking with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
DeepInfra
ReasoningInput: Free/MOutput: Free/M
Qwen/Qwen3.5-0.8B
oah/qwen3.5-0.8bDeploy Qwen/Qwen3.5-0.8B with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
DeepInfra
ReasoningInput: Free/MOutput: Free/M
Qwen Pricing Comparison (per 1M tokens, USD)
Input / Output pricing by provider. Managed Mode adds a 25% managed markup. Pro BYOK = 0% markup.
| Model | Params | Context | Vision | Together.ai | DeepInfra | Groq |
|---|---|---|---|---|---|---|
Qwen2-VL (72B) Instruct oah/qwen2-vl | — | 33K | No | $1.20/$1.20 | — | — |
Qwen 2.5 14B Instruct oah/qwen2.5 | — | 33K | No | $0.30/$0.30 | $0.12/$0.39 | — |
Qwen/Qwen3-235B-A22B oah/qwen3 | — | — | No | Free/Free | $0.10/$0.28 | $0.29/$0.39 |
Qwen3 235B A22B Instruct 2507 FP8 Throughput oah/qwen3-235b-a22b-instruct-2507-tput | — | 262K | No | $0.20/$0.60 | — | — |
Qwen3 235B A22B Thinking 2507 FP8 oah/qwen3-235b-a22b-thinking | — | 262K | No | $0.65/$3.00 | $0.30/$2.90 | — |
Qwen3 Coder 480B A35B Instruct Fp8 oah/qwen3-coder | — | 262K | No | $2.00/$2.00 | $0.29/$1.20 | — |
Qwen3 Coder Next Fp8 oah/qwen3-coder-next | — | 262K | No | $0.50/$1.20 | — | — |
Qwen3 Next 80B A3b Instruct oah/qwen3-next | — | 262K | No | $0.15/$1.50 | $0.14/$1.40 | — |
Qwen3-VL-8B-Instruct oah/qwen3-vl | — | 262K | No | $0.18/$0.68 | — | — |
Qwen3.5 35B A3b oah/qwen3.5 | — | 262K | No | Free/Free | — | — |
Arize AI Qwen 2 1.5B Instruct oah/qwen-2-1.5b | — | 33K | No | $0.10/$0.10 | — | — |
Qwen/Qwen-Image-Edit oah/qwen-image-edit | — | — | No | — | — | — |
Qwen/Qwen-Image-Edit-Max oah/qwen-image-edit-max | — | — | No | — | — | — |
Qwen/Qwen-Image-Max oah/qwen-image-max | — | — | No | — | — | — |
Qwen/Qwen2.5-VL-32B-Instruct oah/qwen2.5-vl | — | — | No | — | $0.20/$0.60 | — |
Qwen/Qwen3-Max oah/qwen3-max | — | — | No | — | — | — |
Qwen/Qwen3-Max-Thinking oah/qwen3-max-thinking | — | — | No | — | — | — |
Qwen/Qwen3.5-0.8B oah/qwen3.5-0.8b | — | — | No | — | — | — |
Qwen Direct vs OpenSourceAIHub
What you get at each pricing tier. Hub adds security, governance, and multi-provider routing on top of raw API access.
| Mode | What You Pay | PII Redaction | Budget Caps | Routing | Audit Trail |
|---|---|---|---|---|---|
| Direct to Alibaba Cloud | Provider pricing only | None | None | Manual | None |
| Hub — Managed Mode | Provider + 25% markup | 28+ PII types | Per-key hard caps | Smart Router | Full compliance log |
| Hub — Pro BYOK ($29/mo) | Direct to provider (0% markup) | 28+ PII types | Per-key hard caps | Smart Router | Full compliance log |
Popular Use Cases
1
Chinese/Asian language applications
2
Multilingual content generation and translation
3
Budget-friendly open-source deployments
4
Fine-tuning base models for domain-specific tasks
Integration — 2 Lines
from openai import OpenAI
client = OpenAI(
base_url="https://api.opensourceaihub.ai/v1",
api_key="your_hub_api_key"
)
# Use any virtual model name from the pricing table above
response = client.chat.completions.create(
model="oah/qwen2-vl",
messages=[{"role": "user", "content": "Hello!"}]
)Use any virtual model name from the pricing table above (prefixed with oah/). Works with the standard OpenAI SDK. Every request is PII-scanned before reaching Alibaba Cloud (Open Source).
Frequently Asked Questions
What is the Qwen API pricing?
Qwen API pricing varies by model size and provider. In Managed Mode, we add a 25% markup. With Pro BYOK, pay the provider directly at 0% markup. See the pricing table above for current rates.
What is the Qwen 2.5 cost?
Qwen 2.5 cost depends on the parameter count (0.5B to 72B) and provider. Smaller variants are extremely affordable. Check the pricing comparison table above.
Is Qwen good for English tasks?
Yes. Qwen 2.5 72B is competitive with Llama 3.3 70B on English benchmarks. For Chinese and multilingual tasks, Qwen is often the best open-source choice.
Deploy Qwen with Enterprise-Grade Security
Get started with 1,000,000 free credits. Every Qwen request is PII-scanned, cost-optimized, and fully logged — zero configuration.
Not ready yet? Get notified about Qwen updates:
Explore Other Model Families
🦙Llama
Meta's open-weights Llama family is the most widely deployed open-source LLM series. Compare Llama API pricing across Gr…
🧠GPT
OpenAI's GPT family powers the majority of commercial AI applications. Compare GPT-4 API cost and OpenAI API pricing acr…
💎Gemini
Google's Gemini family offers powerful multimodal capabilities with large context windows. Compare Gemini API pricing an…
🤖Claude
Anthropic's Claude family is built with safety and reliability at its core. Compare Claude API pricing and Claude Sonnet…
🔍DeepSeek
DeepSeek has rapidly risen as a leading open-source model family, known for exceptional coding performance and cost effi…
Model registry last updated: . Pricing shown is the lowest available rate across providers (per 1M tokens, USD). Actual pricing depends on provider and plan.