Qwen 3.6 Plus
Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference.
qwen-3.6-plusReleased 2 Apr 2026 (Apr 2026)Pricing
List prices at Kyma API, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.439 | $2.63 | |
| Prompts over 256K tokens | $1.75 | $5.26 |
What it costs a month
At Kyma API list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$329
- RAG over documents2,000 requests a day, 8K in / 0.6K out$305
- Coding agent1,000 requests a day, 40K in / 2K out$685
- Overnight batch20,000 requests a day, 4K in / 0.4K out$1,685
Where to run it
1 host serve Qwen 3.6 Plus. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Kyma APICloud qwen-3.6-plus | $0.439 / $2.63 | qwen-3.6-plus |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- TextImages
- Produces
- Text
- Features
- Prompt caching
- Open weights
- License: Apache-2.0Runtimes: Ollama, SGLang, llama.cpp, vLLM
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than Kyma API.
Smaller Alibaba Qwen models
No cheaper Alibaba Qwen model keeps its key capabilities.
Other frontier labs
- 14% less
- 53% less
- 80% less
- 80% less
Open-weight picks
- 31% less
- 35% less
- 47% less
- 51% less
Model line
Newer and older versions, at each lab's own price.
- Jun 2026Qwen3.7 PlusLatestNot listed
- Jun 2026Qwen 3.7 Plus$0.432 / $1.73
- Apr 2026Qwen3.5 PlusNot listed
- Apr 2026Qwen3.6 Plus$0.50 / $3.00
- Apr 2026Qwen 3.6 PlusThis page$0.439 / $2.63
Call it
Using Kyma API's API.
from litellm import completion
response = completion(
model="kyma/qwen-3.6-plus",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Qwen 3.6 Plus cost?
On Kyma API, Qwen 3.6 Plus costs $0.439 per million input tokens and $2.63 per million output tokens.
Which APIs offer Qwen 3.6 Plus?
Qwen 3.6 Plus runs on 1 API: Kyma API.
What is Qwen 3.6 Plus's context window?
1M tokens, with up to 66K tokens in one reply.
Is Qwen 3.6 Plus being retired?
No retirement date is scheduled for it on any API we track.
Is there a newer version of Qwen 3.6 Plus?
Yes. Qwen3.7 Plus is the newest model in this line, released on 3 Jun 2026.
What are cheaper alternatives to Qwen 3.6 Plus?
Models that cost less and keep most of what it can do: Gemini 3.5 Flash Lite on Google AI Studio (14% less), GPT-5.4 Nano on OpenAI (53% less) and Kimi K2.7 Code on CLF AI Gateway (31% less). Savings are on a mix of 3 input tokens to 1 output token.
When was Qwen 3.6 Plus released?
Alibaba Qwen released it on 2 Apr 2026.
What is Qwen 3.6 Plus's API model id?
Use qwen-3.6-plus with Kyma API.
Sources
Raw catalog entry for qwen-3.6-plus on Kyma API
{
"max_input_tokens": 1000000,
"max_output_tokens": 65536,
"input_cost_per_token": 4.388e-7,
"output_cost_per_token": 0.000002633,
"input_cost_per_token_above_256k_tokens": 0.000001755,
"output_cost_per_token_above_256k_tokens": 0.000005265,
"litellm_provider": "kyma",
"mode": "chat",
"supports_function_calling": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_pdf_input": false
}