Qwen 3.7 Max
Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series.
qwen-3.7-maxReleased 21 May 2026 (May 2026)Pricing
List prices at Kyma API, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $2.07 | $6.21 | |
| Cached input 92% off input | $0.169 | 92% off input |
What it costs a month
At Kyma API list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$916
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$761
- Coding agent1,000 requests a day, 40K in / 2K out, cached$1,260
- Overnight batch20,000 requests a day, 4K in / 0.4K out$6,460
Where to run it
1 host serve Qwen 3.7 Max. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Kyma APICloud qwen-3.7-max | $2.07 / $6.21 | qwen-3.7-max |
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
- Text
- 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
- 3% less
- 3% less
- 36% less
- 94% less
Open-weight picks
- 3% less
- 44% less
- 72% less
- 74% less
Model line
Newer and older versions, at each lab's own price.
- Nov 2026Qwen4 MaxLatest$1.50 / $4.50
- Sep 2026Qwen3.8 Max$2.00 / $6.00
- UndatedQwen 3.8 Max$2.23 / $6.68
- May 2026Qwen3.7 Max$2.50 / $7.50
- May 2026Qwen 3.7 MaxThis page$2.07 / $6.21
- Jan 2026Qwen3 MaxNot listed
Call it
Using Kyma API's API.
from litellm import completion
response = completion(
model="kyma/qwen-3.7-max",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Qwen 3.7 Max cost?
On Kyma API, Qwen 3.7 Max costs $2.07 per million input tokens and $6.21 per million output tokens. Cached input costs $0.169 per million tokens.
Which APIs offer Qwen 3.7 Max?
Qwen 3.7 Max runs on 1 API: Kyma API.
What is Qwen 3.7 Max's context window?
1M tokens, with up to 33K tokens in one reply.
Is Qwen 3.7 Max being retired?
No retirement date is scheduled for it on any API we track.
Is there a newer version of Qwen 3.7 Max?
Yes. Qwen4 Max is the newest model in this line, released on 16 Nov 2026.
What are cheaper alternatives to Qwen 3.7 Max?
Models that cost less and keep most of what it can do: Gemini 4 Hydrogen on Google AI Studio (3% less), Grok 4.7 on xAI (3% less) and Qwen3.8.2 4T A95B on DeepInfra (3% less). Savings are on a mix of 3 input tokens to 1 output token.
When was Qwen 3.7 Max released?
Alibaba Qwen released it on 21 May 2026.
What is Qwen 3.7 Max's API model id?
Use qwen-3.7-max with Kyma API.
Sources
Raw catalog entry for qwen-3.7-max on Kyma API
{
"max_input_tokens": 1000000,
"max_output_tokens": 32768,
"input_cost_per_token": 0.000002071,
"cache_read_input_token_cost": 1.6875e-7,
"output_cost_per_token": 0.000006207,
"litellm_provider": "kyma",
"mode": "chat",
"supports_function_calling": true,
"supports_vision": false,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_pdf_input": false
}