Alibaba Qwen · LLM API pricing
Qwen3.5 397B-A17B API pricing: cheapest provider
5 providers sell Qwen3.5 397B-A17B. DeepInfra is cheapest; the most expensive charges 1.4× as much for the same model.
- Cheapest$1.09per 1M · DeepInfra
- Input · output$0.45 / $3.00per 1M tokens
- Price gap1.4×across 5 providers
- Accuracy86.4%GPQA · none reasoning
- Context262Kmax tokens
Standard list prices in USD from each provider's pricing page · last price change Sep 28, 2026 · How we collect and rank prices
Ranked for your volume
Qwen3.5 397B-A17B monthly cost by provider
Change the monthly tokens and the ranking updates instantly, using each provider's standard list price.
More requirements: caching, context, features, provider
| Provider | Estimated / month | Input / 1M | Output / 1M | Cached input / 1M | Context |
|---|---|---|---|---|---|
1 DeepInfraInference provider - lowest for your volumePricing page | $10.50 | $0.45 | $3.00 | $0.22 | 262,144 |
2 Alibaba Cloud Model StudioModel developerSingapore (International) list price; other regions differ.Pricing page | $13.20 | $0.60 | $3.60 | Not listed | 262,144 |
3 Nebius Token FactoryCloud platformPricing page | $13.20 | $0.60 | $3.60 | Not listed | 262,144 |
4 Novita AIInference providerPricing page | $13.20 | $0.60 | $3.60 | Not listed | 262,144 |
5 ScalewayCloud platformBilled in EUR: €0.60 input, €3.60 output per 1M tokens. USD at the ECB rate of Oct 30, 2026 (1.1172).Pricing page | $14.75 | $0.6703 | $4.02 | Not listed | 256,000 |
Order depends on listed price for your volume only. No provider pays for its position.
Input volume includes the cached share, not an additional token volume. This is a list-price estimate, not a quote: cache-write charges, cache eligibility/TTL, batch discounts, long-context surcharges, regional pricing and taxes are excluded. Check the provider's terms for your workload before switching.
Accuracy: GPQA Diamond (graduate-level science questions) measured by Epoch AI (CC BY 4.0) on qwen3.5-397b-a17b_none, run Aug 7, 2026. The model is the same at every provider, though quantized deployments can score lower.
Price history
Cheapest blended price: $0.8775 on Sep 28, 2026, now $1.09 at DeepInfra (+24%).
Show all 2 steps with sources
- Sep 28, 2026: $0.8775 at SiliconFlow
- Oct 31, 2026: $1.09 at DeepInfra
Every step is a confirmed list-price change; links go to each provider's pricing page. All price changes
Switch to the cheapest provider
Already using the OpenAI SDK? Change the base URL, key and model name:
from openai import OpenAI
import os
client = OpenAI(
base_url="https://api.deepinfra.com/v1/openai",
api_key=os.environ["DEEPINFRA_API_KEY"],
)
response = client.chat.completions.create(
model="Qwen/Qwen3.5-397B-A17B",
messages=[{"role": "user", "content": "Hello"}],
)Compare Qwen3.5 397B-A17B with another model
Or pick any model
Before you pick a provider
DeepInfra lists Qwen3.5 397B-A17B 19% below the developer's own API (Alibaba Cloud Model Studio) on a blended basis. Check rate limits, data retention and model quantization before switching.
Context windows differ by provider, from 256K to 262K tokens. A cheaper host may not accept your longest prompts.
1 of 5 providers list a cached-input price. Repeated system prompts or documents can cost much less there than the standard input rate shown above.
Keep comparing
More Alibaba Qwen models
Qwen3 32B, Qwen3.8 27B, Qwen2.5-72B-Instruct, Qwen3 235B A22B Instruct 2507, Qwen3.6 35B-A3B, Qwen2.5 Coder 32B Instruct, Qwen3.8 2.4T A95B, Qwq 32B
All Alibaba Qwen API prices - All LLM API prices - Watch Qwen3.5 397B-A17B prices (RSS) - Methodology