Qwen3.5-397B-A17B pricing calculator
Alibaba's large hybrid-attention MoE model; only about a quarter of layers keep a full KV cache. Pricing shown is DeepInfra's serverless rate.
- Input
- $0.45 / 1M
- Cached input
- $0.22 / 1M
- Output
- $3.00 / 1M
- Context window
- 256K
- Batch API
- No
- Reasoning
- Yes
Workload
Quick presets
1,000 tokens ≈ 750 English words.
Pro / Agent mode
Caching, batch, multi-turn loops, reasoning tokens
Cost comparison
Cheapest / month
$8.46
Llama 3.3 70B Instruct
Most expensive / month
$57.04
Qwen3.5-397B-A17B
Tokens / request
1.5K in
400 out (cheapest model)
| Remove | |||||
|---|---|---|---|---|---|
| Llama 3.3 70B InstructCheapestMeta via DeepInfra · $0.10 / $0.32 | $0.00028 | $0.278 | $8.46 | $101.47 | |
| gpt-oss-120bOpenAI via Together · $0.15 / $0.60 | $0.00047 | $0.465 | $14.15 | $169.73 | |
| DeepSeek R1-0528DeepSeek via DeepInfra · $0.50 / $2.15 | $0.00161 | $1.61 | $48.98 | $587.65 | |
| Qwen3.5-397B-A17BAlibaba via DeepInfra · $0.45 / $3.00 | $0.00187 | $1.88 | $57.04 | $684.38 |
Monthly = daily × 30.42. Prices are list prices for the standard context tier. Long-context surcharges, regional pricing and taxes are not included.Official pricing: DeepInfra ↗ · Together ↗
What Qwen3.5-397B-A17B costs for common workloads
Monthly estimates using the presets above, at list price.
| Workload | Per request / session | Monthly | Yearly |
|---|---|---|---|
| Small Chatbot1K chats/day, short prompts | $0.00117 | $35.59 | $427.05 |
| RAG App5K queries/day, 4K-token retrieved context | $0.00263 | $400.33 | $4,803 |
| Coding Agent200 sessions/day × 25 turns | $0.403 | $2,452 | $29,422 |
| Enterprise Scale250K requests/day, batched | $0.00287 | $21,857 | $262,253 |
Official pricing ↗ (Alibaba via DeepInfra) · API model ID Qwen/Qwen3.5-397B-A17B
Qwen3.5-397B-A17B pricing FAQ
How much does Qwen3.5-397B-A17B cost per 1M tokens?
Qwen3.5-397B-A17B via DeepInfra costs $0.45 per 1M input tokens and $3.00 per 1M output tokens. Cached input is $0.22 per 1M. Prices were last verified on Nov 21, 2026.
How much does one Qwen3.5-397B-A17B request cost?
A typical request with 1,000 input tokens and 500 output tokens costs about $0.00195. At 1,000 such requests per day that is $59.32 per month.
Does Qwen3.5-397B-A17B support prompt caching?
Yes. Cached input tokens cost $0.22 per 1M, 51% less than regular input. Turn on Pro mode above to model your cache hit rate.
Is there a Batch API discount for Qwen3.5-397B-A17B?
No 50% batch discount is listed for Qwen3.5-397B-A17B via DeepInfra.
What is the context window of Qwen3.5-397B-A17B?
Qwen3.5-397B-A17B supports up to 256K tokens of context.
Is Qwen3.5-397B-A17B cheaper than DeepSeek R1-0528?
For a 1,000-in / 500-out request, Qwen3.5-397B-A17B costs $0.00195 and DeepSeek R1-0528 costs $0.00158, so DeepSeek R1-0528 is 19% cheaper. Quality, speed and caching behaviour differ, so compare on your own workload above.
More AI cost tools
LLM API & Agent Cost Calculator
Compare per-request, monthly and yearly cost across 30+ models, with caching, batch and multi-turn agent modelling.
Open calculator →GBGPU & VRAM Calculator
See exactly how much VRAM a model needs (weights + KV cache + overhead) and which GPUs or Macs it fits on.
Open calculator →$/minVoice Agent Cost Calculator
Cost per minute and per call for STT + LLM + TTS + telephony voice agent stacks.
Open calculator →break-evenAPI vs Self-Hosting Break-Even
Find the monthly token volume where renting a dedicated GPU beats paying per token.
Open calculator →