Fresh paint, wet floors — we're rebuilding CostOfToken into a cross-provider price comparison. Some corners are still under construction; the full version is coming up soon.

Qwen/Qwen3.5-397B-A17B pricing

Qwen3.5-397B-A17B is Alibaba's most capable Qwen3.5 model, a Mixture-of-Experts architecture with 397B total parameters and 17B activated per token. It features a 262K token context window (extensible to 1M with YaRN), thinking/reasoning mode, tool calling with MCP integration, and support for 201 languages. Qwen/Qwen3.5-397B-A17B from DeepInfra costs $0.450 per 1M input tokens and $3.00 per 1M output tokens. Cached input is $0.220 per 1M. Context window 262,144 tokens.

API id Qwen/Qwen3.5-397B-A17B · DeepInfra · source · updated 2026-09-25 · general-purpose

$0.450
Input / 1M tokens
$3.00
Output / 1M tokens
$0.220
Cached input / 1M
262K
Context window

Qwen/Qwen3.5-397B-A17B specifications

Provider
DeepInfra
API id
Qwen/Qwen3.5-397B-A17B
Model type
general-purpose
Context window
262K tokens
Max output
not published
Currency
USD
Price source
Provider API
Last checked
2026-09-25

Qwen3.5 397B A17B across providers

The same model, priced by every seller we track. Ranked by the cost of 1M input + 1M output tokens, standard tier; savings measured against buying from the vendor directly.

ProviderInput /1MCached /1MOutput /1M1M in + 1M outvs vendor
DeepInfraHostCheapestviewing
$0.450$0.220$3.00$3.45−15%
$0.550$0.225$3.50$4.05—
$0.550$0.225$3.50$4.05—
$0.600$0.350$3.60$4.20+4%

What Qwen/Qwen3.5-397B-A17B costs in practice

Estimated cost at common usage volumes
WorkloadInput tokensOutput tokensEstimated cost
Short chat turn1,000500$0.0019
Document summary50,0002,000$0.03
1M tokens in, 200K out1,000,000200,000$1.05

Estimates use the standard tier and ignore caching discounts, so real bills with repeated prompt prefixes are typically lower.

Common questions

How much does Qwen/Qwen3.5-397B-A17B cost per 1M tokens?
Qwen/Qwen3.5-397B-A17B costs $0.450 per 1M input tokens and $3.00 per 1M output tokens on the standard tier. Cached input is $0.220 per 1M.
What is Qwen/Qwen3.5-397B-A17B's context window?
Qwen/Qwen3.5-397B-A17B accepts up to 262,144 tokens in a single request.
Is there a cheaper DeepInfra model than Qwen/Qwen3.5-397B-A17B?
Yes. deepseek-ai/DeepSeek-V4-Flash is $0.090 per 1M input tokens versus $0.450 for Qwen/Qwen3.5-397B-A17B, with a 1,048,576 token context window.
Where does this Qwen/Qwen3.5-397B-A17B price come from?
From the OpenRouter catalogue, because DeepInfra does not publish machine-readable pricing. OpenRouter is a reseller, so its rate can differ from DeepInfra's own — verify before committing spend.

Head-to-head comparisons

Other DeepInfra models

See all DeepInfra pricing →