This model was retired on 2026-06-29. The pricing below is the last-known rate, kept for migration reference.
Qwen3.5 397B A17BDeprecated
VisionTool useReasoningPrompt cachingStructured output
Context
262K
Max output
66K
Serving providers
5
Cheapest input
$0.39 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: Artificial Analysis and Hugging Face leaderboardsSpeed & latency
Output speed
90 t/s
tokens / second
Time to first token
2.27s
latency
Headline indices
Intelligence Index
34.3
of 100
Coding Index
48.2
of 100
Agentic Index
19.8
of 100
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| AA-Briefcase | 2% | — | — | |||||||||||||
| AIME 2026 | 93% | default | — | |||||||||||||
| APEX Agents | 15% | default | — | |||||||||||||
| Automation Bench | 0.1 | default | — | |||||||||||||
| CritPt | 2% | default | — | |||||||||||||
| ||||||||||||||||
| EvalComputeProxy | 451.5 | default | — | |||||||||||||
| ||||||||||||||||
| GDPval | 964.2 | default | — | |||||||||||||
| GPQA Diamond | 89% | default | — | |||||||||||||
| ||||||||||||||||
| Harvey Lab | 0.7 | default | — | |||||||||||||
| Humanity's Last Exam | 29% | default | — | |||||||||||||
| ||||||||||||||||
| IFBench | 79% | default | — | |||||||||||||
| ||||||||||||||||
| IT-Bench SRE | 34% | default | — | |||||||||||||
| Long-Context Reasoning | 73% | default | — | |||||||||||||
| ||||||||||||||||
| MMMU-Pro | 77% | default | — | |||||||||||||
| ||||||||||||||||
| Omniscience | -30.8 | default | — | |||||||||||||
| ||||||||||||||||
| Omniscience Accuracy | 0.3 | default | — | |||||||||||||
| ||||||||||||||||
| Omniscience Non Hallucination | 0.2 | reasoning: false | — | |||||||||||||
| ||||||||||||||||
| SciCode | 42% | default | — | |||||||||||||
| ||||||||||||||||
| SWE-bench Verified | 76% | default | — | |||||||||||||
| TerminalBench Hard | 41% | default | — | |||||||||||||
| ||||||||||||||||
| TerminalBench v2.1 | 51% | default | — | |||||||||||||
| τ-bench Banking | 13% | default | — | |||||||||||||
| τ²-bench | 96% | default | — | |||||||||||||
| ||||||||||||||||
Pricing by serving provider
last-known · per 1M tokens · click a provider to expand| Serving provider | Input /1M | Output /1M | Endpoints | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| OpenRouter | $0.39 | $2.34 | 1 | ||||||||||||||||
| |||||||||||||||||||
| DeepInfra | $0.45 | $3.00 | 1 | ||||||||||||||||
| |||||||||||||||||||
| Together AI | $0.60 | $3.60 | 1 | ||||||||||||||||
| |||||||||||||||||||
| Novita | $0.60 | $3.60 | 1 | ||||||||||||||||
| |||||||||||||||||||
| Scaleway | $0.60 | $3.60 | 1 | ||||||||||||||||
| |||||||||||||||||||
Price history
input + output $/1M since we started tracking Input Output
Input down 35% since first tracked
Cost calculator
estimate your monthly spend on this model$265
estimated / month
Model IDs
copy the exact identifier for your platformqwen/qwen3.5-397b-a17bdeepinfra/Qwen/Qwen3.5-397B-A17Btogether_ai/Qwen/Qwen3.5-397B-A17Bnovita/qwen/qwen3.5-397b-a17bscaleway/qwen/qwen3.5-397b-a17b
Frequently asked questions
Qwen3.5 397B A17B pricing, context and availabilityIs Qwen3.5 397B A17B still available?
Qwen3.5 397B A17B was retired on 2026-06-29. The pricing on this page is the last-known rate, kept for migration reference.
How much did Qwen3.5 397B A17B cost?
Qwen3.5 397B A17B's last-known pricing, before it was retired on 2026-06-29, was $0.39 per 1M input tokens and $2.34 per 1M output tokens.
What was the context window of Qwen3.5 397B A17B?
Qwen3.5 397B A17B had a 262K token context window and could return up to 66K output tokens.
What could Qwen3.5 397B A17B do?
Qwen3.5 397B A17B supported image input (vision), tool use, reasoning, prompt caching and structured output.
Other Alibaba models
compare pricing across the Alibaba lineupQwen3 32B$0.08/1M · 8 providersQwen3.6 35B A3B$0.10/1M · 7 providersQwQ 32B$0.15/1M · 7 providersQwen3 Next 80B A3B Instruct$0.09/1M · 6 providersQwen3 235B A22b Instruct 2507$0.09/1M · 6 providersQwen3 Next 80B A3B Thinking$0.14/1M · 6 providersQwen3.6 27B$0.15/1M · 6 providersQwen3 30B A3B$0.09/1M · 5 providers
Popular comparisons
head-to-head pages featuring Qwen3.5 397B A17B
Qwen3.5 397B A17B vs Claude Fable 5side-by-side pricing & benchmarks Qwen3.5 397B A17B vs Claude Opus 4.8side-by-side pricing & benchmarks Qwen3.5 397B A17B vs Claude Sonnet 5side-by-side pricing & benchmarks
Qwen3.5 397B A17B vs DeepSeek V4 Pro 0423side-by-side pricing & benchmarks
Qwen3.5 397B A17B vs Gemini 3.1 Pro Previewside-by-side pricing & benchmarks Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI