Qwen3.5 397B A17B

qwen/qwen3.5-397b-a17b
VisionToolsJSONReasoning
by Qwen · 2026-02-16

Qwen3.5 397B-A17B — open-weight MoE multimodal (text/image/video), 397B total / 17B active params, 32k context (vision mode).

Endpoints:/v1/chat/completions
ctx32.8K tokens
Max output65.5K
Inputtext + image + video
Outputtext
p50 TTFT2.64 s
INPUT$0.17/ 1M tokens
OUTPUT$1.03/ 1M tokens
p50 TTFT2.64 s7d
p95 TTFT5.00 s7d
TRAFFIC458.2Ktokens / 7d
Get the Qwen3.5 397B A17B API →▶ Try in playground</> Use via API

Code samples

Call from any SDK

OpenAI-compatible — keep the SDK you already use

  • OpenAI SDKhttps://api.orcarouter.ai/v1
from openai import OpenAI

client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key="$ORCAROUTER_API_KEY",
)

response = client.chat.completions.create(
    model="qwen/qwen3.5-397b-a17b",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Supported parameters

  • enable_search
  • enable_thinking
  • include_reasoning
  • logprobs
  • max_tokens
  • n
  • parallel_tool_calls
  • presence_penalty
  • reasoning
  • repetition_penalty
  • response_format
  • seed
  • stop
  • stream
  • stream_options
  • temperature
  • thinking_budget
  • tool_choice
  • tools
  • top_k
  • top_logprobs
  • top_p

Pricing

TierInput / 1M tokensOutput / 1M tokens
≤ 128K$0.172$1.032
≤ 256K$0.430$2.58
Tier selected by input token count of each request

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $4.30

Estimate based on list price

Tiered pricing — this estimate uses base-tier rates.

Token & cost estimator

Input tokens: 20Cost per request: $0.000519

Estimate only — actual token counts depend on the provider's tokenizer.

Performance

last 7 days
p50 TTFT
2.64 s
Output speed
73.8 tok/s
p95 TTFT
5.00 s
Error rate
0%

Public benchmarks

Last evaluated 2026-02-16
41.3
AA Coding
Better than 51% of models compared
#52 of 106
45.0
AA Intelligence
Better than 55% of models compared
#50 of 110
GPQA Diamond
89.3
Humanity's Last Exam
27.3
IFBench
78.8
Long-Context Recall
65.7
SciCode
42.0
TerminalBench Hard
40.9
τ²-Bench
95.6
Source: artificialanalysis.ai

How it compares

Qwen3.5 397B A17Bqwen/qwen3-max-previewqwen/qwen3.5-plusQwen3.6 35B A3B
Input $/M$0.17$0.86$0.12$0.25
Output $/M$1.03$3.44$0.69$1.49
Context33K262K1.0M262K
Quality8/108/108/108/10
Compare side-by-sideCompare side-by-sideCompare side-by-sideCompare side-by-side

More from Qwen

See all models from qwen →
Qwen3.6 Plus
qwen/qwen3.6-plus
$0.50 in · $3.00 out / 1M
1.05M ctx· quality 8/10
 Compare side-by-side
Qwen3.7 PlusCheapest
qwen/qwen3.7-plus
$0.35 in · $1.42 out / 1M
1M ctx· quality 8/10
 Compare side-by-side
Qwen3 Max
qwen/qwen3-max
$0.36 in · $1.43 out / 1M
262.1K ctx· quality 7/10
 Compare side-by-side

FAQ

How much does Qwen: Qwen3.5 397B A17B cost on OrcaRouter?
Qwen: Qwen3.5 397B A17B is priced at $0.17 per 1M input tokens and $1.03 per 1M output tokens via OrcaRouter. Pricing is pulled live from the routing layer.
What is Qwen: Qwen3.5 397B A17B's context window?
Qwen: Qwen3.5 397B A17B supports a context window of 33K tokens. Use long-context features (RAG, summarisation) up to that limit.
How do I call Qwen: Qwen3.5 397B A17B via the OpenAI SDK?
Set OpenAI base_url to https://api.orcarouter.ai/v1, supply your OrcaRouter API key, and pass model="qwen/qwen3.5-397b-a17b" in the chat.completions.create call.
Does OrcaRouter rate-limit Qwen: Qwen3.5 397B A17B?
Per-model rate limits follow your OrcaRouter plan. Free tiers ship with conservative caps; paid tiers lift them. Check /pricing for current quotas.

Embed this badge

Paste into your blog post
Qwen: Qwen3.5 397B A17B•$0.17/M in•2642ms p50•via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/qwen/qwen3.5-397b-a17b" target="_blank"> <img src="https://www.orcarouter.ai/embed/qwen/qwen3.5-397b-a17b.svg" alt="Qwen: Qwen3.5 397B A17B on OrcaRouter" /> </a>
Markdown [![Qwen: Qwen3.5 397B A17B](https://www.orcarouter.ai/embed/qwen/qwen3.5-397b-a17b.svg)](https://www.orcarouter.ai/models/qwen/qwen3.5-397b-a17b)

Model card as data

GET /api/public/models/qwen/qwen3.5-397b-a17bOpen
Machine-readable:/llms.txt/llms-full.txt