Qwen3.5 397B-A17B

llmgateway/qwen35-397b-a17b · family qwen · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtextimagevideoaudio.

$1.35Blended $/1M (3:1)

$0.6Input $/1M

$3.6Output $/1M

$4.201M in + 1M out

—Cache read $/1M

#3498 of 5,000Cheapest rank

Provider: LLM Gateway (llmgateway)
Context: 262,144 tokens
Max output: 65,536 tokens
Capabilities: toolsreasoningtextimagevideoaudio

Same model, other providers

“Qwen3.5 397B-A17B” is offered by 9 providers — cheapest-effective first. UnoRouter is the cheapest at $0.00 blended.

Provider	Input	Output	Blended	Context
UnoRouter	free	free	$0.00	262k
EmpirioLabs AI	$0.172	$1.032	$0.39	256k
OrcaRouter	$0.172	$1.032	$0.39	262k
CrofAI	$0.35	$1.75	$0.70	262k
Vultr	$0.3	$2	$0.72	262k
SiliconFlow	$0.39	$2.34	$0.88	262k
Kilo Gateway	$0.39	$2.34	$0.88	262k
OpenRouter	$0.39	$2.34	$0.88	262k
LLM Gateway (this)	$0.6	$3.6	$1.35	262k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at LLM Gateway and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"qwen35-397b-a17b","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):