jishie

Qwen3.6 35B A3B

neuralwatt/Qwen/Qwen3.6-35B-A3B · family qwen3.6 · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtextimage.

$0.50Blended $/1M (3:1)
$0.29Input $/1M
$1.15Output $/1M
$1.441M in + 1M out
$0.0725 −75%Cache read $/1M
#2240 of 5,000Cheapest rank
Provider
Neuralwatt (neuralwatt)
Context
131,056 tokens
Max output
131,056 tokens
Capabilities
toolsreasoningtextimage

Same model, other providers

“Qwen3.6 35B A3B” is offered by 8 providers — cheapest-effective first. Umans AI Coding Plan is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
Umans AI Coding Planfreefree$0.00262k
EmpirioLabs AI$0.07$0.42$0.16131k
NanoGPT$0.112$0.8$0.28262k
Deep Infra$0.1$0.95$0.31262k
Weights & Biases$0.25$1.25$0.50262k
Neuralwatt (this)$0.29$1.15$0.50131k
Merge Gateway$0.248$1.485$0.56262k
Scaleway$0.25$1.5$0.56128k

Call it

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"Qwen/Qwen3.6-35B-A3B","messages":[{"role":"user","content":"hello"}]}'

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