jishie

Qwen3.6 35B-A3B

zenifra/alibaba/qwen3.6-35b-a3b · family qwen · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.

$0.26
Blended $/1M (3:1)
$0.19
Input $/1M
$0.48
Output $/1M
$0.67
1M in + 1M out
—
Cache read $/1M
#2087 of 7,717
Cheapest rank
Provider
Zenifra (zenifra)
Kind
text (outputs text)
Context
262,144 tokens
Max output
65,536 tokens
Capabilities
tools reasoning text

Same model, other providers

“Qwen3.6 35B-A3B” is offered by 19 providers — cheapest-effective first. NaN is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
NaNfreefree$0.00262k
QVACfreefree$0.00262k
SaladCloud AI Gateway$0.09$0.6$0.22262k
AKI.IO$0.15$0.5$0.24256k
Zenifra (this)$0.19$0.48$0.26262k
Cortecs$0.167$0.557$0.26262k
Hugging Face$0.15$0.95$0.35262k
Pioneer$0.14$1$0.35262k
Kilo Gateway$0.15$1$0.36262k
OpenRouter$0.15$1$0.36262k
SiliconFlow$0.2$1.6$0.55262k
Alibaba$0.248$1.49$0.56262k
OrcaRouter$0.248$1.49$0.56262k

Call it

jishie indexes & prices models; it does not proxy inference.

Most providers are OpenAI-compatible — point base_url at Zenifra and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"alibaba/qwen3.6-35b-a3b","messages":[{"role":"user","content":"hello"}]}'

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

← all Zenifra models · model index · JSON