jishie

Qwen3.5 27B

kilo/qwen/qwen3.5-27b · family qwen · in: text, image, video → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image video.

$0.54
Blended $/1M (3:1)
$0.195
Input $/1M
$1.56
Output $/1M
$1.76
1M in + 1M out
—
Cache read $/1M
#3036 of 7,708
Cheapest rank
Provider
Kilo Gateway (kilo)
Kind
text (outputs text)
Context
262,144 tokens
Max output
65,536 tokens
Capabilities
tools reasoning text image video

Same model, other providers

“Qwen3.5 27B” is offered by 14 providers — cheapest-effective first. EmpirioLabs AI is the cheapest at $0.24 blended.

ProviderInputOutputBlendedContext
EmpirioLabs AI$0.086$0.688$0.24256k
OrcaRouter$0.086$0.688$0.24262k
Merge Gateway$0.086$0.688$0.24131k
Kilo Gateway (this)$0.195$1.56$0.54262k
OpenRouter$0.195$1.56$0.54262k
SiliconFlow$0.25$2$0.69262k
Ofox$0.29$2.05$0.73262k
NanoGPT$0.27$2.16$0.74260k
Alibaba$0.3$2.4$0.82262k
Hugging Face$0.3$2.4$0.82262k
Mixlayer$0.3$2.4$0.82262k
Jalapeno Cloud$0.3$2.4$0.82262k
Deep Infra$0.26$2.6$0.84262k

Call it

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

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"qwen/qwen3.5-27b","messages":[{"role":"user","content":"hello"}]}'

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

← all Kilo Gateway models · model index · JSON