jishie

Qwen3.5 9B

routing-run/qwen3.5-9b · family qwen · in: text, image, video → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image video.

$0.24
Blended $/1M (3:1)
$0.16
Input $/1M
$0.48
Output $/1M
$0.64
1M in + 1M out
—
Cache read $/1M
#1917 of 7,710
Cheapest rank
Provider
routing.run (routing-run)
Kind
text (outputs text)
Context
262,144 tokens
Max output
32,000 tokens
Capabilities
tools reasoning text image video

Same model, other providers

“Qwen3.5 9B” is offered by 16 providers — cheapest-effective first. QVAC is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
QVACfreefree$0.0033k
CrofAI$0.04$0.15$0.07262k
NanoGPT$0.05$0.15$0.08256k
EmpirioLabs AI$0.09$0.13$0.10262k
Merge Gateway$0.09$0.13$0.10262k
Deep Infra$0.1$0.15$0.11262k
Kilo Gateway$0.1$0.15$0.11256k
OpenRouter$0.1$0.15$0.11262k
DevPass (LLM Gateway)$0.1$0.15$0.11262k
Cortecs$0.111$0.167$0.13262k
TensorX$0.15$0.2$0.16262k
Mixlayer$0.1$0.4$0.18262k
routing.run (this)$0.16$0.48$0.24262k

Call it

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

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"qwen3.5-9b","messages":[{"role":"user","content":"hello"}]}'

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

← all routing.run models · model index · JSON