jishie

Qwen3.8 Flash

kilo/qwen/qwen3.8-flash · family qwen · in: text, image, video → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image video.

$0.23
Blended $/1M (3:1)
$0.15
Input $/1M
$0.47
Output $/1M
$0.62
1M in + 1M out
$0.016 −89%
Cache read $/1M
#1934 of 7,978
Cheapest rank
Provider
Kilo Gateway (kilo)
Kind
text (outputs text)
Context
1,000,000 tokens
Max output
131,072 tokens
Capabilities
tools reasoning text image video

Same model, other providers

“Qwen3.8 Flash” is offered by 25 providers — cheapest-effective first. Alibaba Token Plan is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
Alibaba Token Planfreefree$0.001M
NaNfreefree$0.00262k
Alibaba Token Plan (China)freefree$0.001M
SCNet Token Planfreefree$0.001M
AIHubMix$0.1126$0.38$0.181M
Ofox$0.11$0.39$0.181M
Deep Infra$0.113$0.382$0.181M
Vancine$0.12$0.38$0.181M
Alibaba (China)$0.1188$0.4007$0.191M
CrossModel$0.13$0.43$0.211M
NanoGPT$0.14$0.42$0.21992k
Kilo Gateway (this)$0.15$0.47$0.231M
Novita AI$0.15$0.47$0.231M

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/qwen3.8-flash","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