jishie

Qwen3.8 27B

kosmik/qwen/qwen3.8-27b · family qwen · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.

$0.81
Blended $/1M (3:1)
$0.35
Input $/1M
$2.2
Output $/1M
$2.55
1M in + 1M out
$0.09 −74%
Cache read $/1M
#4405 of 9,407
Cheapest rank
Provider
Kosmik Compute (kosmik)
Kind
text (outputs text)
Context
262,144 tokens
Max output
32,768 tokens
Capabilities
tools reasoning text image

Same model, other providers

“Qwen3.8 27B” is offered by 64 providers — cheapest-effective first. AMD is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
AMDfreefree$0.00262k
IteraComputefreefree$0.00131k
engy$0.045$0.32$0.111M
DevPass (LLM Gateway)$0.08$0.35$0.151M
Entrim$0.1$0.4$0.18262k
Cortecs$0.1$0.4$0.181M
RunInfra$0.1$0.4$0.18262k
Powerspring$0.1044$0.4166$0.181M
Liquid Inference$0.08$0.525$0.19262k
EmpirioLabs AI$0.17$0.5$0.25262k
NanoGPT$0.15$0.7$0.291M
AKI.IO$0.1675$0.7257$0.31262k
Kosmik Compute (this)$0.35$2.2$0.81262k

Call it

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

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"qwen/qwen3.8-27b","messages":[{"role":"user","content":"hello"}]}'

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

← all Kosmik Compute models · model index · JSON