jishie

Qwen3.8 27B

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

$0.71
Blended $/1M (3:1)
$0.25
Input $/1M
$2.1
Output $/1M
$2.35
1M in + 1M out
$0.06 −76%
Cache read $/1M
#3068 of 6,819
Cheapest rank
Provider
CrofAI (crof)
Kind
text (outputs text)
Context
262,144 tokens
Max output
262,144 tokens
Capabilities
tools reasoning text image video

Same model, other providers

“Qwen3.8 27B” is offered by 16 providers — cheapest-effective first. RunInfra is the cheapest at $0.18 blended.

ProviderInputOutputBlendedContext
RunInfra$0.1$0.4$0.18262k
EmpirioLabs AI$0.17$0.5$0.25262k
NanoGPT$0.2$1.4$0.50262k
CrofAI (this)$0.25$2.1$0.71262k
AKI.IO$0.3$2.2$0.78262k
Kosmik Compute$0.35$2.2$0.81262k
Cortecs$0.334$2.45$0.86262k
Kilo Gateway$0.425$2.55$0.96262k
IteraCompute$0.35$3$1.01262k
Deep Infra$0.4$3$1.05262k
OpenRouter$0.4$3$1.051M
Weights & Biases$0.4$3$1.05262k
Eden AI$0.5$3$1.131M

Call it

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

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

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

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

← all CrofAI models · model index · JSON