jishie

Qwen3.8 2.4T A95B

tensorx/qwen/qwen3.8-2.4t-a95b · family qwen · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.

$3.38
Blended $/1M (3:1)
$2.5
Input $/1M
$6
Output $/1M
$8.50
1M in + 1M out
$0.63 −75%
Cache read $/1M
#5909 of 7,708
Cheapest rank
Provider
TensorX (tensorx)
Kind
text (outputs text)
Context
262,144 tokens
Max output
64,000 tokens
Capabilities
tools reasoning text

Same model, other providers

“Qwen3.8 2.4T A95B” is offered by 17 providers — cheapest-effective first. IteraCompute is the cheapest at $2.95 blended.

ProviderInputOutputBlendedContext
IteraCompute$1.95$5.95$2.95970k
Deep Infra$2$6$3.00262k
SiliconFlow$2$6$3.001M
Kilo Gateway$2$6$3.001M
OpenRouter$2$6$3.001M
Vercel AI Gateway$2$6$3.00262k
Charm Hyper$2$6$3.001M
Fireworks AI$2$6$3.00262k
AIHubMix$2$6$3.00262k
Eden AI$2$6$3.001M
Requesty$2$6$3.00262k
DevPass (LLM Gateway)$2$6$3.001M
TensorX (this)$2.5$6$3.38262k

Call it

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

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"qwen/qwen3.8-2.4t-a95b","messages":[{"role":"user","content":"hello"}]}'

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

← all TensorX models · model index · JSON