jishie

Qwen3.5 122B-A10B

tensorx/qwen/qwen3.5-122b-a10b · family qwen · in: text, image, video, audio → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image video audio.

$1.25
Blended $/1M (3:1)
$0.5
Input $/1M
$3.5
Output $/1M
$4.00
1M in + 1M out
$0.125 −75%
Cache read $/1M
#4431 of 7,708
Cheapest rank
Provider
TensorX (tensorx)
Kind
text (outputs text)
Context
262,144 tokens
Max output
262,144 tokens
Capabilities
tools reasoning text image video audio

Same model, other providers

“Qwen3.5 122B-A10B” is offered by 14 providers — cheapest-effective first. Nvidia is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
Nvidiafreefree$0.00262k
EmpirioLabs AI$0.115$0.917$0.32256k
OrcaRouter$0.115$0.917$0.32262k
SiliconFlow$0.26$2.08$0.72262k
Kilo Gateway$0.26$2.08$0.72262k
OpenRouter$0.26$2.08$0.72262k
Neon$0.22$2.2$0.72262k
Ofox$0.29$2.29$0.79256k
Deep Infra$0.29$2.4$0.82262k
Alibaba$0.4$3.2$1.10262k
Hugging Face$0.4$3.2$1.10262k
Jalapeno Cloud$0.4$3.2$1.10262k
TensorX (this)$0.5$3.5$1.25262k

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/qwen3.5-122b-a10b","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