jishie

Qwen3.5 397B A17B TEE

nano-gpt/TEE/qwen3.5-397b-a17b · family qwen · in: text → out: text · price provider-declared (via models.dev). Capabilities: text.

$1.29
Blended $/1M (3:1)
$0.55
Input $/1M
$3.5
Output $/1M
$4.05
1M in + 1M out
$0.275 −50%
Cache read $/1M
#4451 of 7,708
Cheapest rank
Provider
NanoGPT (nano-gpt)
Kind
text (outputs text)
Context
262,144 tokens
Max output
65,536 tokens
Capabilities
text

Same model, other providers

“Qwen3.5 397B A17B TEE” is offered by 2 providers — cheapest-effective first. Chutes is the cheapest at $1.09 blended.

ProviderInputOutputBlendedContext
Chutes$0.45$3$1.09262k
NanoGPT (this)$0.55$3.5$1.29262k

Call it

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

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"TEE/qwen3.5-397b-a17b","messages":[{"role":"user","content":"hello"}]}'

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

← all NanoGPT models · model index · JSON