jishie

Llama 4 Maverick 17B 128E Instruct

io-net/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 · family llama · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolstextimage.

$0.26Blended $/1M (3:1)
$0.15Input $/1M
$0.6Output $/1M
$0.751M in + 1M out
$0.075 −50%Cache read $/1M
#1548 of 5,000Cheapest rank
Provider
IO.NET (io-net)
Context
430,000 tokens
Max output
4,096 tokens
Capabilities
toolstextimage

Same model, other providers

“Llama 4 Maverick 17B 128E Instruct” is offered by 3 providers — cheapest-effective first. Nvidia is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
Nvidiafreefree$0.00128k
IO.NET (this)$0.15$0.6$0.26430k
Vertex$0.35$1.15$0.55524k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at IO.NET and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","messages":[{"role":"user","content":"hello"}]}'

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