jishie

Llama 4 Maverick 17B Instruct

abacus/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 · family llama · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools text image.

$0.25
Blended $/1M (3:1)
$0.14
Input $/1M
$0.59
Output $/1M
$0.73
1M in + 1M out
—
Cache read $/1M
#1967 of 7,708
Cheapest rank
Provider
Abacus (abacus)
Kind
text (outputs text)
Context
1,048,576 tokens
Max output
8,192 tokens
Capabilities
tools text image

Same model, other providers

“Llama 4 Maverick 17B Instruct” is offered by 5 providers — cheapest-effective first. This one (Abacus) is the cheapest.

ProviderInputOutputBlendedContext
Abacus (this)$0.14$0.59$0.251M
DevPass (LLM Gateway)$0.27$0.85$0.421M
Amazon Bedrock$0.24$0.97$0.421M
OCI Generative AI$0.72$0.72$0.72512k
Neon$0.5$1.5$0.751M

Call it

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

Most providers are OpenAI-compatible — point base_url at Abacus 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):

← all Abacus models · model index · JSON