jishie

Grok 4

abacus/grok-4-0709 · family grok · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.

$6.00
Blended $/1M (3:1)
$3
Input $/1M
$15
Output $/1M
$18.00
1M in + 1M out
—
Cache read $/1M
#6801 of 7,708
Cheapest rank
Provider
Abacus (abacus)
Kind
text (outputs text)
Context
256,000 tokens
Max output
16,384 tokens
Capabilities
tools reasoning text image

Same model, other providers

“Grok 4” is offered by 3 providers — cheapest-effective first. This one (Abacus) is the cheapest.

ProviderInputOutputBlendedContext
Abacus (this)$3$15$6.00256k
FastRouter$3$15$6.00256k
DevPass (LLM Gateway)$3$15$6.00256k

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":"grok-4-0709","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