jishie

Granite 4.2 8B

openrouter/ibm-granite/granite-4.2-8b · family granite · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.

$0.11
Blended $/1M (3:1)
$0.1
Input $/1M
$0.15
Output $/1M
$0.25
1M in + 1M out
$0.05 −50%
Cache read $/1M
#930 of 7,000
Cheapest rank
Provider
OpenRouter (openrouter)
Kind
text (outputs text)
Context
131,072 tokens
Max output
117,964 tokens
Capabilities
tools reasoning text

Same model, other providers

“Granite 4.2 8B” is offered by 3 providers — cheapest-effective first. This one (OpenRouter) is the cheapest.

ProviderInputOutputBlendedContext
OpenRouter (this)$0.1$0.15$0.11131k
NanoGPT$0.1$0.15$0.11131k
Weights & Biases$0.1$0.15$0.11131k

Call it

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

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"ibm-granite/granite-4.2-8b","messages":[{"role":"user","content":"hello"}]}'

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

← all OpenRouter models · model index · JSON