jishie

GPT OSS 120B

pendra/gpt-oss:120b · family gpt-oss · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.

free
Blended $/1M (3:1)
free
Input $/1M
free
Output $/1M
free
1M in + 1M out
Cache read $/1M
#168 of 6,825
Cheapest rank
Provider
Pendra (pendra)
Kind
text (outputs text)
Context
131,072 tokens
Max output
32,768 tokens
Capabilities
tools reasoning text

Same model, other providers

“GPT OSS 120B” is offered by 39 providers — cheapest-effective first. This one (Pendra) is the cheapest.

ProviderInputOutputBlendedContext
Pendra (this)freefree$0.00131k
QVACfreefree$0.00131k
Kenarifreefree$0.00131k
Eden AI$0.039$0.1$0.05131k
DevPass (LLM Gateway)$0.032$0.14$0.06131k
Kilo Gateway$0.03$0.17$0.07131k
Deep Infra$0.037$0.17$0.07131k
OpenRouter$0.037$0.17$0.07131k
TensorX$0.04$0.2$0.08131k
Crusoe$0.05$0.2$0.09131k
Synthetic$0.1$0.1$0.10131k
DInference$0.0675$0.27$0.12131k
Databricks$0.072$0.28$0.12131k

Call it

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

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"gpt-oss:120b","messages":[{"role":"user","content":"hello"}]}'

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

← all Pendra models · model index · JSON