jishie

GPT OSS 20B

oci/openai.gpt-oss-20b · family gpt-oss · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.

$0.13
Blended $/1M (3:1)
$0.07
Input $/1M
$0.3
Output $/1M
$0.37
1M in + 1M out
Cache read $/1M
#1109 of 7,381
Cheapest rank
Provider
OCI Generative AI (oci)
Kind
text (outputs text)
Context
128,000 tokens
Max output
16,384 tokens
Capabilities
tools reasoning text

Same model, other providers

“GPT OSS 20B” is offered by 25 providers — cheapest-effective first. Kenari is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
Kenarifreefree$0.00131k
Nvidiafreefree$0.00131k
QVACfreefree$0.00131k
LMStudiofreefree$0.00131k
Kilo Gateway$0.02$0.1$0.04131k
OpenRouter$0.03$0.13$0.06131k
Vercel AI Gateway$0.03$0.14$0.06131k
Deep Infra$0.03$0.14$0.06131k
Cortecs$0.045$0.167$0.08131k
DevPass (LLM Gateway)$0.04$0.19$0.08131k
Clarifai$0.045$0.18$0.08131k
FastRouter$0.05$0.2$0.09131k
OCI Generative AI (this)$0.07$0.3$0.13128k

Call it

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

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"openai.gpt-oss-20b","messages":[{"role":"user","content":"hello"}]}'

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

← all OCI Generative AI models · model index · JSON