GPT OSS 20B

vercel/openai/gpt-oss-20b · family gpt-oss · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtext.

$0.09Blended $/1M (3:1)

$0.05Input $/1M

$0.2Output $/1M

$0.251M in + 1M out

—Cache read $/1M

#711 of 5,000Cheapest rank

Provider: Vercel AI Gateway (vercel)
Context: 131,072 tokens
Max output: 8,192 tokens
Capabilities: toolsreasoningtext

Same model, other providers

“GPT OSS 20B” is offered by 9 providers — cheapest-effective first. Nvidia is the cheapest at $0.00 blended.

Provider	Input	Output	Blended	Context
Nvidia	free	free	$0.00	131k
QVAC	free	free	$0.00	131k
Kenari	free	free	$0.00	131k
LMStudio	free	free	$0.00	131k
Kilo Gateway	$0.03	$0.13	$0.06	131k
OpenRouter	$0.03	$0.13	$0.06	131k
Deep Infra	$0.03	$0.14	$0.06	131k
LLM Gateway	$0.04	$0.15	$0.07	131k
Vercel AI Gateway (this)	$0.05	$0.2	$0.09	131k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at Vercel AI Gateway 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):