Llama 3.1 8B Instruct

openrouter/meta-llama/llama-3.1-8b-instruct · family llama · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolstext.

$0.06Blended $/1M (3:1)

$0.05Input $/1M

$0.08Output $/1M

$0.131M in + 1M out

$0.025 −50%Cache read $/1M

#609 of 5,000Cheapest rank

Provider: OpenRouter (openrouter)
Context: 131,072 tokens
Max output: 131,072 tokens
Capabilities: toolstext

Same model, other providers

“Llama 3.1 8B Instruct” 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	16k
Inference	$0.025	$0.025	$0.03	16k
Abacus	$0.02	$0.05	$0.03	128k
NovitaAI	$0.02	$0.05	$0.03	16k
OpenRouter (this)	$0.05	$0.08	$0.06	131k
NanoGPT	$0.0544	$0.085	$0.06	131k
Pioneer	$0.2	$0.2	$0.20	131k
Amazon Bedrock	$0.22	$0.22	$0.22	128k
Vercel AI Gateway	$0.22	$0.22	$0.22	128k

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":"meta-llama/llama-3.1-8b-instruct","messages":[{"role":"user","content":"hello"}]}'

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