Claude Opus 4.8

snowflake-cortex/claude-opus-4-8 · family claude-opus · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtextimagepdf.

—Blended $/1M (3:1)

—Input $/1M

—Output $/1M

—1M in + 1M out

—Cache read $/1M

—Cheapest rank

Provider: Snowflake Cortex (snowflake-cortex)
Context: 1,000,000 tokens
Max output: 128,000 tokens
Capabilities: toolsreasoningtextimagepdf

Same model, other providers

“Claude Opus 4.8” is offered by 4 providers — cheapest-effective first. Kenari is the cheapest at $0.00 blended.

Provider	Input	Output	Blended	Context
Kenari	free	free	$0.00	1000k
UnoRouter	$0.425	$2.125	$0.85	1000k
Xpersona	$1.5	$9.25	$3.44	200k
Snowflake Cortex (this)	—	—	—	1000k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at Snowflake Cortex and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"claude-opus-4-8","messages":[{"role":"user","content":"hello"}]}'

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