jishie

Kimi K3.1 Pro

tinfoil/kimi-k3-1-pro · family kimi-k3 · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.

$8.00
Blended $/1M (3:1)
$4
Input $/1M
$20
Output $/1M
$24.00
1M in + 1M out
$0.4 −90%
Cache read $/1M
#7734 of 8,504
Cheapest rank
Provider
Tinfoil (tinfoil)
Kind
text (outputs text)
Context
262,144 tokens
Max output
131,072 tokens
Capabilities
tools reasoning text image

Same model, other providers

“Kimi K3.1 Pro” is offered by 28 providers — cheapest-effective first. Kimi For Coding (kimi.ai) is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
Kimi For Coding (kimi.ai)freefree$0.001M
Kimi For Coding (kimi.com)freefree$0.001M
DevPass (LLM Gateway)$1.9$9.5$3.801M
Moonshot AI (China)$1.94$10.17$4.001M
Venice AI$2$10$4.001M
Ollama Cloud$2$10$4.001M
Vercel AI Gateway$2$10$4.001M
OpenRouter$2$10$4.001M
Novita AI$2$10$4.001M
OpenCode Go$2$10$4.001M
Merge Gateway$2$10$4.001M
Together AI$2$10$4.001M
Tinfoil (this)$4$20$8.00262k

Call it

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

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"kimi-k3-1-pro","messages":[{"role":"user","content":"hello"}]}'

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

← all Tinfoil models · model index · JSON