jishie

Kimi K2.7 Code

nebius/moonshotai/Kimi-K2.7-Code · family kimi-k2 · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.

$1.71
Blended $/1M (3:1)
$0.95
Input $/1M
$4
Output $/1M
$4.95
1M in + 1M out
$0.15 −84%
Cache read $/1M
#5358 of 8,512
Cheapest rank
Provider
Nebius Token Factory (nebius)
Kind
text (outputs text)
Context
262,144 tokens
Max output
8,000 tokens
Capabilities
tools reasoning text

Same model, other providers

“Kimi K2.7 Code” is offered by 53 providers — cheapest-effective first. SCNet Token Plan is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
SCNet Token Planfreefree$0.00262k
Volcengine Ark Coding Planfreefree$0.00262k
Alibaba Token Plan (China)freefree$0.00262k
Alibaba Token Planfreefree$0.00262k
routing.run$0.275$1.1$0.48200k
Kenari$0.5714$2.86$1.14262k
CoreWeave$0.6$3$1.20262k
NanoGPT$0.6$3$1.20262k
Melious$0.6133$3.29$1.28262k
Cortecs$0.656$3.3$1.32262k
DevPass (LLM Gateway)$0.737$3.08$1.32262k
Kilo Gateway$0.6$3.5$1.32262k
Nebius Token Factory (this)$0.95$4$1.71262k

Call it

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

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"moonshotai/Kimi-K2.7-Code","messages":[{"role":"user","content":"hello"}]}'

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

← all Nebius Token Factory models · model index · JSON