jishie

Kimi K2.7 Code

neuralwatt/kimi-k2.7-code · family kimi-k2 · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.

$1.71
Blended $/1M (3:1)
$0.95
Input $/1M
$4
Output $/1M
$4.95
1M in + 1M out
$0.095 −90%
Cache read $/1M
#5361 of 8,539
Cheapest rank
Provider
Neuralwatt (neuralwatt)
Kind
text (outputs text)
Context
262,128 tokens
Max output
262,128 tokens
Capabilities
tools reasoning text image

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 Planfreefree$0.00262k
Alibaba Token Plan (China)freefree$0.00262k
routing.run$0.275$1.1$0.48200k
Kenari$0.5714$2.86$1.14262k
NanoGPT$0.6$3$1.20262k
CoreWeave$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
OpenRouter$0.6$3.5$1.32262k
Neuralwatt (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 Neuralwatt and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"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 Neuralwatt models · model index · JSON