Kimi K2.7 Code Highspeed
gmicloud/moonshotai/kimi-k2.7-code-highspeed · family kimi-k2 · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$3.42
Blended $/1M (3:1)
$1.9
Input $/1M
$8
Output $/1M
$9.90
1M in + 1M out
$0.38 −80%
Cache read $/1M
#5920 of 7,708
Cheapest rank
- Provider
- GMI Cloud (
gmicloud) - Kind
- text (outputs text)
- Context
- 262,144 tokens
- Max output
- 262,144 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“Kimi K2.7 Code Highspeed” is offered by 9 providers — cheapest-effective first. AIHubMix is the cheapest at $3.42 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| AIHubMix | $1.9 | $8 | $3.42 | 262k |
| GMI Cloud (this) | $1.9 | $8 | $3.42 | 262k |
| EmpirioLabs AI | $1.9 | $8 | $3.42 | 256k |
| Ofox | $1.9 | $8 | $3.42 | 262k |
| Merge Gateway | $1.9 | $8 | $3.42 | 262k |
| Eden AI | $1.9 | $8 | $3.42 | 262k |
| DevPass (LLM Gateway) | $1.9 | $8 | $3.42 | 262k |
| Moonshot AI (China) | $1.9 | $8 | $3.42 | 262k |
| Moonshot AI | $1.9 | $8 | $3.42 | 262k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at GMI Cloud 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-highspeed","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):