Kimi K2.5
nano-gpt/moonshotai/kimi-k2.5 · family kimi-k2 · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools text image.
$0.78
Blended $/1M (3:1)
$0.375
Input $/1M
$2
Output $/1M
$2.38
1M in + 1M out
$0.07 −81%
Cache read $/1M
#3939 of 8,511
Cheapest rank
- Provider
- NanoGPT (
nano-gpt) - Kind
- text (outputs text)
- Context
- 262,144 tokens
- Max output
- 65,536 tokens
- Capabilities
- tools text image
Same model, other providers
“Kimi K2.5” is offered by 29 providers — cheapest-effective first. Alibaba Coding Plan is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Alibaba Coding Plan | free | free | $0.00 | 262k |
| Alibaba Token Plan (China) | free | free | $0.00 | 262k |
| Alibaba Token Plan | free | free | $0.00 | 262k |
| SCNet Token Plan | free | free | $0.00 | 262k |
| Alibaba Coding Plan (China) | free | free | $0.00 | 262k |
| NanoGPT (this) | $0.375 | $2 | $0.78 | 262k |
| Deep Infra | $0.45 | $2.25 | $0.90 | 262k |
| Meganova | $0.45 | $2.25 | $0.90 | 262k |
| Auriko | $0.45 | $2.25 | $0.90 | 262k |
| TensorX | $0.5 | $2.8 | $1.07 | 262k |
| DevPass (LLM Gateway) | $0.574 | $3.01 | $1.18 | 262k |
| Vercel AI Gateway | $0.6 | $3 | $1.20 | 256k |
| HPC-AI | $0.6 | $3 | $1.20 | 256k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at NanoGPT 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-k2.5","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):