Kimi For Coding (K2.8 Preview)
meldport/kimi-for-codingKimi For Coding (K2.8 Preview) is available through Meldport as kimi-for-coding. Published capabilities: Text, Vision, Cache.
MODEL OVERVIEW
About Moonshot AI Kimi For Coding (K2.8 Preview)
Kimi For Coding (K2.8 Preview) is available through Meldport as kimi-for-coding. Published capabilities: Text, Vision, Cache.
Use the published model ID in requests to Meldport's API. Check the current pricing, context window, and supported capabilities on this page before sending production traffic. See the quickstart for a request example.
GOOD FIT FOR
- Text generation, extraction, and automation
- Image-aware prompts and visual analysis
- Tool calling and agent workflows
BEFORE YOU SHIP
- Confirm the published capabilities, context limit, and current price against your workload before sending production traffic.
- Test tool call parsing and error handling before production.
- Verify image input size and format limits for your use case.
TECHNICAL SPECIFICATIONS
What this model supports
| Model ID | meldport/kimi-for-coding |
|---|---|
| Publisher | Moonshot AI |
| Capabilities | Text, Vision, Cache, Tools |
| Context window | 1.048576M |
| Lifecycle | active |
| Verified | Nov 1, 2026 |
CURRENT RATES
Pricing
| Metric | Rate | Unit |
|---|---|---|
| Input | $0.475 | per million tokens |
| Output | $2 | per million tokens |
| Cache hit (10% of standard price) | $0.0475 | per million tokens |
| Minimum charge | $0.00001 | per request |
Prices are shown before traffic is sent. Eligible opt-in deterministic, non-stream cache hits are charged at 10% of the current standard price; streaming and tool calls bypass cache. Request billing is recorded in the wallet ledger.
QUICKSTART
Call this model
Use the stable model ID above with the same endpoint across languages.
curl https://meldport-api.eidosstack.com/v1/chat/completions \
-H "Authorization: Bearer $MELDPORT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "meldport/kimi-for-coding",
"messages": [{"role": "user", "content": "Hello"}]
}'import os
import requests
response = requests.post(
"https://meldport-api.eidosstack.com/v1/chat/completions",
headers={
"Authorization": f"Bearer {os.environ['MELDPORT_API_KEY']}",
},
json={
"model": "meldport/kimi-for-coding",
"messages": [{"role": "user", "content": "Hello"}],
},
)
print(response.json())const response = await fetch(
"https://meldport-api.eidosstack.com/v1/chat/completions",
{
method: "POST",
headers: {
Authorization: "Bearer " + process.env.MELDPORT_API_KEY,
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "meldport/kimi-for-coding",
messages: [{ role: "user", content: "Hello" }],
}),
},
);
console.log(await response.json());COMMON QUESTIONS
About this model
What is Kimi For Coding (K2.8 Preview) best for?
Kimi For Coding (K2.8 Preview) is available through Meldport as kimi-for-coding. Published capabilities: Text, Vision, Cache.
Which capabilities does Kimi For Coding (K2.8 Preview) support?
This model currently publishes Text, Vision, Cache, Tools support through Meldport.
How is Kimi For Coding (K2.8 Preview) priced?
Requests are billed per token. Input costs $0.475 per million tokens and output costs $2 per million tokens. Cache read hits cost $0.0475 per million tokens. A minimum charge of $0.00001 applies per request. Charges are deducted from your wallet balance in real time.