Kimi K2.8 Preview API

Call Kimi K2.8 Preview through Wokey and review published catalog pricing, upstream-native API forms, context, and model capabilities.

Model ID
kimi-for-coding
Vendors
moonshot, volcengine
Supply status
Currently callable

Catalog pricing snapshot

Prices are per 1M tokens; request-time pricing controls settlement.

MeterWokeyOfficial referenceSavings
Input$0.3$170%
Output$1.2$470%
Cache read$0.075$0.2570%
Cache write———

Official price source: https://www.tencentcloud.com/document/product/1300/78937

Measured on Wokey

Last 28 days (2026-09-29 to 2026-10-26), updated every Monday · Real requests from 30+ accounts

Time to first token, short prompts
Not enough samples (Median · prompts under 8K tokens)
Time to first token, agent-size prompts
2.8 s (Median · prompts of 32K–128K tokens)
Prompt cache hit rate
98% (Share of input tokens read from cache)

How this is measured

Time to first token runs from the Wokey gateway receiving the request to the first streamed content (text, reasoning summary or refusal). It includes queueing, retries on another account and the model's thinking time, so it is longer than the upstream's own first-token latency. Only successful streamed requests count, banded by prompt size (input plus cache reads and writes).

Cache hit rate = cache-read tokens ÷ input tokens over successful requests. It depends on the client and how it is used; the cache hit-rate pages break it down by client.

Enterprise accounts and Wokey's own test accounts are excluded. A model is shown once at least 20 users used it in the last 28 days and no single user sent more than 50% of its requests, counting accounts registered through one referral chain as one user; each first-token figure needs at least 500 requests.

Cache hit rate by client

Model capabilities

Context
1,048,576 tokens
Max output
32,768 tokens
Streaming
Supported
Tools
Supported
Vision
Supported
Supported API forms
/v1/chat/completions

Send a request

/v1/chat/completions

curl https://api.wokey.ai/v1/chat/completions \
  -H "Authorization: Bearer $WOKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"kimi-for-coding","messages":[{"role":"user","content":"Hello"}]}'

Use Kimi K2.8 Preview in your tools

The gateway is https://api.wokey.ai (OpenAI-compatible clients usually take https://api.wokey.ai/v1), and the model ID is kimi-for-coding. Open the guide for the client you use.

Frequently asked questions

How much does the Kimi K2.8 Preview API cost, and how much does it save versus the official API?

Wokey lists input at $0.3 per 1M tokens and output at $1.2 per 1M tokens; the official references are $1 and $4. That is 70% lower for input and 70% lower for output. Request-time pricing controls settlement, and the vendor pricing source is linked on this page.

What is the Kimi K2.8 Preview API model ID?

The model ID for Kimi K2.8 Preview on Wokey is kimi-for-coding. Use it exactly as written in the request body's model field or in your client's model setting (for example ANTHROPIC_MODEL in Claude Code, or model in the Codex CLI config.toml); GET https://api.wokey.ai/v1/models also lists it.

Which API forms does Kimi K2.8 Preview support, and how do I call it through Wokey?

Kimi K2.8 Preview supports /v1/chat/completions (Chat Completions requests). Set the API base URL to https://api.wokey.ai, authenticate with a Wokey API key, and use the canonical model ID kimi-for-coding; you can start with /v1/chat/completions. The Send a request section includes a curl example for every supported API form.

How do I use Kimi K2.8 Preview in opencode, Hermes Agent, and similar clients?

These clients call Kimi K2.8 Preview over OpenAI Chat Completions: point the API address at https://api.wokey.ai (clients that expect an OpenAI SDK-style address take https://api.wokey.ai/v1), add your Wokey API key, and use the model ID kimi-for-coding. Each client's guide shows its config format.

What are the context window and maximum output for Kimi K2.8 Preview?

The catalog context window is 1,048,576 tokens and the maximum output is 32,768 tokens. These are separate limits, and a request must also satisfy the upstream constraints in effect when it is processed.

How are cache reads and cache writes priced for Kimi K2.8 Preview?

Cache read: Wokey lists $0.075 per 1M tokens and the official reference is $0.25 per 1M tokens. Cache write: the vendor does not publish a separate meter, so Wokey also shows — as the public price.

How does calling Kimi K2.8 Preview through Wokey differ from OpenRouter?

Wokey lists Kimi K2.8 Preview at $0.3 input / $1.2 output per 1M tokens, against an official reference of $1 / $4. OpenRouter states it adds no markup on inference and charges its fee when you buy credits (5.5% by card). Wokey carries a curated set of models and has no per-provider routing parameters, so OpenRouter fits better if you need a wider catalog. The OpenRouter alternative page has the full comparison.

How do Kimi K2.8 Preview and Kimi K3.1 Pro differ in price and context?

In the published price comparison, Kimi K2.8 Preview lists input/output at $0.3 / $1.2 with a 1,048,576-token context window; Kimi K3.1 Pro lists $0.6 / $3 with a 1,048,576-token context window. This is a factual price-and-capacity comparison, not a quality ranking; also compare their supported API forms and capabilities.

How fast is Kimi K2.8 Preview on Wokey?

Measured on real Wokey gateway requests from 2026-09-29 to 2026-10-26: 2.8 s for 32K–128K-token agent prompts. 98% of input tokens were read from the prompt cache. Times run from the gateway receiving the request and include queueing, retries and thinking.

Related models and documentation

Get API key · kimi-for-coding