How Moonshot works

Moonshot AI publishes the Kimi family of models (K2, K2.5, K2.6, K2.6 Coding). Kimi is particularly strong on long-context code understanding and agentic workflows, and the API is fully OpenAI-compatible — Mesrai talks to it via the OpenAI Compatible provider (or directly through the curated Kimi K2.6 Coding card in BYOK).

Moonshot offers two paths to the same model family, each with its own endpoint:

• Developer API (platform.moonshot.ai) — pay-per-token, billed per usage. Concurrency scales with your recharge tier.
• Kimi Code Plan (kimi.com/code) — subscription with a dedicated coding endpoint. Flat pricing, capped concurrency (30 concurrent).

Moonshot also operates a China-only platform (platform.moonshot.cn, base URL https://api.moonshot.cn/v1) billed in CNY. Use that only if you operate inside mainland China.

Plans at a glance

Kimi Code Plan (subscription)

Developer API (pay-per-token)

Developer API endpoint: https://api.moonshot.ai/v1 (international). Concurrency scales with recharge tier — Tier 1 ($10 recharge) starts at ~50 concurrent, up to ~1000 concurrent on Tier 5.

Creating an API Key

Configure Moonshot in Mesrai

The primary flow is BYOK on Mesrai Cloud — the curated Kimi K2.6 Coding card handles the endpoint swap for you. Self-hosted users who prefer fixing the provider at the process level can use environment variables instead.

Option 1 — BYOK on Mesrai Cloud (recommended)

1. 1

   Open BYOK and pick Kimi K2.6 Coding

   Go to app.mesrai.com/organization/byok and click the Kimi K2.6 Coding card in the Main model section.

2. 2

   Select your plan

   The card expands with a Plan selector. Pick:

   • Developer API — if your key is from platform.moonshot.ai
   • Kimi Code Plan — if your key is from a kimi.com/code subscription

   The base URL and “Get a key” link update automatically.

3. 3

   Paste your API key

   Just the key. For Kimi Code Plan users, Mesrai pre-fills maxConcurrentRequests=30 in Advanced settings (matches the documented cap).

4. 4

   Test & save

   Click Test & save. Mesrai probes the endpoint with a cheap metadata call and persists the config on success. 401 means the key doesn’t match the selected plan’s endpoint.

Tuning reasoning (optional)

Reasoning is ON by default for Kimi K2.6 Coding — the curated card pre-fills Thinking: Medium, which for OpenAI-compatible providers emits thinking: { type: "enabled" }. Two common overrides:

• Disable thinking for faster/cheaper reviews on small PRs:

  {
    "thinking": { "type": "disabled" }
  }

• Force a specific token budget (if Moonshot adds support for budget_tokens on your tier):

  {
    "thinking": { "type": "enabled", "budget_tokens": 25000 }
  }

Tuning concurrency

• Kimi Code Plan: keep the pre-filled maxConcurrentRequests=30 (the documented cap). Going higher returns 429.
• Developer API: start empty (no cap). Your actual limit scales with your recharge tier — Tier 1 (~$10 recharge) allows 50 concurrent; Tier 5 ($3000) allows ~1000. Lower it explicitly if you see 429s at review time.

Option 2 — Manual configuration

If you need a Kimi variant not in the curated catalog (e.g. kimi-k2.5 or kimi-k2-0905), click Configure manually at the bottom of the catalog and fill:

Enterprise deployments

For Enterprise customers running Mesrai in their own VPC, the Moonshot block is configured via environment variables in the API + worker containers. Your onboarding contact will share the exact .env template and deployment runbook for your tenancy. Contact sales for details.

Choosing between Kimi Code Plan, Developer API, and aggregators

• Kimi Code Plan — predictable flat-rate cost, 30-concurrent cap, dedicated api.kimi.com/coding/v1 endpoint optimized for coding workflows. Best for steady-state teams with predictable PR volume.
• Moonshot Developer API — pay-per-token, concurrency scales with recharge tier, largest flexibility. Best for bursty workloads.
• OpenRouter proxy — if you want one billing relationship across many providers, OpenRouter exposes Kimi models with a small routing markup. Pick this when Kimi is part of a mixed-provider fleet, not a primary workload.

Troubleshooting

Related

• Moonshot platform (international)
• Kimi Code Plan
• Kimi API documentation
• BYOK overview