Model APIs - 1 entries
Moonshot Kimi API limits
Moonshot AI's official docs, read on October 17, 2026, set limits for the Kimi API. For Batch API (kimi-k2.7-code, kimi-k2.6; kimi-k3 not supported), the docs list Input file size: no larger than 100MB (.jsonl, non-empty); Models per batch: only one model per batch is allowed.
Last verified from platform.kimi.ai. What the docs leave out
- Sources
- 1
- Tables
- 1
- Entries
- 1
- Verified
- Oct 17, 2026
Limits by scope
Values are copied exactly as the docs show them, units included, in the docs' own order. A dash means the docs list no value for that row.
Batch API (kimi-k2.7-code, kimi-k2.6; kimi-k3 not supported)
| Metric | Limit |
|---|---|
| Input file size | no larger than 100MB (.jsonl, non-empty) |
| Models per batch | only one model per batch is allowed |
| completion_window examples | 24h; use 3d or 7d for larger datasets |
| Discount | saving 40% on inference costs compared to real-time API calls |
- "Batch API supports both the `kimi-k2.7-code` and `kimi-k2.6` models; `kimi-k3` is not supported." No separate batch queue/token quota is published.
What the docs leave out
- No per-model rate limits are published for the Open Platform: docs state "we share rate limits across all models", so every tier row applies to kimi-k3, kimi-k2.7-code, kimi-k2.7-code-highspeed and kimi-k2.6 together.
- Input/output TPM split is not published; only a combined TPM, with request tokens plus max_completion_tokens counted.
- RPD is not published; TPD is published (Tier0 1,500,000; Tier1-5 Unlimited).
- Limits above Tier5 and enterprise limits are not published; they go through the contact-sales rate limit increase form.
- The per-account values that actually apply are shown in the logged-in console dashboard, which was not viewed.
- Kimi Code (subscription product): no numeric quotas are published for any plan (5-hour window size, monthly total, concurrency). Remaining quota and rate-limit status are shown only in the logged-in Kimi Code Console or via `/usage`.
- The limits table has one more per-tier column, a QPS limit for a tool endpoint. It was left out on purpose under the house content boundary.
FAQ
What are the Moonshot Kimi API limits?
Moonshot AI's official docs, read on October 17, 2026, set limits for the Kimi API. For Batch API (kimi-k2.7-code, kimi-k2.6; kimi-k3 not supported), the docs list Input file size: no larger than 100MB (.jsonl, non-empty); Models per batch: only one model per batch is allowed.
How do I raise my Kimi API limits?
The Moonshot AI docs read for this page do not describe a way to raise these limits.
Where do these Moonshot Kimi API numbers come from?
Every value is copied verbatim from Moonshot AI's official documentation at platform.kimi.ai, read on October 17, 2026. This page lists all 1 entry in 1 table, each linked to the page it came from.
Related reading
- Kimi K3 in 10 Minutes: Moonshot AI's 2.8T Open Model, API Setup, Pricing, and BenchmarksKimi K3 from Moonshot AI is a 2.8T open model with a 1M-token context and an OpenAI-compatible API. How to call it, what it costs, and how it benchmarks.
- Where to Access Kimi K3: Every Provider and Price Compared (2026)Where to access Kimi K3: Moonshot's API at $3 input and $15 output per million tokens, OpenRouter hosts, inference clouds, and open weights.
Sources
Last verified . Every value is copied verbatim from the official pages below, read on that date.
Newsletter
Know when limits change
One email per week. New model releases, pricing and limit changes, and what they mean for what you build.