Moonshot Batch API now supports kimi-k3.1-pro and kimi-k3
The Moonshot Batch API now accepts kimi-k3.1-pro and kimi-k3 on both the CN and Global platforms.
On Zabio today
kimi-k3.1-proLive. Call it by name, or let auto pick it when it fits the job.Price and detailskimi-k3Live. Call it by name with your Zabio key.Price and detailskimi-k2.7-codeLive. Call it by name, or let auto pick it when it fits the job.Price and detailskimi-k2.6Live. Call it by name with your Zabio key.Price and details
What changed
The Batch API now supports the kimi-k3.1-pro and kimi-k3 models, which were previously limited to kimi-k2.7-code and kimi-k2.6. They are available on both the CN and Global platforms. Batch inference is still priced at 60% of standard rates.
What it means for Zabio customers
Developers can run batch jobs on these models at batch rates. Batch jobs on these models are also charged Cache Write fees, and cache hits are provided on a best-effort basis.
Source
The Batch API now supports the kimi-k3.1-pro and kimi-k3 models (previously limited to kimi-k2.7-code and kimi-k2.6), available on both the CN and Global platforms.
Original announcement: Moonshot AI platform changelog
How it compares
The models in this story next to models of the same class at a similar price, all available with one Zabio key.
| Model | Input, $/M | Output, $/M | Cached, $/M | Context window | 1,000 calls | Analysis and reasoning, hard |
|---|---|---|---|---|---|---|
kimi-k3.1-proMoonshot AIIn this story | 2.00 | 10.00 | 0.20 | 1,048,576 | $9.00 | 86.6 |
kimi-k3Moonshot AIIn this story | 3.00 | 15.00 | 0.30 | 1,048,576 | $13.50 | 85.1 |
kimi-k2.7-codeMoonshot AIIn this story | 0.95 | 4.00 | no data | 131,072 | $3.90 | 87.9 |
kimi-k2.6Moonshot AIIn this story | 0.75 | 3.50 | 0.15 | 131,072 | $3.25 | 90.8 |
gemini-4-argonGoogle | 2.00 | 10.00 | no data | 200,000 | $9.00 | 92.8 |
gpt-6-solOpenAI | 2.00 | 10.00 | 0.20 | 400,000 | $9.00 | 94.3 |
qwen3.7-maxQwen | 2.50 | 7.50 | 0.50 | 1,000,000 | $8.75 | 90.9 |
Prices are the vendor list prices in USD per million tokens. "1,000 calls" is 1,000 requests of 2,000 input tokens and 500 output tokens each, without caching. Zabio bills the list price plus its service fee: see pricing.
Scores: percent correct for that kind of job, aggregated from public results by Epoch AI, LMArena, and LiveBench, read on 16 November 2026. Epoch AI: CC BY 4.0, LMArena: CC BY 4.0, LiveBench: Leaderboard results used with attribution; the 2.0 release states no terms of its own (read 2026-11-06); the first version's Mathematics, Language, IF results: Code Apache 2.0 and MIT; leaderboard results used with attribution
Source: Moonshot AI platform changelog