Moonshot · model
Kimi K3 (batch)
$3.00/1M in · $15.00/1M out · 1.0M context. That's cheaper than 9% of the 404 models we track, by output price. Here's what it costs, how its price has moved, and where it fits.
- Context
- 1.0M
- Input / 1M
- $3.00
- Output / 1M
- $15.00
- Modality
- text + image + video
- Provider
- Moonshot
- Tokenizer
- Other
Snapshot · source: OpenRouter ↗ · how we measure →
For 1,500 input + 500 output tokens across 200,000 requests/month. That's 276× the cheapest tracked option (Mistral Nemo, $8.70/mo).
Price history is accruing — the archive began 2026-08-06 and captures a snapshot every other day. Track it on the history page →
Where it fits
- Long inputs — a 1.0M-token window holds roughly 1,573 pages of text at once.
- Multimodal prompts — accepts image input alongside text.
Watch for
- Output at $15.00/1M is among the priciest tracked — output-heavy or reasoning-heavy workloads add up fast.
- Priced from OpenRouter's routed market, not a first-party list price — availability and rate can shift without notice.
These notes are derived from price, context and modality — structural facts, not measured quality. Measured cost-to-finish-a-task lives on the real-cost index.
Related models
How to read Kimi K3 (batch)'s pricing
Two numbers decide most of the bill: $3.00/1M for input (everything you send — prompt, context, attachments) and $15.00/1M for output (everything it generates, including hidden reasoning tokens). Output is priced 5.0× the input rate here, so the shape of your workload — how much it reads versus writes — matters as much as the headline figure. This row is OpenRouter's routed market price; it can move as providers and routing change.
Frequently asked questions
How much does Kimi K3 (batch) cost per million tokens?
Kimi K3 (batch) is priced at $3.00 per 1M input tokens and $15.00 per 1M output tokens, from OpenRouter's routed market price as of the 2026-08-30 snapshot. Output is the figure that usually drives the bill. Enter your own token volumes in the cost calculator for a monthly estimate.
What is Kimi K3 (batch)'s context window?
Kimi K3 (batch) has a 1.0M-token context window — roughly 1,573 pages of text. Prompt, attachments, conversation and the model's own output all share that budget, and every token you send is billed at the input rate.
Related
- API cost calculator — your monthly cost for Kimi K3 (batch) and every other model.
- Model comparison — the full sortable table.
- Price history — how token prices move over time.
- LLM pricing explained — input, output, cached and reasoning tokens.