Kimi K3
opencode The API that serves this model and sets the prices shown here. kimi-k3 The model identifier to send in API requests. LLM Generates text from a prompt, so it can be compared with other LLMs on price and capability.Provider: moonshot · served via OpenCode
Nothing to act on today. The cost is the checking: someone has to remember to look again next month, and the month after. Coolhand watches this model for you and automatically updates your agents to the most compatible replacement the moment a retirement is announced — one less thing on your list, permanently.
Sticker prices & cost-per-token
List rates as published by OpenCode, before any volume or enterprise discounts.
$3.00
$15.00
1,048,576 tokens
131,072
tokens per response (includes reasoning tokens)
$0.30
Get this data free
Want to stay updated on price changes on this model? Pull this data free (no API key required) here:
curl "https://coolhandlabs.com/api/v2/inference_apis?q%5Bmodel_eq%5D=kimi-k3&q%5Bsource_api_eq%5D=opencode"Pricing History
| Effective | Price |
|---|---|
| Aug 12, 2026 – present | Input cost: $3.00 / 1M, Output cost: $15.00 / 1M, Cached input cost: $0.30 / 1M, Cache creation cost: $0.00 / 1M, 5-minute cache write cost: $0.00 / 1M, 1-hour cache write cost: $0.00 / 1M, Reasoning output cost: $0.00 / 1M, Cache storage cost: $0.00 / 1M/hr |
History
No automated scan changes recorded yet.
| Date | Changed by | What changed |
|---|---|---|
| Aug 12, 2026 | Unknown | Initial record created |
Source
https://opencode.ai/docs/zen/ (via https://models.dev/api.json)Comparable models
No comparable models identified yet.
Reliability
No reliability incidents recorded in the last 90 days.
Frequently asked questions
Kimi K3 (moonshot via OpenCode) costs $3.00 per 1M input tokens and $15.00 per 1M output tokens, as last published by OpenCode.
Kimi K3 has a context window of 1,048,576 tokens (the maximum combined input and output it can handle in a single request).
Kimi K3 can generate up to 131,072 tokens in a single response. Reasoning (thinking) tokens count toward this limit.
Kimi K3 accepts image, text, and video as input and produces text as output, as recorded in the Coolhand catalog.
No, Kimi K3 is currently active with no announced deprecation date.
Call GET https://coolhandlabs.com/api/v2/inference_apis?q[source_api_eq]=opencode&q[model_eq]=kimi-k3 — free, no API key required, and scoped to just this model since source_api and model together are unique. See https://coolhandlabs.com/docs for the full REST API reference.
Coolhand also tracks Kimi K2.5 Free, Kimi K2.5, Kimi K2.7 Code, Kimi K2 0711, and Kimi K2 0905 from moonshot. Some may already be deprecated, so check each model's status alongside its current pricing.
| Model | Input cost | Output cost | Context window | Max output tokens | Status |
|---|---|---|---|---|---|
| Kimi K2.5 Free via OpenCode | $0.00/1M $0.0000000000 | $0.00/1M $0.0000000000 | 262,144 | 262,144 |
Deprecated Aug 12, 2026
|
| Kimi K2.5 via Azure | $0.60/1M $0.0000006000 | $3.00/1M $0.0000030000 | 262,144 | 262,144 | Active |
| Kimi K2.7 Code via OpenCode | $0.95/1M $0.0000009500 | $4.00/1M $0.0000040000 | 262,144 | 262,144 | Active |
| Kimi K2 0711 via OpenRouter | $0.57/1M $0.0000005700 | $2.30/1M $0.0000023000 | 131,072 | 98,304 | Active |
| Kimi K2 0905 via OpenRouter | $0.60/1M $0.0000006000 | $2.50/1M $0.0000025000 | 262,144 | 98,304 | Active |
Track LLM pricing and deprecations automatically.
Start free