Aihubmix
Kimi K3
Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work
Cheapest input
$0
$/MTok · models.dev
Cheapest output
$0
$/MTok
Context
1.0M
tokens
Offers
12
1 source
Offers
Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number. Showing free/$0 offers. Hide them.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestkimi-k3 | Kenari | $0 | $0 | $0 | 1.0M |
| models.devkimi-k3 | CrofAI | $2 | $8 | $0.25 | 1M |
| models.devkimi-k3 | AIHubMix | $3 | $15 | $0.3 | 1.0M |
| models.devkimi-k3 | Cortecs | $3 | $15 | $0 | 1.0M |
| models.devkimi-k3 | DigitalOcean | $3 | $15 | $0.3 | 1.0M |
| models.devkimi-k3 | EmpirioLabs AI | $3 | $15 | $3 | 1M |
| models.devkimi-k3 | LLM Gateway | $3 | $15 | $0.3 | 1.0M |
| models.devkimi-k3 | Moonshot AI (China) | $3 | $15 | $0.3 | 1.0M |
| models.devkimi-k3 | OpenCode Go | $3 | $15 | $0.3 | 1.0M |
| models.devkimi-k3 | OpenCode Zen | $3 | $15 | $0.3 | 1.0M |
| models.devkimi-k3 | Charm Hyper | $3.27 | $16.33 | $0.3266 | 1.0M |
| models.devkimi-k3 | Venice AI | $3.75 | $18.75 | $0.375 | 1M |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Attachments
- Open weights
- In: text
- In: image
- In: video
- Out: text
Released: 2026-07-16Family: kimi-k3
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.
- Arena agent (net improvement)9.91
- Arena agent net improvement9.91
- Arena agent confirmed success14.23
- AA intelligence57.1
- AA coding76.2
- AA agentic50.1
Sources: Arena AI, Artificial Analysis. See /benchmarks.