Kimi K2.6
$0.95
Input / MTok
$4
Output / MTok
$0.16
Cache read / MTok
Hosted third-party inference; price is Fireworks' Standard serverless rate, not Moonshot's own API. Fireworks also sells a Fast deployment of this model at a higher per-token rate, and an optional Priority tier at ~1.5x.
API identifier accounts/fireworks/models/kimi-k2p6
· vendor pricing page
Full price sheet
| Metric | USD / million tokens |
|---|---|
| Input | $0.95 |
| Output | $4 |
| Cache read | $0.16 |
Price history
| Observed | Metric | Price |
|---|---|---|
| 2026-08-08 07:26:49 | Input | $0.95 |
| 2026-08-08 07:26:49 | Output | $4 |
| 2026-08-08 07:26:49 | Cache read | $0.16 |
Current prices are free and always will be. The full series — every observation since we started watching, which nobody can reconstruct after the fact — is the part Pro pays for.
Changes affecting this model
coverage
Kimi K2.6 added to coverage
—
2026-08-08Compare with
Models at a similar price point.
| Model | Input | Output | |
|---|---|---|---|
| Kimi K2.7 Code | $0.95 | $4 | compare → |
| Kimi K2.7 Code | $0.95 | $4 | compare → |
| Inkling | $1 | $4.05 | compare → |
| Qwen3.7 Max | $1.25 | $3.75 | compare → |
| DeepSeek V4 Pro | $1.74 | $3.48 | compare → |
| DeepSeek V4 Pro | $1.74 | $3.48 | compare → |