Compare model prices
Input, output, cached and batch prices, every route and a month of tokens, side by side.
A month of tokens
Kimi K2 0711$103.00
Kimi K3$355.00
100M input and 20M output tokens, list price. Use your own numbers.
Side by side
| Kimi K2 0711 | Kimi K3 | |
|---|---|---|
| Input per 1M | $0.57 | $1.4 |
| Output per 1M | $2.3 | $10.8 |
| Cached input | n/a | $0.3 |
| Batch in / out | n/a | n/a |
| Blended (3:1) | $1 | $3.74 |
| Context | 131K | 1M |
| Routes | 1 | 20 |
| Released | Jul 11, 2025 | Jul 16, 2026 |
| Leadersboard score | n/a | 11 (#18) |
On the price map
Size: context window, 8K to 2MEqual blended cost (3:1) 243 models, lower left is cheaper
Every route
Kimi K2 0711
Novita AIfp8, fp8$0.57 / $2.3$1 blended
Kimi K3
- InferenceNetfp4, fp4$1.4 / $10.8cached $0.3
- Sail Researchfp4, fp4+7%$1.5 / $11.5cached $0.3
- Phaladefault region+12%$2.1 / $10.5cached $0.21
- Relacefp4, fp4+12%$2.1 / $10.5cached $0.21
- Makoradefault region+36%$2.55 / $12.8cached $0.256
- Waferdefault region+37%$1.99 / $14.5cached $0.199
DigitalOceandefault region+38%$2.55 / $13cached $0.255
- Morphdefault region+44%$2.5 / $14cached $0.29
DeepInfrabf16, bf16+53%$2.85 / $14.3cached $0.285
Basetenfp8, fp8+61%$3 / $15cached $0.3
Chutesmxfp4, mxfp4+61%$3 / $15cached $0.3
Fireworks AIdefault region+61%$3 / $15cached $0.3
Modalmxfp4, mxfp4+61%$3 / $15cached $0.3
Moonshot AImxfp4, mxfp4+61%$3 / $15cached $0.3
Parasailfp4, fp4+61%$3 / $15cached $0.3
Together AIdefault region+61%$3 / $15cached $0.3
Fireworks AIus+77%$3.3 / $16.5cached $0.33
Qwen (Alibaba)default region+85%$3.45 / $17.3cached $0.345
Fireworks AIfast+141%$4.5 / $22.5cached $0.45
- Morphfast+171%$6 / $22.5cached $0.6
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.