Kimi K2 0711 pricing
Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for... Live index: 8 priced offers. Best input $0.500 per million tokens from DeepInfra. Best output $2.00 per million tokens from DeepInfra.
Pricing across providers
All figures are list prices per million tokens unless a column says otherwise. 8 offers are listed for Kimi K2 0711. Best input in this view: DeepInfra.
| Provider | Input / 1M | Output / 1M | Cached input | Batch |
|---|---|---|---|---|
D DeepInfra | $0.500 | $2.00 | — | — |
FA Fireworks AI | $0.600 | $2.50 | — | — |
H Hyperbolic | $2.00 | $2.00 | — | — |
TA Together AI | $1.00 | $3.00 | — | — |
VA Vercel Ai Gateway | $0.550 | $2.20 | — | — |
W Wandb | $0.600 | $2.50 | — | — |
N Novita | $0.570 | $2.30 | — | — |
O Openrouter | $0.570 | $2.30 | — | — |
Input vs output · per provider
Cost calculator
Pick any of the providers above and type how many tokens you expect per day, week, or year. We turn that into rough dollar totals for Kimi K2 0711.
Provider
0.050000¢ / req
0.100000¢ / req
Model specifications
Context length, caps, and capability flags for Kimi K2 0711. Values follow the main provider (Moonshot) record in our index.
- Context window
- 131,072 tokens
- Max output
- 131,072 tokens
- Vision (images)
- No
- Tool / function calling
- Yes
- Streaming
- No
- Released
- Jul 2025
- Primary provider
- Moonshot
- Model family
- N/A
Compare Kimi K2 0711
Jump into a comparison when you want one table for two models instead of two tabs. 6 curated matches for Kimi K2 0711.
- Kimi K2 0711 vs GPT-4o
Compare pricing side by side
- Kimi K2 0711 vs GPT-4o mini
Compare pricing side by side
- Kimi K2 0711 vs Claude Sonnet 4.6
Compare pricing side by side
- Kimi K2 0711 vs Gemini 2.0 Flash
Compare pricing side by side
- Kimi K2 0711 vs o3
Compare pricing side by side
- Kimi K2 0711 vs Llama 3.1 70B
Compare pricing side by side
Frequently asked questions
Answers pull from the same numbers you see on this page. The short model note from our index: Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...
Also from Moonshot
Other models by Moonshot with live pricing in our catalog.