kimi-k2-thinking API Pricing
kimi-k2-thinking on Fireworks AI costs $0.60 per 1M input tokens and $2.50 per 1M output tokens (as of ).
| Input | $0.60 / 1M tokens |
|---|---|
| Output | $2.50 / 1M tokens |
| Cached input (read) | — |
| Cache write | — |
| Batch input / output | — |
| Above 200K tokens (input / output) | — |
| Context window | 262K tokens |
| Max output | 262K tokens |
| Supports | tool calling |
| Deprecation date | None listed |
| API model id | accounts/fireworks/models/kimi-k2-thinking |
| In our records since |
What it costs for common jobs
Estimated from the list price above (no caching or batch discount).
| Job | Estimated cost |
|---|---|
| 1,000 chat replies (2,000 tokens in, 500 out each) | $2.45 |
| Summarising 100 long documents (50,000 in, 1,000 out each) | $3.25 |
| 1 million classification calls (300 in, 5 out each) | $192.50 |
Try your own numbers in the LLM API cost calculator.
Price history
No price change recorded since .
Similarly priced models
| Model | Provider | Input / 1M | Output / 1M | Cached input / 1M | Context |
|---|---|---|---|---|---|
| kimi-k2-instruct | Fireworks AI | $0.60 | $2.50 | — | 131K |
| nemotron-3-ultra-nvfp4 | Fireworks AI | $0.60 | $2.40 | $0.12 | 262K |
| nemotron-3-ultra-nvfp4 | Fireworks AI | $0.60 | $2.40 | $0.12 | 262K |
| glm-4p7 | Fireworks AI | $0.60 | $2.20 | $0.30 | 203K |
| glm-4p7 | Fireworks AI | $0.60 | $2.20 | $0.30 | 203K |
| deepseek-r1-basic | Fireworks AI | $0.55 | $2.19 | — | 164K |
| glm-4p5 | Fireworks AI | $0.55 | $2.19 | — | 131K |
| glm-4p6 | Fireworks AI | $0.55 | $2.19 | — | 203K |