Kimi K3 Us
kimi-k3-usPricing
List prices at Fireworks AI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $4.50 | $22.50 | |
| Cached input 90% off input | $0.45 | 90% off input | |
| Priority 25% more | $5.63 | $28.13 | 25% more |
What it costs a month
At Fireworks AI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$2,673
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$1,998
- Coding agent1,000 requests a day, 40K in / 2K out, cached$3,348
- Overnight batch20,000 requests a day, 4K in / 0.4K out$16,200
Where to run it
1 host serve Kimi K3 Us. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Fireworks AIInference kimi-k3-us | $4.50 / $22.50 | kimi-k3-us |
Show 1 more listings: regions, snapshots and variantsHide regional listings
| Fireworks AI | |||||||
| Alias kimi-k3-us | $4.50 / $22.50 | kimi-k3-us | |||||
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- TextImages
- Produces
- Text
- Effort settings the source lists
- lowhighmax
- Open weights
- License: Modified MIT LicenseRuntimes: SGLang, vLLM
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than Fireworks AI.
Smaller Moonshot AI models
No cheaper Moonshot AI model keeps its key capabilities.
Other frontier labs
- 11% less
- 47% less
- 56% less
- 67% less
Open-weight picks
- 51% less
- 56% less
- 75% less
- 81% less
Call it
Using Fireworks AI's API.
from litellm import completion
response = completion(
model="fireworks_ai/kimi-k3-us",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Kimi K3 Us cost?
On Fireworks AI, Kimi K3 Us costs $4.50 per million input tokens and $22.50 per million output tokens. Cached input costs $0.45 per million tokens.
Which APIs offer Kimi K3 Us?
Kimi K3 Us runs on 1 API: Fireworks AI.
What is Kimi K3 Us's context window?
1M tokens, with up to 131K tokens in one reply.
Is Kimi K3 Us being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Kimi K3 Us?
Models that cost less and keep most of what it can do: Claude Opus 5.5 on Anthropic (11% less), GPT-5.3 Codex on OpenAI (47% less) and Command A Plus on AIHubMix (51% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Kimi K3 Us's API model id?
Use kimi-k3-us with Fireworks AI.
Sources
Raw catalog entry for kimi-k3-us on Fireworks AI
{
"cache_read_input_token_cost": 4.5e-7,
"cache_read_input_token_cost_priority": 5.625e-7,
"input_cost_per_token": 0.0000045,
"input_cost_per_token_priority": 0.000005625,
"litellm_provider": "fireworks_ai",
"max_input_tokens": 1048576,
"max_output_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 0.0000225,
"output_cost_per_token_priority": 0.000028125,
"reasoning_effort_levels": [
"low",
"high",
"max"
],
"source": "https://docs.fireworks.ai/serverless/pricing",
"supports_function_calling": true,
"supports_mid_conversation_system": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
}