Kimi K3 Fast
kimi-k3-fastPricing
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 |
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 Fast. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Fireworks AIInference kimi-k3-fast | $4.50 / $22.50 | kimi-k3-fast |
Show 1 more listings: regions, snapshots and variantsHide regional listings
| Fireworks AI | |||||||
| Alias kimi-k3-fast | $4.50 / $22.50 | kimi-k3-fast | |||||
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
- 33% less
- 47% less
- 67% less
Open-weight picks
- 51% less
- 56% less
- 76% less
- 81% less
Model line
Newer and older versions, at each lab's own price.
- UndatedKimi K3 FastLatest$4.50 / $22.50
- UndatedKimi K2.6 Fast$2.00 / $8.00
Call it
Using Fireworks AI's API.
from litellm import completion
response = completion(
model="fireworks_ai/kimi-k3-fast",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Kimi K3 Fast cost?
On Fireworks AI, Kimi K3 Fast 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 Fast?
Kimi K3 Fast runs on 1 API: Fireworks AI.
What is Kimi K3 Fast's context window?
1M tokens, with up to 131K tokens in one reply.
Is Kimi K3 Fast being retired?
No retirement date is scheduled for it on any API we track.
Is there a newer version of Kimi K3 Fast?
No. Kimi K3 Fast is the newest model in its line.
What are cheaper alternatives to Kimi K3 Fast?
Models that cost less and keep most of what it can do: Claude Opus 5.5 on Anthropic (11% less), Gemini 4 Neon on Google AI Studio (33% 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 Fast's API model id?
Use kimi-k3-fast with Fireworks AI.
Sources
Raw catalog entry for kimi-k3-fast on Fireworks AI
{
"cache_read_input_token_cost": 4.5e-7,
"input_cost_per_token": 0.0000045,
"litellm_provider": "fireworks_ai",
"max_input_tokens": 1048576,
"max_output_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 0.0000225,
"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
}