Kimi K2.5 Fp4
Kimi-K2.5-fp4Pricing
List prices at Together AI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.50 | $2.80 |
What it costs a month
At Together AI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$360
- RAG over documents2,000 requests a day, 8K in / 0.6K out$341
- Coding agent1,000 requests a day, 40K in / 2K out$768
- Overnight batch20,000 requests a day, 4K in / 0.4K out$1,872
Where to run it
1 host serve Kimi K2.5 Fp4. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Together AIInference Kimi-K2.5-fp4 | $0.50 / $2.80 | Kimi-K2.5-fp4 |
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
- Text
- Produces
- Text
- 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 Together AI.
Smaller Moonshot AI models
No cheaper Moonshot AI model keeps its key capabilities.
Other frontier labs
- 21% less
- 57% less
- 81% less
- 81% less
Open-weight picks
- 19% less
- 20% less
- 24% less
- 26% less
Call it
Using Together AI's API.
from litellm import completion
response = completion(
model="together_ai/Kimi-K2.5-fp4",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Kimi K2.5 Fp4 cost?
On Together AI, Kimi K2.5 Fp4 costs $0.50 per million input tokens and $2.80 per million output tokens.
Which APIs offer Kimi K2.5 Fp4?
Kimi K2.5 Fp4 runs on 1 API: Together AI.
What is Kimi K2.5 Fp4's context window?
262K tokens.
Is Kimi K2.5 Fp4 being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Kimi K2.5 Fp4?
Models that cost less and keep most of what it can do: Gemini 3.5 Flash Lite on Google AI Studio (21% less), GPT-5.4 Nano on OpenAI (57% less) and Motif 3 on ai& (19% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Kimi K2.5 Fp4's API model id?
Use Kimi-K2.5-fp4 with Together AI.
Sources
Raw catalog entry for Kimi-K2.5-fp4 on Together AI
{
"input_cost_per_token": 5e-7,
"output_cost_per_token": 0.0000028,
"litellm_provider": "together_ai",
"max_input_tokens": 262144,
"mode": "chat",
"source": "https://api.together.ai/v1/models"
}