Kimi K3.1 Pro Xploded in Aider

Kimi K3.1 Pro Xploded in Aider

Run kimi-k3.1-pro-xploded in Aider through MagmaRouter: one key, a hard spend cap, and a model that answers instead of refusing.

Model idkimi-k3.1-pro-xploded
Context window1,048,576 tokens (1M)
Tool callingSupported
Price per 1M tokens$7.50 input, $0.80 on a cache hit, $37.50 output
Intelligence55 on the Artificial Analysis Intelligence Index v4.3.2, for the base model
Web searchAdd :online to the id

Set it up

  1. Set OPENAI_API_BASE to https://api.magmarouter.com/v1 and OPENAI_API_KEY to your key.
  2. Run aider --model openai/kimi-k3.1-pro-xploded; the openai/ prefix is what sends it to the base URL.
  3. Add the metadata file below so Aider knows the real context window and price instead of warning that it does not.
# shell
setx OPENAI_API_BASE https://api.magmarouter.com/v1
setx OPENAI_API_KEY sk-mr-...
aider --model openai/kimi-k3.1-pro-xploded

# .aider.model.metadata.json
{
  "openai/kimi-k3.1-pro-xploded": {
    "max_input_tokens": 1048576,
    "max_output_tokens": 32768,
    "input_cost_per_token": 0.0000075,
    "output_cost_per_token": 0.0000375,
    "litellm_provider": "openai",
    "mode": "chat"
  }
}
Aider with Kimi K3.1 Pro Xploded Aider edits through its own diff format rather than tool calls, so it does not depend on tool calling. It does re-send the files you add on every turn, so add only what the change needs.

Kimi K3.1 Pro Xploded has its own page with every limit and price.

Uncensored Kimi K3.1 Pro sets it against the rest of the line, and uncensored Kimi goes through the Kimi releases one by one.

What a session costs

For a 12-turn Aider session (about 180K input tokens, half of them cache hits, 12K output), Kimi K3.1 Pro Xploded comes to about $1.20 at today's prices; the cache price does most of the work, since re-read context is billed at $0.80 rather than $7.50 per million.

FAQ

Can Kimi K3.1 Pro Xploded be used in Aider?

Yes. Aider does not depend on tool calling, so any chat model works; this one also brings a 1M context.

What does a session cost?

About $1.20 for a 12-turn Aider session (about 180K input tokens, half of them cache hits, 12K output), at $7.50 in, $37.50 out and $0.80 per million on cache hits. Put a spend cap on the key so a long run cannot overrun it.

Is it uncensored?

Kimi K3.1 Pro, uncensored: the strongest model on the line, with a million tokens of context, tool calling, reasoning and vision.

The other model in Aider