NewHow we catch a seller listing the wrong model, and refund you if one does.
MoonshotAI logo

How do I use MoonshotAI: Kimi K3.1 Pro in Claude Code?

moonshotai/kimi-k3.1-pro

Claude Code reaches MoonshotAI: Kimi K3.1 Pro through the Anthropic-compatible address of MartLLM. Set ANTHROPIC_BASE_URL to https://api.martllm.com (with no /v1 at the end), ANTHROPIC_AUTH_TOKEN to your MartLLM key and ANTHROPIC_MODEL to moonshotai/kimi-k3.1-pro[1m], then start claude. Set the opus, sonnet, haiku and subagent model variables to moonshotai/kimi-k3.1-pro as well: a slot left unset keeps asking for a Claude model at Claude prices. The [1m] at the end of the id tells Claude Code that MoonshotAI: Kimi K3.1 Pro has a 1M-token context; without it Claude Code plans for 200,000 tokens.

bash
export ANTHROPIC_BASE_URL=https://api.martllm.com
export ANTHROPIC_AUTH_TOKEN=ull_your_key
export ANTHROPIC_MODEL='moonshotai/kimi-k3.1-pro[1m]'
export ANTHROPIC_DEFAULT_OPUS_MODEL='moonshotai/kimi-k3.1-pro'
export ANTHROPIC_DEFAULT_SONNET_MODEL='moonshotai/kimi-k3.1-pro'
export ANTHROPIC_DEFAULT_HAIKU_MODEL='moonshotai/kimi-k3.1-pro'
export CLAUDE_CODE_SUBAGENT_MODEL='moonshotai/kimi-k3.1-pro'
claude

Claude Code calls: Anthropic Messages API https://api.martllm.com/v1/messages · Full Claude Code guide

Replace ull_your_key with your MartLLM API key. One key works in every tool and for every model.

By API, MoonshotAI: Kimi K3.1 Pro answers on three addresses with the same MartLLM key and the model id moonshotai/kimi-k3.1-pro: OpenAI chat completions at https://api.martllm.com/v1/chat/completions, the OpenAI Responses API at https://api.martllm.com/v1/responses and the Anthropic Messages API at https://api.martllm.com/v1/messages.

How much does the MoonshotAI: Kimi K3.1 Pro API cost?

On November 20, 2026, MoonshotAI: Kimi K3.1 Pro costs $0.2054 per million input tokens and $1.027 per million output tokens through MartLLM, 89.7% below its list price of $2.00 and $10.00. 95 sellers on the market can serve it. In the 7 days before, half of its 5,721 streamed requests got their first token within 5.1 seconds, with a typical prompt of 145,073 tokens. It reads up to 1,048,576 tokens of context. MartLLM adds no fee to these prices, and a request that fails is not billed.

Prices as of 11:00 UTC.

MoonshotAI: Kimi K3.1 Pro in other tools

Other models in Claude Code