Kimi K3 in OpenCode: What One Finished Coding Task Actually Cost

A developer at Vancine, a third-party API aggregation platform, tested Kimi K3 on a single coding task using OpenCode, finding it cost $0.19 to complete a leap-year fix in 84 seconds. The run used 28,707 tokens and passed all tests, highlighting that per-task cost matters more than per-token price for coding agents.

Kimi K3 launched with impressive benchmark results—and a lot of debate about its price. For developers using coding agents, however, price per million tokens is only part of the story. A more useful question is: How much does it cost to finish an actual coding task—with file reads, edits, tool calls, and passing tests? We ran one controlled Kimi K3 coding task through OpenCode and recorded the result. Disclosure:I work on Vancine, a third-party API aggregation platform. Vancine is not Moonshot AI and is not an official Kimi service. The cost below is measured Vancine usage for one specific run, not official Kimi pricing or a fixed-price promise. The agent received a small repository containing a faulty leap-year implementation. It had to: The run used OpenCode v1.18.3 inside an isolated Docker Linux ARM64 environment. | Metric | Result | |---|---| | Completed model steps | 6 | | Completed tool calls | 7 | | File reads | 5 | | Source edits | 1 | | Shell commands | 1 | | Failed tool calls | 0 | | Total tokens | 28,707 | | Duration | 84.3 seconds | | Tests passed | Yes | | Measured Vancine usage | $0.19 | The 28,707 total tokens included: The run completed without recorded HTTP 429 responses, HTTP 5xx responses, provider errors, or permission failures. You can inspect the sanitized machine-readable evidence here: Kimi K3 OpenCode verification evidence https://github.com/VancineAI/kimi-k3-api-starter/blob/main/results/opencode-agent.verified.json For this specific task, Kimi K3 successfully: The source file was modified, the test file remained unchanged, and no unexpected files were created. This is one controlled task—not a general benchmark. It does not prove that: Cline and Roo Code configuration examples are included in the starter repository, but they have not yet been independently live-verified. Only the recorded OpenCode v1.18.3 task is verified. Coding agents rarely make one isolated API request. A normal agent loop may: Because of that, the cheapest model per token is not necessarily the cheapest model per finished task. A useful coding-model evaluation should report: One task is not a leaderboard, but it is a more concrete starting point than benchmark scores or token prices alone. Vancine exposes the model alias kimi-k3 through an OpenAI-compatible API. A minimal OpenCode provider configuration looks like this: { "$schema": "https://opencode.ai/config.json", "provider": { "vancine": { "npm": "@ai-sdk/openai-compatible", "name": "Vancine", "options": { "baseURL": "https://vancine.com/v1", "apiKey": "{env:VANCINE API KEY}" }, "models": { "kimi-k3": { "name": "Kimi K3" } } } } } Keep the API key in an environment variable: export VANCINE API KEY="your-api-key" opencode Then select: vancine/kimi-k3 Do not commit real API keys to source control or paste them into shared configuration files. The same model can be called through the OpenAI-compatible Chat Completions endpoint: curl https://vancine.com/v1/chat/completions \ -H "Authorization: Bearer $VANCINE API KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "kimi-k3", "messages": { "role": "user", "content": "Review this function and identify the bug." } }' The Vancine model alias is kimi-k3 . Kimi’s first-party documentation uses k3 for the official Kimi Code model ID, so always use the identifier required by the provider you are connecting to. The public starter repository includes: View the Kimi K3 API Starter on GitHub https://github.com/VancineAI/kimi-k3-api-starter You can also open the complete quick start here: New Vancine accounts currently receive $1 in starting credit , with no credit card required. Usage depends on the model, prompt size, context, tool loop, and number of requests. The starting credit does not guarantee that any particular coding task will complete within that amount. The broader takeaway is simple: For coding agents, measure the cost of reaching a tested solution—not just the price of generating a token.