Kimi Code is Moonshot’s coding membership for its CLI and compatible coding agents. To choose a workflow, start with the Codex, Claude Code and Kimi Code comparison.
October 13, 2026 documentation check: Kimi’s model configuration now lists K3, K2.8 Preview and K2.7 Code HighSpeed; kimi-for-coding has moved to K2.8 Preview. New membership plans remove the weekly quota, while legacy plans retain it. Five-hour and monthly limits still apply. Verify the displayed model and plan in your account.
The sections below preserve the July 18 documentation snapshot, including client support, quotas and API details. The K3 and K2.7 Code API evidence does not evaluate K2.8 Preview or price a membership quota. Account access and checkout remain untested here.
July 18 Status Snapshot
| Item | July 18 read |
|---|---|
| Product models shown | Kimi K3 and Kimi K2.7 Code |
| CLI | Node.js-based Kimi Code CLI |
| Tool-facing model IDs | k3, kimi-for-coding, kimi-for-coding-highspeed |
| Protocols | OpenAI-compatible and Anthropic-compatible endpoints |
| Membership accounting | Shared Kimi credits plus Kimi Code quota/rate windows |
| API platform billing | Separate pay-as-you-go Kimi Platform product |
The tool-facing IDs are not the same contract as explicit Kimi Platform API IDs such as kimi-k3 or kimi-k2.7-code. Record the displayed backend model when reproducibility matters.
Install and Authenticate
| |
Use /login for the official OAuth flow. Membership users can also create API keys for supported third-party tools.
The July 18 Kimi docs listed membership/tool routes separately from the Kimi Platform API. Explicit API model IDs were kimi-k3 and kimi-k2.7-code through the Kimi API platform.
- OpenAI-compatible base URL:
https://api.kimi.com/coding/v1 - Anthropic-compatible base URL:
https://api.kimi.com/coding/ - Model IDs:
k3,kimi-for-coding, orkimi-for-coding-highspeeddepending on client and entitlement
Keep the tool’s real identity/User-Agent. Kimi warns that spoofing the client identity can suspend membership benefits.
CLI, IDE, and Third-Party Tools
The July 18 CLI docs listed code reading, file editing, command execution, web search, goals, MCP, skills, plugins, hooks, and subagents.
The July 18 VS Code docs limited new extension installations to legacy Python CLI users while the TypeScript CLI integration was adapted. They said existing users could continue and other editors could connect through the CLI’s ACP protocol; this is historical client guidance.
Third-party integrations include Claude Code, Roo Code, OpenCode, OpenClaw, and compatible agent frameworks. Compatibility does not mean unlimited use or a direct K2.7 pay-as-you-go entitlement.
Quotas and Credits
The July 18 membership read recorded two layers; the weekly rule below now applies only to legacy plans:
- Kimi Code quota refreshes every seven days from the subscription date; unused weekly quota does not carry over.
- A rolling five-hour frequency window can rate-limit bursts even when weekly quota remains.
All logged-in devices and Kimi Code API keys share the same account quota. The July 18 credit update described a unified monthly pool, including Kimi Code, and said exhausting it could freeze new Code work until refresh or upgrade.
Do not preserve older fixed request-count promises as current guarantees. Check the console and subscription page for the account’s remaining credits, frequency status, and next refresh.
Membership vs Pay-As-You-Go API
| Question | Kimi Code membership | Kimi Platform API |
|---|---|---|
| Billing | Subscription credits and quotas | Pay as you go |
| Model ID | k3, kimi-for-coding, or kimi-for-coding-highspeed | kimi-k3, kimi-k2.7-code, or kimi-k2.7-code-highspeed |
| Best fit | Terminal/IDE agent programming | Product integration and measured API workloads |
| Reproducibility | Backend alias can upgrade | Explicit model ID |
| Limits | Weekly, five-hour, and monthly credit controls | Published API rates and provider rate limits |
| K3 reasoning | low, high, or max through membership model ID k3 | max only in the July 18 pay-as-you-go API guide |
| K3 context | Moderato: up to 256K; Allegretto and above: up to 1M | 1M model context, subject to API request limits |
The July 18 K3 API pricing read was $0.30 cache-hit input, $3.00 cache-miss input, and $15.00 output per million tokens. K2.7 Code was $0.19 cache-hit input, $0.95 cache-miss input, and $4.00 output per million tokens, with HighSpeed at twice those K2.7 prices. These are dated API rates; do not use them to calculate the value of a membership quota without measured consumption.
Do not transfer Kimi Code settings to the API by analogy. In the July 18 read, membership k3 supported low/high/max reasoning and plan-dependent 256K/1M context; pay-as-you-go kimi-k3 used always-on, max-only reasoning. Start a new session when changing the membership model or reasoning effort so the old context cache is not mistaken for a reusable K3 session.
Model Evidence
benchmark artifact
Kimi Code and Dated Comparison Evidence
| Model | Provider | Status | Context | Input price | Output price | Coding signal | Tool-use signal | Benchmark evidence | Speed | Verdict | Sources | Checked |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Kimi K3 | Moonshot AI |
active Kimi API/product flagship; Kimi K3 License weights. NVIDIA also lists K3 under trial terms as checked September 14; account access untested. | 1M | $3.00 / 1M $0.30 cache-hit / $3.00 cache-miss input / $15.00 output per 1M tokens | $15.00 / 1M | Moonshot reports strong max-reasoning launch-suite coding and agent results; AIHackers repo eval is not verified. | Kimi API and Kimi Code support K3; Kimi docs warn to preserve full assistant history and avoid mid-session model switching. |
| Artificial Analysis reports 62 output tokens/s and flags high verbosity; measure total output cost per accepted task. | Test as Kimi's newest 1M-context frontier-adjacent lane; keep K2.7 Code for cheaper routine Kimi coding until K3 passes local CAR tests. | NVIDIA Kimi K3 model card, Kimi K3 launch blog [archive], Kimi K3 quickstart [archive], Kimi K3 API pricing [archive], Kimi K3 weights and license [archive], Kimi current model list [archive], Kimi Code model configuration, Artificial Analysis: Kimi K3 [archive] | 2026-08-01 |
| Kimi K2.7 Code | Moonshot AI |
active Cheaper routine Kimi coding API lane; HighSpeed is the same model at higher token prices. | 256K | $0.95 / 1M $0.19 cache-hit / $0.95 cache-miss input / $4.00 output per 1M tokens; HighSpeed doubles those rates | $4.00 / 1M | Kimi K2.7 Code remains the lower-cost 256K coding lane after K3; independent normalized benchmarks are not imported. | OpenAI-compatible API; thinking mode required in the documented K2.7 Code quickstart. |
| HighSpeed model ID exists at a higher token price; latency not independently measured here. | Cheaper routine Kimi coding API lane when Kimi routing fits and 256K context is enough. | Kimi K2.7 Code quickstart [archive], Kimi K2.7 Code pricing [archive], Kimi Code K2.7 release notes [archive], SWE-bench, Berkeley Function Calling Leaderboard | 2026-06-28 |
| GLM-5.2 | Z.AI |
historical Historical July comparison; Z.AI now documents GLM-5.3. These scores and prices do not evaluate 5.3. Historical status does not imply API retirement. | 1M | $1.40 / 1M $1.40 input / $0.26 cached input / $4.40 output per 1M tokens | $4.40 / 1M | Z.AI reports 62.1 on SWE-Bench Pro and 81.0 on Terminal-Bench 2.1. | Supported-tool coding lane; BFCL score not imported. |
| Artificial Analysis flags higher output-token use; measure total cost per successful task. | Dated July value candidate; retain for pinned integrations and historical comparisons. Check the newer GLM revision separately before new routing decisions. | Z.AI GLM-5.3 successor documentation, Z.AI GLM-5.2 overview [archive], Z.AI pricing [archive], Artificial Analysis: GLM-5.2 article [archive], Artificial Analysis Intelligence Index v4.1, SWE-bench, Berkeley Function Calling Leaderboard | 2026-06-28 |
| Claude Sonnet 5 | Anthropic |
active Generally available across Claude plans, Claude Code, the Claude API, GitHub Copilot, and supported AWS paths. | 1M | $2.00 / 1M $2.00 input / $10.00 output checked September 27; earlier launch schedule superseded | $10.00 / 1M | Anthropic reports substantial coding and agentic gains over Sonnet 4.6; independent normalized results are pending. | Available in Claude Code and the Claude API; adaptive thinking is on by default. |
| No site-owned normalized latency result is verified. | First Claude cost/performance test before Opus 5.5; escalate only when the premium pass changes the accepted result. | Claude Sonnet 5 current specifications, Anthropic Claude Sonnet 5 launch [archive], Claude Sonnet 5 migration guide [archive], GitHub Copilot Claude Sonnet 5 launch [archive], Claude Sonnet 5 on AWS [archive], Artificial Analysis: Claude Opus 5 [archive] | 2026-09-27 |
| Claude Opus 4.8 | Anthropic |
historical Historical comparison; use Opus 5.5 for current premium evaluation. | 1M | $5.00 / 1M $5.00 input / $25.00 output per 1M tokens | $25.00 / 1M | Historical premium Claude baseline; use Opus 5 for new task-level comparisons. | Still available for pinned integrations; new Claude premium routing should test Opus 5. |
| Artificial Analysis measured 57.3 output tokens/s; provider and workload latency vary. | Historical premium baseline. Use Claude Opus 5.5 for current Claude premium routing. | Claude models overview [archive], Claude API pricing [archive], Artificial Analysis: Claude Opus 4.8 [archive], Artificial Analysis Intelligence Index v4.1, LMArena leaderboard dataset, Berkeley Function Calling Leaderboard | 2026-07-25 |
| GPT-5.5 | OpenAI |
active Prior generation; October 14 retirement announced for ChatGPT/Work/Codex sign-in, not API. Dated metrics retained. | 1.05M API; 400K Codex | $5.00 / 1M $5.00 input / $30.00 output per 1M tokens | $30.00 / 1M | not verified | not verified | not verified | not verified | Primary coding seat while ChatGPT/Codex limits fit the workload. | OpenAI GPT-5.5 API model page, OpenAI GPT-5.5 ChatGPT limits, Artificial Analysis: GPT-5.5, LMArena leaderboard dataset | 2026-06-28 |
Kimi Code membership uses provider-managed tool IDs; the K3 and K2.7 rows describe explicit pay-as-you-go API models. Record the actual displayed backend model for tool evaluations.
Kimi K3 has early independent Artificial Analysis evidence and Moonshot launch-suite evidence, but no AIHackers-owned repository eval. Kimi K2.7 Code’s earlier release notes report improvements over K2.6 of 10.4% on Program-Bench, 11.4% on MCP Mark Verified, and 76.2% on SWE Marathon, plus 30% lower reasoning-token use. Keep both sets source-labeled.
Evaluation Checklist
- Confirm the displayed backend model and client version.
- Pin the repository commit and task.
- Record weekly quota, five-hour window, and monthly credit state.
- Run tests and review the final diff.
- Record retries, latency, accepted completion, and human repair.
- Re-run after a backend alias upgrade before comparing with older results.
Pricing and Checkout
The July 18 public product-page read exposed purchase controls without a stable, complete checkout table. Treat the signed-in checkout as the final source for plan price, renewal, promotion, tax, region, and cancellation terms.
Do not describe old haggling, first-month pricing, trial banners, or fixed benefit counts as current unless the live checkout and terms still show them.
Verdict
Choose Kimi Code when you want the official Kimi CLI or a membership-backed route into compatible coding agents. Choose the explicit K3 or K2.7 API when model identity, per-token accounting, multimodal API behavior, or reproducible evaluation matters more than membership convenience.
Sources
- Kimi: Kimi Code
- Kimi: Kimi Code model configuration (fresh archive pending after exact/protocol/wildcard retries and an HTTP 520 save response on July 18)
- Kimi: Kimi K3 launch blog (Archive)
- Kimi: K2.7 Code release notes (Archive)
- Kimi: Membership credit update (Archive)
- Kimi Platform: K2.7 Code quickstart (Archive)
- Kimi Platform: K2.7 Code pricing (Archive)
- Kimi Platform: K3 quickstart (Archive)
- Kimi Platform: K3 pricing (Archive)
Related links
- /models/kimi-k3/
- /models/kimi-k2.7-code/
- /value/kimi-access/
- /compare/codex-vs-claude-vs-kimi/
- /compare/models/budget-tier/
- /risks/kimi/
Documentation snapshot: July 18, 2026. The October 13 check covers only the linked model configuration and new-versus-legacy quota rules. Backend aliases, client support, API prices, account entitlements and checkout can change independently.