Kimi now has two current coding routes and several older access paths that should not be mixed together.

1
2
3
4
Need an explicit current API model? → Kimi K2.7 Code
Need lower latency? → Kimi K2.7 Code HighSpeed
Need Kimi's membership-backed CLI? → Kimi Code with kimi-for-coding
Need a zero-dollar experiment? → Verify a current hosted trial; it may expose older K2.5, not K2.7

Current Kimi Routes

RouteModel identityBillingBest for
Kimi K2.7 Code APIkimi-k2.7-codePay as you goReproducible coding API evaluation
Kimi K2.7 Code HighSpeedkimi-k2.7-code-highspeedPay as you go at 2x base token pricesLatency-sensitive coding
Kimi Code membershipkimi-for-coding, provider-managed backend aliasSubscription credits and quotasOfficial CLI and supported coding agents
Older hosted K2.5 routesK2.5 where explicitly listedTrial/free-provider termsHistorical or zero-dollar testing only

K2.7 Code is the current coding model. K2.6 remains a compatibility and prior-comparison lane; K2.5 remains historical/free-access context.

K2.7 API Pricing

Prices are per 1 million tokens.

ModelCache-hit inputCache-miss inputOutputContext
K2.7 Code$0.19$0.95$4.00256K
K2.7 Code HighSpeed$0.38$1.90$8.00256K
K2.6$0.16$0.95$4.00256K

K2.7 Code requires thinking mode in the documented API path. HighSpeed is the same model at higher token prices, with Kimi advertising approximately 180 tokens/s and up to 260 tokens/s for short contexts while warning that constrained resources can make performance fluctuate.

Kimi Code Membership

The current Kimi Code product page shows K2.7 Code and a new Node.js-based CLI:

1
2
curl -fsSL https://code.kimi.com/kimi-code/install.sh | bash
kimi

Membership-backed third-party tools use kimi-for-coding, a stable ID whose backend display model can change after upgrades. That is convenient but less reproducible than pinning kimi-k2.7-code.

Kimi documents weekly quota refresh, a rolling five-hour frequency window, shared device/API-key quota, and a unified monthly credit pool across membership features. Check the signed-in console for the current balance and exact plan terms.

The VS Code path is transitional: current docs say new extension installs are limited to legacy Python CLI users while the TypeScript CLI integration is adapted. Other editors can connect through ACP.

Free and Promotional Routes

The safe wording is narrow:

  • A third-party provider may offer trial credits or a free hosted K2.5 route.
  • That does not make K2.7 Code free.
  • A no-payment-required trial can be labeled Free only while the live signup requires no payment.
  • A discounted first month is Low-cost, not free.
  • Checkout screenshots and old campaign rules are not evergreen entitlements.

NVIDIA NIM K2.5 setup remains an older-model trial guide. Recheck the provider catalog, signup requirements, quota, and model ID before recommending it.

For a free coding IDE rather than Kimi specifically, use the Free Stack guide and verify its current hosted model roster.

Evidence and Quality

benchmark artifact

Kimi K2.7 and Current Coding Alternatives

ModelProviderStatusContextInput priceOutput priceCoding signalTool-use signalBenchmark evidenceSpeedVerdictSourcesChecked
Kimi K2.7 CodeMoonshot AIactive
Current Kimi coding API release; HighSpeed is the same model at higher token prices.
256K$0.95 / 1M$4.00 / 1MKimi positions K2.7 Code as its current coding model; independent normalized benchmarks are not imported.OpenAI-compatible API; thinking mode required in the documented K2.7 Code quickstart.
  • Program-Bench improvement vs K2.6: +10.4% (vendor)
  • MCP Mark Verified improvement vs K2.6: +11.4% (vendor)
  • SWE Marathon improvement vs K2.6: +76.2% (vendor)
  • Reasoning-token use vs K2.6: 30% lower (vendor)
  • AIHackers repo eval: not verified (site-owned)
HighSpeed model ID exists at a higher token price; latency not independently measured here.Current 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 Leaderboard2026-06-28
GLM-5.2Z.AIactive
Current Z.AI flagship coding model and supported-tool value lane.
1M$1.40 / 1M$4.40 / 1MZ.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 Intelligence Index v4.1: 51 (independent)
  • SWE-Bench Pro: 62.1 (vendor)
  • Terminal-Bench 2.1: 81.0 (vendor)
Artificial Analysis flags higher output-token use; measure total cost per successful task.July value pick to test for supported coding-tool workflows; keep Opus/GPT for final arbitration until local evals pass.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 Leaderboard2026-06-28
Gemini 3 FlashGoogleactive
Current Gemini value lane where Gemini API or Vertex AI fits.
1.05M input$0.50 / 1M$3.00 / 1Mnot verifiedFunction calling and code execution supported.not verifiedPreview model positioned for lower latency; independent value not imported.High-context value lane when Gemini API or Vertex AI fits.Gemini API models, Gemini API pricing, Artificial Analysis: Gemini 3 Flash, LMArena leaderboard dataset2026-05-26
Claude Sonnet 5Anthropicactive
Generally available across Claude plans, Claude Code, the Claude API, GitHub Copilot, and supported AWS paths.
1M$2.00 / 1M$10.00 / 1MAnthropic 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.
  • Cross-model benchmark evidence: vendor-reported; updated chart and system card preferred (vendor)
  • Independent normalized evaluation: not verified (independent)
  • AIHackers repo eval: not verified (site-owned)
No site-owned normalized latency result is verified.First Claude cost/performance test before Opus API pricing; retain Opus for highest-accuracy arbitration.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]2026-07-01
Claude Opus 4.8Anthropicactive
Current generally available Opus-tier premium baseline.
1M$5.00 / 1M$25.00 / 1MPractical premium Claude baseline; AIHackers recommends task-level comparison rather than blanket default routing.Claude API and Claude-native workflow baseline; third-party routing must follow Anthropic terms.
  • Artificial Analysis Intelligence Index v4.0: 61 (independent)
  • Artificial Analysis output speed: 60.4 tokens/s (independent)
Artificial Analysis measured 60.4 output tokens/s; provider and workload latency vary.Premium review, architecture, hard-debugging, and final-arbitration lane.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 Leaderboard2026-06-28

K2.7 improvements remain vendor-reported. No independent normalized K2.7 score or AIHackers-owned repository result is currently verified.

Kimi’s June 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 the “vendor” label attached: these are relative K2.6 deltas, not absolute scores that can be compared directly with Opus, GLM, or SWE-bench Verified.

Do not reuse K2.5’s 76.8% SWE-bench Verified result as a K2.7 score.

Cost per Successful Task

Run the same repository task and record:

  • exact model ID or backend alias;
  • input, output, cache hits, and cache writes;
  • retries and wall-clock time;
  • tests and accepted completion;
  • human review and repair.

The HighSpeed premium is justified only if lower latency changes the workflow. The membership is justified only if its credits and tool convenience beat measured API use for the same accepted tasks.

Which Route to Choose

RequirementRecommended route
Explicit current model and repeatable API testK2.7 Code API
Lowest K2.7 cache-hit costBase K2.7 Code
Lowest latencyHighSpeed after measuring the premium
Official Kimi CLI and third-party coding agentsKimi Code membership
One-off zero-dollar testA currently verified trial, with the actual model labeled
1M contextCompare GLM-5.2, Gemini, MiniMax, or Xiaomi instead
Premium final reviewClaude Opus 4.8 or another approved premium lane

Sources


Last verified: June 28, 2026. API prices, HighSpeed capacity, membership aliases, credits, checkout terms, and third-party free routes can change independently.