New API is a unified LLM API gateway that offers access to various AI models from providers like OpenAI, Claude, Gemini, and others. It supports multiple endpoints including chat completions, embeddings, image generation, and audio processing. The service emphasizes competitive pricing and stability without subscription requirements. Users can integrate by replacing the model base URL with provided endpoints such as /v1/chat/completions and /v1/embeddings. Key features include support for over 30 providers, including MoonshotAI, Zhipu, Cohere, and DeepSeek, with endpoints for text, image, and audio tasks.
Koru API
new.api.koru.ink
Koru API delivers an OpenAI-compatible API relay with seamless access to a wide range of AI models.
- Models
- 60 models
- From
- --
- Speed
- 516 tok/s
- Updated
- 6/8/2026
- Latency
- 0.00 s
- Created At
- 3/30/2026
- Recharge Rate
- ¥7.30 per $1 quota
Features
API Endpoints
- Endpoint 1Historical / Unverified
https://new.api.koru.ink
Verify ownership to unlock provider management features:
- Edit provider name, content, and links
- Get featured with priority traffic and visibility boost
- Display a verified badge to build user trust
Leaderboard Rankings
Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.
About Koru API
Health Check
API Benchmarks & Pricing
Compare 49 model rows across audit recency, latest speed tests, throughput, latency, and per-token pricing.
baidu/cobuddy:freedefault | $75.00/M | $75.00/M | - | - |
elf-basedefault | $75.00/M | $75.00/M | - | - |
qwen3.6-35b-a3b | - | - | - | - |
talkie-lmdefault | $75.00/M | $75.00/M | 93.7 t/s | 0.87 s |
| $75.00/M | $75.00/M | - | - | |
poolside/laguna-xs.2:freedefault | $75.00/M | $75.00/M | - | - |
poolside/laguna-m.1:freedefault | $75.00/M | $75.00/M | - | - |
| $75.00/M | $75.00/M | - | - | |
gemma-4-e2b-it | - | - | 224.1 t/s | 1.55 s |
deepseek-expert-chatdefault | $75.00/M | $75.00/M | - | - |
gemini-2.5-flash-禁止用于openclaw等default | $75.00/M | $625.00/M | 203.6 t/s | 3.90 s |
grok-4.20-0309-non-reasoningdefault | $75.00/M | $75.00/M | - | - |
grok-4.20-0309-reasoningdefault | $75.00/M | $75.00/M | - | - |
deepseek-expert-reasonerdefault | $75.00/M | $75.00/M | - | - |
deepseek-reasonerdefault | $0.550/M | $0.550/M | - | - |
deepseek-chatdefault | $0.270/M | $0.270/M | - | - |
| $75.00/M | $75.00/M | - | - | |
google/gemma-4-31b-it:freedefault | $75.00/M | $75.00/M | - | - |
| $75.00/M | $75.00/M | - | - | |
llama3.1-8Bdefault | $75.00/M | $75.00/M | 891.4 t/s | 0.91 s |
minimax-m2.7default | $75.00/M | $75.00/M | - | - |
| $75.00/M | $75.00/M | - | - | |
| - | - | 63.6 t/s | 13.78 s | |
| - | - | 164.7 t/s | 7.09 s | |
mercury-2default | $75.00/M | $75.00/M | 458.6 t/s | 0.90 s |
Showing 25 of 49 model rows
Recent Test Records
| Time | Model | Speed | Latency |
|---|---|---|---|
| May 2, 05:48 PM | talkie-lm | 93.73 tok/s | 0.87s |
| May 2, 05:47 PM | llama3.1-8B | 660.66 tok/s | 0.64s |
| Apr 29, 03:22 AM | mercury-2 | 537.27 tok/s | 0.75s |
| Apr 29, 03:21 AM | mercury-2 | 364.18 tok/s | 0.83s |
| Apr 29, 03:21 AM | mercury-2 | 447.03 tok/s | 0.99s |
| Apr 29, 03:17 AM | llama3.1-8B | 935.36 tok/s | 0.39s |
| Apr 29, 03:17 AM | llama3.1-8B | 890.44 tok/s | 0.53s |
| Apr 29, 03:16 AM | llama3.1-8B | 1687.87 tok/s | 0.38s |
| Apr 29, 03:16 AM | llama3.1-8B | 814.09 tok/s | 0.53s |
| Apr 21, 11:43 AM | gemma-4-e2b-it | 266.55 tok/s | 1.61s |
Similar API Provider Alternatives to Compare
Compare Koru API alternatives against 6 nearby API providers using 229 LMSpeed signals across shared model coverage, pricing, benchmark speed, uptime, and free-model availability.
| Provider | Why compare | Models | Free | Avg price | Speed | 30d uptime |
|---|---|---|---|---|---|---|
| Koru API new-api-koru-ink Koru API delivers an OpenAI-compatible API relay with seamless access to a wide range of AI models. | Current provider baseline | 60 | 45 | N/A | 516 tok/s | 0% |
| Koyeb AI Gateway new-api-koyeb-app An OpenAI-compatible API gateway deployed on Koyeb, providing access to multiple AI models. |
| 578 | 420 | N/A | 33 tok/s | 9970% |
| OpenRouter openrouter A unified API interface providing access to over 300 models from 60+ providers, including OpenAI, Anthropic, and Google. |
| 547 | 0 | N/A | 85 tok/s | 9990% |
| LLMService llmservice LLMService provides API access to large language models for self-use applications. |
| 425 | 0 | N/A | 139 tok/s | 3300% |
| DeadlySignal API deadlysignal |
| 290 | 0 | N/A | 63 tok/s | 9960% |
| Gitee AI gitee-ai Gitee AI provides a platform for AI model hosting, inference, and deployment with access to open-source LLMs. |
| 260 | 0 | N/A | 88 tok/s | 5470% |
| CHB API api-464888-xyz Provides API access to AI models including GPT-4, Claude, and Gemini through a unified interface. |
| 191 | 356 | N/A | N/A | 0% |
Notes
- Health checks: Scope: the 72-hour chart and recent availability measure API connectivity only. Each bar summarizes one hour of checks. Targets: LMSpeed tries the configured health check URL and provider status URL first, then API endpoints derived from known API hosts and recent speed-test base URLs. A website host is considered only when it looks like an API endpoint. Probe steps: each candidate goes through DNS lookup, TCP connection, TLS handshake for HTTPS, and an HTTP HEAD request with redirects followed. Probing stops after the first reachable candidate. Reachable criteria: every required network step must succeed. An HTTP response below 500 is treated as reachable, including 401 because it confirms that an authenticated API endpoint responded, except for statuses classified as blocked. Blocked results: HTTP 403, 429, 521, 525, and 530, plus detected WAF or Cloudflare challenges, are shown as blocked and excluded from availability calculations because LMSpeed cannot determine whether the API itself is down. Model availability: when a dedicated test key is configured, LMSpeed sends an authenticated GET request to a derived /models endpoint and compares returned model IDs with this provider's listed models. These per-model results appear in Models & Pricing and are not included in the provider connectivity percentage. Timeouts: TCP connection, TLS handshake, HTTP connectivity, and model requests each use a 20-second timeout. A full run can take longer when several candidates are tried. Frequency: a background worker checks all providers every 5 minutes by default. The 72-hour chart combines those samples into hourly bars, and the schedule may be changed by the service operator. Limit: automated samples are not an SLA and do not guarantee account quota, every model, every region, or successful completion requests. Check the provider's own status page before making operational decisions.
- Domain Rating data is sourced from Ahrefs. It is a 0–100 backlink-based domain strength signal and does not measure API speed or reliability.
- Announcements and FAQ are read from this provider's NewAPI status snapshot when available. LMSpeed stores the original content and optional English translations from the provider status source, then shows the localized fields on this page.
