OpenRouter offers a single API for accessing a wide range of large language models (LLMs) from multiple providers. It supports over 300 models from more than 60 active providers, such as OpenAI (e.g., GPT-5.1), Anthropic (e.g., Claude Opus 4.5), Google (e.g., Gemini 3 Pro Preview), and others like Meta, Microsoft, and NVIDIA. The API is fully compatible with the OpenAI SDK, allowing for easy integration. Key features include routing optimization for better uptime and competitive pricing without subscriptions. Typical use cases include AI-powered applications, research, and enterprise solutions requiring multi-model access.
A unified API interface providing access to over 300 models from 60+ providers, including OpenAI, Anthropic, and Google.
- Models
- 561 models
- From
- --
- Speed
- 85 tok/s
- Updated
- 7/10/2026
- Latency
- 0.00 s
- Created At
- 8/13/2025
API Endpoints
- Endpoint 1
openrouter.ai
Claim this provider
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 OpenRouter
Health Check
100%Recent availability
History (72 pts)
PastNow
API Benchmarks & Pricing
Compare 557 model rows across audit recency, latest speed tests, throughput, latency, and per-token pricing.
~z-ai/glm-latest |
deepseek/deepseek-v4-flash-vision-exp |
meta/muse-spark-1.2-contributor |
minimax/minimax-m2.7:free |
minimax/minimax-m3:free |
mistralai/ministral-8b |
qwen/qwen3.8-flash |
tencent/hy-mt2-1.8b |
tencent/hy-mt2-30b-a3b |
tencent/hy-mt2-7b |
thinkingmachines/inkling-small:free |
thinkingmachines/inkling:free |
z-ai/glm-5.3 |
z-ai/glm-5.3-flash |
z-ai/glm-5.2:free |
dots-studio/dots-3-note-preview:free |
google/gemini-3.7-flash |
google/gemini-3.7-flash:batch |
qwen/qwen3.8-27b |
bytedance-seed/seed-2-1-turbo |
deepseek/deepseek-v4-pro-0813 |
qwen/qwen3.8-2.4t-a95b |
x-ai/grok-4.6 |
bytedance-seed/seed-2.0-code |
liquid/lfm-2.5-2.6b:free |
Showing 25 of 557 model rows
Recent Test Records
| Time | Model | Speed | Latency |
|---|---|---|---|
| Aug 9, 07:55 AM | nvidia/nemotron-3-ultra-550b-a55b:free | 36.00 tok/s | 5.37s |
| Jun 2, 11:36 AM | openai/gpt-oss-120b:free | 32.22 tok/s | 2.89s |
| May 22, 12:52 AM | deepseek/deepseek-v4-flash | 88.40 tok/s | 3.31s |
| May 22, 12:51 AM | inception/mercury-2 | 617.82 tok/s | 0.85s |
| May 9, 08:20 AM | x-ai/grok-4.3 | 48.69 tok/s | 6.49s |
| May 9, 06:58 AM | deepseek/deepseek-v4-pro | 36.31 tok/s | 12.13s |
| May 2, 06:45 AM | nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free | 110.33 tok/s | 9.33s |
| Apr 28, 08:00 PM | openai/gpt-oss-120b:free | 25.78 tok/s | 2.49s |
| Apr 27, 09:59 AM | openai/gpt-oss-120b:free | 30.93 tok/s | 1.64s |
| Apr 26, 12:23 PM | openai/gpt-oss-120b:free | 35.22 tok/s | 1.54s |
Similar API Provider Alternatives to Compare
Compare OpenRouter alternatives against 6 nearby API providers using 1207 LMSpeed signals across shared model coverage, pricing, benchmark speed, uptime, and free-model availability.
| Provider | Why compare | Models | Free | Avg price | Speed | 30d uptime |
|---|---|---|---|---|---|---|
| OpenRouter openrouter A unified API interface providing access to over 300 models from 60+ providers, including OpenAI, Anthropic, and Google. | Current provider baseline | 561 | 0 | N/A | 85 tok/s | 9990% |
| 并行科技 llmapi-paratera-com Provides high-performance computing (HPC) and AI infrastructure services, including GPU cloud servers, MaaS platforms, and industry-specific solutions. |
| 97 | 0 | N/A | 195 tok/s | 0% |
| 七牛云 qiniu-2 七牛云提供AI大模型推理服务，包括多种模型调用、智能问答助手、代码助手等企业级AI解决方案。 |
| 89 | 0 | N/A | 90 tok/s | 9980% |
| Fireworks AI api-fireworks-ai Fireworks AI provides a cloud platform for running and fine-tuning open-source AI models with optimized inference for production applications. |
| 36 | 0 | N/A | 139 tok/s | 7190% |
| 共绩算力（算了么 API） api-suanli-cn Gongji Compute (共绩算力) provides pay-as-you-go, standard API access to mainstream LLMs and elastic GPU computing for AI applications. |
| 15 | 5 | N/A | 36 tok/s | 5620% |
| iTokens itokens iTokens is an OpenAI-compatible AI API gateway with usage-based access to models from DeepSeek, GLM, Kimi, Qwen, MiniMax, KwaiKAT, and other developers. It publishes per-model token pricing and offers promotional credits to new users. |
| 12 | 0 | $0.168/M | 149 tok/s | 9920% |
| Kriora api-kriora-com Provides OpenAI-compatible APIs and managed GPU instances for deploying and scaling open-source AI models. |
| 11 | 0 | N/A | 565 tok/s | 9970% |
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.