ClaudeAPI is a third-party relay that forwards traffic to Anthropic's Claude models — it is NOT the official Anthropic API. The service supports both Anthropic and OpenAI request formats with pay-as-you-go pricing in CNY at roughly 80% of official rates (e.g. Opus $4 input / $20 output vs official $5 / $25). Models include Claude Opus 4.7 / 4.6 / 4.5, Sonnet 4.6 / 4.5 and Haiku 4.5. Claims 99.8% uptime, sub-200ms latency and zero data retention. Gateway endpoint: gw.claudeapi.com.
ClaudeAPI Relay
console.claudeapi.com
Third-party Claude-only relay (not Anthropic official) — RMB pay-as-you-go at ~80% of official Claude pricing.
- Models
- 21 models
- From
- $0.065/M
- Speed
- 46 tok/s
- Updated
- 6/8/2026
- Latency
- 0.00 s
- Created At
- 4/27/2026
- Recharge Rate
- ¥7.00 per $1 quota
Features
API Endpoints
- Endpoint 1Historical / Unverified
https://www.claudeapi.com - Endpoint 2Historical / Unverified
https://console.claudeapi.com - Endpoint 3Historical / Unverified
https://claudeapi.com - Endpoint 4Historical / Unverified
https://gw.claudeapi.com
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 ClaudeAPI Relay
Health Check
API Benchmarks & Pricing
Compare 21 model rows across audit recency, latest speed tests, throughput, latency, and per-token pricing.
claude-opus-5default | $4.00/M | $20.00/M | - | - | ||||||||||
gemini-3.6-flashdefault | $0.975/M | $4.88/M | - | - | ||||||||||
gemini-3.5-flash-litedefault | $0.195/M | $1.63/M | - | - | ||||||||||
claude-sonnet-5default | $1.60/M | $8.00/M | - | - | ||||||||||
gemini-3.1-flash-imagedefault | $0.325/M | $39.00/M | - | - | ||||||||||
gemini-3-pro-imagedefault | $1.30/M | $78.00/M | - | - | ||||||||||
claude-fable-5default | $8.00/M | $40.00/M | - | - | ||||||||||
claude-opus-4-8default | $4.00/M | $20.00/M | 45.6 t/s | 2.08 s | ||||||||||
gemini-3.5-flashdefault | $0.975/M | $5.85/M | - | - | ||||||||||
claude-opus-4-7default | $4.00/M | $20.00/M | - | - | ||||||||||
gpt-5.5default | $3.50/M | $21.00/M | - | - | ||||||||||
gpt-5.4default | $1.75/M | $10.50/M | - | - | ||||||||||
gemini-3.1-pro-previewdefault | $1.30/M | $7.80/M | - | - | ||||||||||
claude-sonnet-4-6default | $2.40/M | $12.00/M | - | - | ||||||||||
claude-opus-4-6default | $4.00/M | $20.00/M | - | - | ||||||||||
gemini-3-flash-previewdefault | $0.325/M | $1.95/M | - | - | ||||||||||
claude-haiku-4-5-20251001default | $0.800/M | $4.00/M | - | - | ||||||||||
gemini-2.5-flash-imagedefault | $0.195/M | $19.50/M | - | - | ||||||||||
gemini-2.5-flash-litedefault | $0.065/M | $0.260/M | - | - | ||||||||||
gemini-2.5-flashdefault | $0.195/M | $1.63/M | - | - | ||||||||||
gemini-2.5-prodefault | $0.813/M | $6.50/M | - | - |
Showing 21 of 21 model rows
Recent Test Records
| Time | Model | Speed | Latency |
|---|---|---|---|
| Jun 19, 03:51 AM | claude-opus-4-8 | 45.57 tok/s | 2.08s |
Similar API Provider Alternatives to Compare
Compare ClaudeAPI Relay alternatives against 6 nearby API providers using 192 LMSpeed signals across shared model coverage, pricing, benchmark speed, uptime, and free-model availability.
| Provider | Why compare | Models | Free | Avg price | Speed | 30d uptime |
|---|---|---|---|---|---|---|
| ClaudeAPI Relay console-claudeapi-com Third-party Claude-only relay (not Anthropic official) — RMB pay-as-you-go at ~80% of official Claude pricing. | Current provider baseline | 21 | 0 | $0.163/M | 46 tok/s | 9920% |
| ChooseC API ipv4-beta-lm-studio ChooseC API is a unified AI model aggregation gateway supporting 260+ mainstream models including Claude, GPT, Qwen, DeepSeek, Kimi, and GLM with OpenAI, Claude, and Gemini compatibility. |
| 335 | 9 | $0.095/M | 138 tok/s | 9950% |
| WONG公益站 wzw-pp-ua WONG公益站 is a free, community-driven OpenAI-compatible API relay. It aggregates 70+ AI models from providers like OpenAI, Anthropic, DeepSeek, xAI, Moonshot, and Zhipu AI, offering free API quotas for developers and researchers. |
| 140 | 0 | $0.013/M | 46 tok/s | 9970% |
| ChooseC API ipv4-beta-kxcym-top-3001 ChooseC API is an OpenAI-compatible relay service hosted at ipv4-beta.kxcym.top, providing access to multiple AI models through standardized endpoints. |
| 122 | 9 | $0.095/M | 51 tok/s | 0% |
| PackyAPI codex-api-packycode-com PackyAPI (codex-api.packycode.com) is an OpenAI-compatible API relay for Codex and other models via a single interface. |
| 78 | 0 | $0.041/M | 69 tok/s | 9980% |
| Elysiver API elysiver-api Elysiver API appears to provide an OpenAI-compatible API gateway at elysiver.h-e.top. The public root is protected by a Cloudflare challenge during review. |
| 78 | 0 | $0.014/M | 119 tok/s | 9940% |
| F2API api-f2api-com F2API is an enterprise AI gateway providing a unified OpenAI-compatible interface for accessing multiple large language models. |
| 1,262 | 0 | N/A | 272 tok/s | 9990% |
Announcements
Apito Announcement [Service Suspension Update Notice] Apito will undergo a version update tonight at 22:00, with an expected service suspension of 1 hour, resuming at 23:00. Please save your data in advance and pause operations during the update to avoid data loss. We apologize for any inconvenience caused. Apito Team
[Notice] ClaudeAPI.com has now been officially upgraded to apito.ai. The official documentation has been updated with the latest API Base URL, including available access addresses such as https://gw.apito.ai. Please replace your original API addresses with the new ones. API keys, account balances, and calling methods remain unchanged. The old domain will gradually be phased out. If you encounter any issues, please contact the administrator for assistance.
[claude-fable-5 Model Restoration Notice]
claude-fable-5 has been restored and is now available for normal use.
When calling the API, set the model field to:
"model": "claude-fable-5"
Claude Code users can type /model to select this model, or use the following at startup:
claude --model claude-fable-5
If you encounter call failures, model unavailability, or abnormal responses during use, please contact platform customer service or technical support for assistance.
New Model Launch Notice
The platform has launched a new model: claude-sonnet-5
Users can select this model from the model list and call it via the API.
If you encounter call failures, model unavailability, or abnormal responses during use, please contact platform customer service or technical support for assistance.
Thank you for your support. We will continue to release more high-quality models.
New version update. If you encounter any issues, please contact customer service promptly for resolution.
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.

