Codex and CodeX2 groups are unified and renamed to "Plus&Team&K12 Mixed Pool" source, with pricing uniformly set to 0.1x multiplier; CodeX-Pro group pricing is reduced and unified to 0.25x multiplier.
AutoRouter is an AI API relay service for developers, providing unified access to multiple AI models.
- Models
- 46 models
- From
- $0.090/M
- Speed
- --
- Updated
- 8/6/2026
- Latency
- --
- Created At
- 6/7/2026
- Recharge Rate
- ¥1.00 per $1 quota
Features
Login Methods
Billing
Payment methods
- Refunds
- Supported
- Invoicing
- Not supported
API Endpoints
- CF Route (VPN Required)
https://autorouter.ioOriginal main route, currently blocked and requires VPN
- Endpoint 2Historical / Unverified
https://z.autorouter.io - Relay Route
https://api.tokenfty.netAsia-Pacific relay route
- Main Route
https://autorouter.netMain route via Cloudflare
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.
Health Check
API Benchmarks & Pricing
Compare 75 model rows across audit recency, latest speed tests, throughput, latency, and per-token pricing.
codex-auto-reviewCodex2 | $0.210/M | $1.68/M |
codex-auto-reviewCodex | $0.210/M | $1.68/M |
codex-auto-reviewCodeX-Pro | $0.438/M | $3.50/M |
gemini-3.6-flash-tieredGemini特价 | $0.750/M | $3.75/M |
nano-bananaBanana | $0.190/request | - |
nano-banana-2Banana | $0.200/request | - |
nano-banana-proBanana | $0.400/request | - |
claude-opus-5满血CC | $3.50/M | $17.50/M |
claude-opus-5CC优质特价 | $3.75/M | $18.75/M |
claude-opus-5ClaudeMax | $7.00/M | $35.00/M |
gemini-3.6-flashGemini特价 | $0.750/M | $3.75/M |
kimi-k3国产模型 | $1.80/M | $9.00/M |
gpt-5.6-lunaCodex2 | $0.120/M | $0.720/M |
gpt-5.6-lunaCodex | $0.120/M | $0.720/M |
gpt-5.6-lunaCodeX-Pro | $0.250/M | $1.50/M |
gpt-5.6-terraCodex2 | $0.300/M | $1.80/M |
gpt-5.6-terraCodex | $0.300/M | $1.80/M |
gpt-5.6-terraCodeX-Pro | $0.625/M | $3.75/M |
gpt-5.6-solCodex | $0.600/M | $3.60/M |
gpt-5.6-solCodex2 | $0.600/M | $3.60/M |
gpt-5.6-solCodeX-Pro | $1.25/M | $7.50/M |
grok-4.5Grok | $0.300/M | $0.900/M |
claude-sonnet-5高缓CC_Kiro | $0.700/M | $3.50/M |
claude-sonnet-5满血CC | $1.40/M | $7.00/M |
claude-sonnet-5CC优质特价 | $1.50/M | $7.50/M |
Showing 25 of 75 model rows
Recent Test Records
Similar API Provider Alternatives to Compare
Compare AutoRouter alternatives against 6 nearby API providers using 333 LMSpeed signals across shared model coverage, pricing, benchmark speed, uptime, and free-model availability.
| Provider | Why compare | Models | Free | Avg price | Speed | 30d uptime |
|---|---|---|---|---|---|---|
| AutoRouter autorouter-io AutoRouter is an AI API relay service for developers, providing unified access to multiple AI models. | Current provider baseline | 46 | 0 | $0.315/M | N/A | 0% |
| Dext API ai-dext-top Dext API is an OpenAI-compatible API relay offering access to 500+ LLM models at competitive prices, with multi-channel routing and broad model coverage. |
| 667 | 219 | $0.017/M | 19 tok/s | 1350% |
| 小水管 API edge-pieixan-icu Pie-Xian (小水管) provides an OpenAI-compatible API relay with multiple endpoints including api.pie-xian.com and edge nodes. |
| 495 | 2 | $0.054/M | 260 tok/s | 9880% |
| 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% |
| VSLLM vsllm-com VSLLM runs a New API-powered AI gateway on vsllm.com for aggregated model access through a single endpoint. |
| 209 | 2 | $0.056/M | 174 tok/s | 9970% |
| Tokeness.io tokeness-cn Tokeness.io is an OpenAI-compatible API relay hub that connects developers to mainstream LLMs including GPT, Claude, and DeepSeek through a single endpoint. |
| 47 | 1 | $0.079/M | 62 tok/s | 9990% |
| 初叶🍂Furry API ai-chuyel-top A free, community-supported API service providing access to various AI models for developers and users. |
| 1,021 | 152 | $18.00/M | 171 tok/s | 5170% |
Announcements
[Important Notice] ChatGPT will discontinue GPT 5.2 and GPT 5.3 Codex in Codex on June 2. Please switch models promptly. These models have been removed.
New [Domestic] group added, priced at 0.6 RMB/dollar, with prices synced with official rates. Current capacity is limited; please contact the site admin in advance for high concurrency needs.
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.

