Sponsored byFusecodeEnterprise coding API for Claude Code, Codex, and model workflows.
LogoLMSpeed

小辣椒

WebsiteShare on X

yyds.215.im

A community-driven API provider offering access to models like Claude and Gemini through a unified interface.

Models
58 models
From
--
Speed
39 tok/s
Updated
6/8/2026
Latency
0.00 s
Created At
4/6/2026
Recharge Rate
¥1.00 per $1 quota

Features

DrawingTaskData ExportCheck-in

Login Methods

LinuxDOPasskey

API Endpoints

  • Endpoint 1Historical / Unverified
    https://yyds.215.im
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

Health
1.0%#31/716

Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.

About 小辣椒

小辣椒 is a community-driven API provider that offers access to various AI models via a unified interface. Key features include:

  • Primary Models: Provides endpoints for Claude and Gemini models, with a general-purpose interface for AI tasks.
  • Unified Interface: Uses a common URL (https://yyds.215.im) for multiple models, simplifying integration.
  • Community Focus: Operates as a public service with user rankings and usage statistics, emphasizing community support.
  • Use Cases: Suitable for developers and users needing AI model access for applications like chatbots, content generation, and coding assistance.
  • Status: The site has announced temporary maintenance and registration closure, with available models listed as operational. Note: No specific pricing, SLAs, or guarantees are detailed; users are advised to check current availability.

Health Check

99%Recent availability
History (72 pts)
PastNow

API Benchmarks & Pricing

Compare 27 model rows across audit recency, latest speed tests, throughput, latency, and per-token pricing.

View all 27 models
Model
Input ($/M)
Output ($/M)
Speed
Latency
claude-haiku-4-5
----
claude-opus-4-6
----
claude-sonnet-4-6
----
deepseek-v3.2:cloud
----
gemini-3-flash-preview:latest
----
gemma4:latest
----
glm-4.7
----
glm-5
----
glm-5.1:cloud
----
grok-4.20-0309
----
grok-4.20-0309-non-reasoning
----
grok-4.20-0309-reasoning
----
grok-4.20-auto
----
grok-4.20-expert
----
grok-4.20-fast
----
kimi-k2
----
mistral-large-3:675b-cloud
----
claude-opus-4-7
----
gemini-3-pro-preview
----
gpt-5.4-pro
----
minimax-k2.5
----
qwen3.5:397b-clouddefault
$0.400/M$2.00/M--
MiniMax-M2.5
--34.6 t/s7.99 s
kimi-k2.5
--41.2 t/s12.43 s
gemini-3-flash-previewdefault
$0.014/M$0.086/M--

Showing 25 of 27 model rows

Recent Test Records

TimeModelSpeedLatency
Apr 19, 07:07 AM
MiniMax-M2.5
34.56 tok/s
7.99s
Apr 6, 04:08 PM
kimi-k2.5
44.68 tok/s
11.38s
Apr 6, 04:01 PM
kimi-k2.5
37.68 tok/s
13.48s

Similar API Provider Alternatives to Compare

Compare 小辣椒 alternatives against 6 nearby API providers using 227 LMSpeed signals across shared model coverage, pricing, benchmark speed, uptime, and free-model availability.

ProviderWhy compareModelsFreeAvg priceSpeed30d uptime
小辣椒

yyds-215-im

A community-driven API provider offering access to models like Claude and Gemini through a unified interface.

Current provider baseline584N/A39 tok/s9990%
TommyLam API

new-api-tommylam-me

TommyLam API offers an OpenAI-compatible API gateway for accessing multiple AI models at competitive rates.

  • Faster measured speed
  • Higher 30-day availability
  • More free-model options
  • Broader model coverage
231100N/A61 tok/s10000%
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.

  • Faster measured speed
  • More free-model options
  • Broader model coverage
1229$0.095/M51 tok/s0%
钱多多 API

api2-aigcbest-top

Provides AI-generated content APIs for various applications, including text and image generation.

  • Faster measured speed
  • Broader model coverage
1,4182$0.0025/M101 tok/s9940%
F2API

api-f2api-com

F2API is an enterprise AI gateway providing a unified OpenAI-compatible interface for accessing multiple large language models.

  • Faster measured speed
  • Broader model coverage
1,2620N/A272 tok/s9990%
Koyeb AI Gateway

new-api-koyeb-app

An OpenAI-compatible API gateway deployed on Koyeb, providing access to multiple AI models.

  • More free-model options
  • Broader model coverage
578420N/A33 tok/s9960%
LLMService

llmservice

LLMService provides API access to large language models for self-use applications.

  • Faster measured speed
  • Broader model coverage
4490N/A139 tok/s4850%

Announcements

default4/1/2026

claude 2api is dead, and context has been limited, and switched to gemini. Waiting for further updates~

success3/30/2026

gpt died too fast. Can't keep up, forget it, I'm taking it down.

warning3/30/2026

New gpt full model set added. If it doesn't work, then it doesn't work.

ongoing3/30/2026

Did an optimization, optimized the reverse cache, not sure if it works well, hit rate is okay, will add gpt5.4 later.

default3/28/2026

Optimized, should have much lower error probability now~

default3/28/2026

Wait a moment~~ Fixing it right away.

ongoing3/27/2026

Updated claude-opus-4.6, available for use~

default3/11/2026

claude-sonnet-4.6 reverse is now available, everyone go ahead and use it~

default3/10/2026

Recently not much maintenance, some tools are broken, if you can avoid ldc, don't use it~

default3/10/2026

Please use: gpt-5.2-codex

success2/26/2026

Open registration: grok / openai / kiro. Registration gets banned instantly, no good solution, if you don't believe it, try it. Of course, occasionally some work, depends on luck.

default2/20/2026

Registration tool is still being fixed~ Will announce when it's ready~

warning2/17/2026

This claude channel is too garbage, I feel like cursing while using it/ If you don't want to use it, switch to other models!!!

default2/13/2026

Google the great benefactor has also distanced itself from me, my heart feels cold.

default2/12/2026

claude opus is temporarily taken down. Sorry.

default2/12/2026

Using anti-gravity, not very stable, opus channel is still under research, everyone use others for now.

ongoing2/12/2026

Holy crap, the sky has fallen brothers, all 8 kiro accounts are banned.

success2/8/2026

Oh my, after two days, the merge is finally complete. Currently all models are available. One aws, one anti-gravity. Available for daily use~

FAQ

What does error 502 (Bad Gateway) mean?

Error: status_code=502 (Bad Gateway) Meaning: The gateway/proxy server received an invalid response from the upstream server (e.g., model API service). Suggestion: First, try opening a new session window. If the issue persists, troubleshoot based on the above points.

What does error status_code=500 indicate?

Meaning: An internal server error occurred, or the request method is not recognized. A 'not implemented' hint usually indicates a protocol or interface mismatch. Common causes and troubleshooting steps: Model protocol or interface mismatch: This is the most likely cause. Strictly check your interface configuration (e.g., API endpoint, request headers, parameter format) to ensure it fully matches the latest official documentation for the target model (GPT-5.3-Codex or Claude Opus 4.6). For example, configuring a GPT API endpoint for Claude 4.6 will cause this error. Suggestion: Focus on checking configuration files to ensure model names, API base addresses, and other key configurations are accurate and clean, without residual invalid configuration items from old models.

What are the general configuration and testing reminders?

Configuration consistency check: Ensure that the model name, API key, and endpoint specified in your configuration file exactly match the gpt5.3 or Claude4.6 service you are actually calling. A single configuration error can cause the entire call to fail. Make full use of the playground: The system has successfully launched support for GPT-5.3-Codex and Claude Opus 4.6 models. Strongly recommend testing the connectivity and basic functions of these two models separately in the platform's playground feature to confirm the API channel is normal. Note context length: Claude Opus 4.6 supports up to 1 million token context window, and GPT-5.3-Codex also supports long context. If requests still error, check if the sent context is too large or the generated token count exceeds your account's or current configuration's rate limits.

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.