LogoLMSpeed

iTokens

WebsiteShare on X

api.itokens.io

API RelaysFree API AccessInference Clouds

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.

New-user credit: $5.00

New users receive $5.00 in account credit after signup. Check the provider's current terms before registering.

Models
12 models
From
$0.112/M
Speed
149 tok/s
Updated
8/18/2026
Latency
0.00 s
Created At
7/28/2026

Billing

Payment methods

Stripe

Billing types

Usage-based
Refunds
Not supported
Invoicing
Supported

API Endpoints

  • Endpoint 1
    api.itokens.io
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

Contact

Leaderboard Rankings

Health
1.0%#232/717

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

About iTokens

iTokens overview

iTokens provides a unified, OpenAI-compatible API for accessing a curated catalog of language and coding models through one account and API key.

API and model access

  • API base URL: https://api.itokens.io/v1
  • Compatibility: OpenAI-compatible requests and SDK workflows
  • Model catalog: Models from DeepSeek, GLM, Kimi, Qwen, MiniMax, KwaiKAT, and other developers
  • Getting started: Register, create an API key, select a model, and send requests to the unified endpoint

Pricing and billing

The service uses usage-based billing. Its public price list is denominated in USD per million tokens and separately shows input, output, and cache-hit prices where applicable. The website currently advertises a standard 20% platform discount, additional time-limited discounts for selected models, and 200 promotional credits for new registrations without requiring a credit card. Promotions and model prices may change.

Invoice details and downloadable invoices are available through the account area. Before production use, verify the current model catalog, pricing, discount schedule, context limits, and service terms on the iTokens website and documentation.

Health Check

100%Recent availability
History (72 pts)
PastNow

API Benchmarks & Pricing

Compare 12 model rows across audit recency, latest speed tests, throughput, latency, and per-token pricing.

Model
Input ($/M)
Output ($/M)
Model availability
Speed
Latency
Hidden prompt
Prompt leak
Real model
Jailbreak leak
Real context
Tool rewrite
Error leak
Streaming output
Wallet safety
Latency swing
deepseek/deepseek-v4-pro-0813
--
1%
--
z-ai/glm-5.3
--
1%
--
deepseek/deepseek-v4-flash-0731default
$0.112/M$0.224/M
1%
74.1 t/s2.70 s
z-ai/glm-5.2default
$1.12/M$3.52/M
1%
102.6 t/s18.18 s
deepseek/deepseek-v4-prodefault
$1.39/M$2.78/M
1%
81.5 t/s10.17 s
deepseek/deepseek-v4-flashdefault
$0.112/M$0.224/M
1%
56.0 t/s6.10 s
moonshot/kimi-k2.6default
$0.760/M$3.20/M
1%
119.6 t/s19.53 s
z-ai/glm-5.1default
$1.12/M$3.52/M
1%
97.8 t/s17.08 s
qwen/qwen3.5-397b-a17bdefault
$0.480/M$2.88/M
1%
366.2 t/s9.72 s
minimax/minimax-m2.5default
$0.240/M$0.960/M
1%
170.6 t/s4.55 s
z-ai/glm-5default
$0.800/M$2.56/M
1%
139.0 t/s13.57 s
streamlake/kat-coder-pro-v2default
$0.240/M$0.960/M
0%
113.9 t/s0.89 s

Showing 12 of 12 model rows

Free resources

Community-shared API keys and redeem codes associated with iTokens.

Free redeem codes

2
View all
Redeem codeRedeem value / Remaining / totalRedemption requirementsShared by / date
rN***zc$5.00· 99931/99999New users only · Minimum spend requiredNexmoe· Aug 11, 2026
ht***qD$40.00· 49977/50000New users only · Invitation or referral requiredolegjeje228-bot· Aug 11, 2026

Recent Test Records

TimeModelSpeedLatency
Aug 11, 12:03 PM
deepseek/deepseek-v4-flash
56.03 tok/s
6.10s
Aug 11, 12:03 PM
deepseek/deepseek-v4-flash-0731
73.14 tok/s
2.95s
Aug 11, 12:03 PM
deepseek/deepseek-v4-pro
94.25 tok/s
10.30s
Aug 11, 12:03 PM
minimax/minimax-m2.5
214.53 tok/s
5.79s
Aug 11, 12:03 PM
moonshot/kimi-k2.6
90.47 tok/s
18.52s
Aug 11, 12:03 PM
qwen/qwen3.5-397b-a17b
312.91 tok/s
10.37s
Aug 11, 12:03 PM
streamlake/kat-coder-pro-v2
112.09 tok/s
0.98s
Aug 11, 12:03 PM
z-ai/glm-5
149.97 tok/s
14.86s
Aug 11, 12:03 PM
z-ai/glm-5.1
94.29 tok/s
14.13s
Aug 11, 12:03 PM
z-ai/glm-5.2
83.42 tok/s
20.83s

Similar API Provider Alternatives to Compare

Compare iTokens alternatives against 6 nearby API providers using 126 LMSpeed signals across shared model coverage, pricing, benchmark speed, uptime, and free-model availability.

ProviderWhy compareModelsFreeAvg priceSpeed30d uptime
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.

Current provider baseline120$0.168/M149 tok/s9940%
钠 API

naapi-cc

Na API (naapi.cc) is an OpenAI-compatible LLM API gateway with competitive pricing and stable access to 100+ models from OpenAI, Anthropic, Google, and more.

  • Lower average pricing
  • Faster measured speed
  • Higher 30-day availability
  • More free-model options
  • Broader model coverage
  • Same provider category
1,0862$0.082/M649 tok/s9950%
速创API

suchuang

Suchuang API provides access to various AI models including text generation, image creation, and video generation through a unified API.

  • Lower average pricing
  • Higher 30-day availability
  • Broader model coverage
  • Same provider category
5210$0.020/M74 tok/s9960%
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.

  • Lower average pricing
  • Higher 30-day availability
  • Broader model coverage
  • Same provider category
3570$0.053/M138 tok/s9960%
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.

  • Lower average pricing
  • Higher 30-day availability
  • Broader model coverage
  • Same provider category
1550$0.0055/M46 tok/s9990%
10dian-API

api-10dian-ai-top

A multi-model aggregation platform providing unified, stable, and high-performance AI API services for developers.

  • Lower average pricing
  • More free-model options
  • Broader model coverage
  • Same provider category
1519$0.000003/M130 tok/s0%
玄黄

apis-soys-site

Xuanhuang provides an API relay for accessing AI models including GPT, Claude, and open-source LLMs.

  • Faster measured speed
  • Higher 30-day availability
  • Broader model coverage
  • Same provider category
660$1.88/M429 tok/s9980%

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.