UNIFIED AI INFRASTRUCTURE/ONE UNIFIED API

Every AI model. One API.

Access leading AI models through one unified API. Manage usage, control spending, and integrate once — without juggling multiple provider integrations.

Explore 34 models
gateway.toknix.com/v1/chat/completions
Provider Route
Claude
Upstream Host
api.anthropic.com/v1
Simulated TTFT
128ms
Cost Est.
$0.00010
curl https://api.toknix.com/v1/chat/completions \
  -H "Authorization: Bearer tk_live_948f2c01e..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-5-5",
    "messages": [
      {"role": "user", "content": "Explain Toknix gateway routing."}
    ],
    "stream": true
  }'
STREAMED OUTPUT
HTTP 200 OK

// Ready to execute. Click "Test" to simulate a live request through Toknix.

Gateway handles transparent auth, token metering, SSE streaming, and upstream failover.

TOKENS: 48 TOKMETRIC: 86 tok/sPASS-THROUGH BILLING
Unified standard: OpenAI-compatible schema across 34 foundation modelsRequest API key →
ECOSYSTEM

Multi-Provider Gateway

Direct connectivity to Anthropic, OpenAI, Google, DeepSeek, xAI, Moonshot & Zhipu AI.

PROTOCOL

Unified Standard API

Familiar OpenAI-compatible format. Switch models by changing a single parameter.

ECONOMICS

Prepaid Wallet Billing

Pay purely for consumed tokens. No recurring seats or forced monthly subscriptions.

PIPELINE

Low-Latency SSE Streaming

Native Server-Sent Events with transparent usage headers and sub-millisecond edge routing.

Model Catalog & Pricing

One endpoint. 40 foundation models.

Pay strictly per token from a prepaid USD balance. No recurring subscriptions. Top-ups start at just $5.

34MODELS
7PROVIDERS
$5MIN TOP-UP
Gemini 4 CarbonGemini

gemini-4-carbon

Context:1.05MMax Out: 16K
In / Out:$1.00 / $1.00per 1M tokens
Cached:$0.10up to 90% savings
Gemini ArgonGemini

gemini-4-argon

Context:128KMax Out: 16K
In / Out:$0.60 / $0.60per 1M tokens
Cached:$0.10up to 90% savings
AstraGPT

gpt-6-astra

Context:1.05MMax Out: 128K
In / Out:$1.30 / $1.30per 1M tokens
Cached:$0.12up to 90% savings
Astra 6.2GPT

gpt-6.2-astra

Context:1.05MMax Out: 128K
In / Out:$1.30 / $1.30per 1M tokens
Cached:$0.12up to 90% savings
6.1 SolGPT

gpt-6.1-sol

Context:1.05MMax Out: 128K
In / Out:$0.30 / $0.30per 1M tokens
Cached:$0.08up to 90% savings
6.2 SolGPT

gpt-6.2-sol

Context:1.05MMax Out: 128K
In / Out:$0.30 / $0.30per 1M tokens
Cached:$0.08up to 90% savings
GPT-6 SolGPT

gpt-6-sol

Context:1.05MMax Out: 128K
In / Out:$0.30 / $0.30per 1M tokens
Cached:$0.08up to 90% savings
GPT-6 LunaGPT

gpt-6-luna

Context:1.05MMax Out: 128K
In / Out:$0.10 / $0.10per 1M tokens
Cached:$0.02up to 90% savings
GPT-5.6 SolGPT

gpt-5.6-sol

Context:1MMax Out: 128K
In / Out:$0.90 / $0.90per 1M tokens
Cached:$0.08up to 90% savings
GPT-5.6 TerraGPT

gpt-5.6-terra

Context:1MMax Out: 128K
In / Out:$0.90 / $0.90per 1M tokens
Cached:$0.08up to 90% savings
GPT-5.6 LunaGPT

gpt-5.6-luna

Context:1MMax Out: 128K
In / Out:$0.90 / $0.90per 1M tokens
Cached:$0.08up to 90% savings
GPT-5.5GPT

gpt-5.5

Context:1MMax Out: 128K
In / Out:$0.90 / $0.90per 1M tokens
Cached:$0.08up to 90% savings
Fable 5.2Claude

claude-fable-5-2

Context:1MMax Out: 64K
In / Out:$1.60 / $1.60per 1M tokens
Cached:$0.16up to 90% savings
Opus 5.5 MaxClaude

claude-opus-5-5-max

Context:1MMax Out: 128K
In / Out:$1.40 / $1.40per 1M tokens
Cached:$0.14up to 90% savings
Opus 5.5Claude

claude-opus-5-5

Context:1MMax Out: 128K
In / Out:$1.40 / $1.40per 1M tokens
Cached:$0.14up to 90% savings
Opus 5Claude

claude-opus-5

Context:1MMax Out: 64K
In / Out:$1.00 / $1.00per 1M tokens
Cached:$0.10up to 90% savings
Opus 4.8Claude

claude-opus-4-8

Context:1MMax Out: 64K
In / Out:$1.00 / $1.00per 1M tokens
Cached:$0.10up to 90% savings
Opus 4.7Claude

claude-opus-4-7

Context:1MMax Out: 64K
In / Out:$1.00 / $1.00per 1M tokens
Cached:$0.10up to 90% savings
Opus 4.6Claude

claude-opus-4-6

Context:1MMax Out: 64K
In / Out:$1.00 / $1.00per 1M tokens
Cached:$0.10up to 90% savings
Sonnet 5.5Claude

claude-sonnet-5-5

Context:1MMax Out: 64K
In / Out:$1.00 / $1.00per 1M tokens
Cached:$0.12up to 90% savings
Sonnet 5Claude

claude-sonnet-5

Context:1MMax Out: 64K
In / Out:$1.00 / $1.00per 1M tokens
Cached:$0.10up to 90% savings
Haiku 5.5Claude

claude-haiku-5-5

Context:1MMax Out: 64K
In / Out:$0.06 / $0.06per 1M tokens
Cached:$0.02up to 90% savings
Grok 4.7Grok

grok-4.7

Context:500KMax Out: 66K
In / Out:$0.20 / $0.20per 1M tokens
Cached:$0.04up to 90% savings
Grok 4.6Grok

grok-4.6

Context:500KMax Out: 66K
In / Out:$0.20 / $0.20per 1M tokens
Cached:$0.04up to 90% savings
Grok 4.5Grok

grok-4.5

Context:200KMax Out: 64K
In / Out:$0.20 / $0.20per 1M tokens
Cached:$0.04up to 90% savings
DeepSeek V4.1 FlashDeepSeek

deepseek-v4.1-flash

Context:1MMax Out: 66K
In / Out:$0.04 / $0.04per 1M tokens
Cached:$0.010up to 90% savings
DeepSeek Flash 1017DeepSeek

deepseek-v4.1-flash-1017

Context:1MMax Out: 66K
In / Out:$0.04 / $0.04per 1M tokens
Cached:$0.010up to 90% savings
DeepSeek Flash 1017 HQDeepSeek

deepseek-v4.1-flash-1017-hq

Context:1MMax Out: 66K
In / Out:$0.10 / $0.10per 1M tokens
Cached:$0.02up to 90% savings
DeepSeek Flash 1017 AbliteratedDeepSeekUncensored

deepseek-v4.1-flash-1017-abliterated

Context:1MMax Out: 66K
In / Out:$0.30 / $0.30per 1M tokens
Cached:$0.10up to 90% savings
DeepSeek Abliterated FastDeepSeekUncensored

deepseek-v4.1-flash-1017-abliterated-fast

Context:1MMax Out: 66K
In / Out:$1.40 / $1.40per 1M tokens
Cached:$0.32up to 90% savings
DeepSeek V4 FlashDeepSeek

deepseek-v4-flash-0731

Context:1MMax Out: 66K
In / Out:$0.06 / $0.06per 1M tokens
Cached:$0.0054up to 90% savings
DeepSeek V4 ProDeepSeek

deepseek-v4-pro-0813

Context:1MMax Out: 66K
In / Out:$0.50 / $0.50per 1M tokens
Cached:$0.10up to 90% savings
GLM 5.2GLM

glm-5.2

Context:1MMax Out: 66K
In / Out:$0.12 / $0.12per 1M tokens
Cached:$0.034up to 90% savings
GLM 5.3GLM

glm-5.3

Context:1MMax Out: 66K
In / Out:$0.10 / $0.10per 1M tokens
Cached:$0.02up to 90% savings
GLM 5.3 UncensoredGLMUncensored

glm-5.3-uncensored

Context:1MMax Out: 66K
In / Out:$0.10 / $0.10per 1M tokens
Cached:$0.02up to 90% savings
GLM 5.3 FlashGLM

glm-5.3-flash

Context:1MMax Out: 66K
In / Out:$0.05 / $0.05per 1M tokens
Cached:$0.005up to 90% savings
GLM 5.3 Flash UncensoredGLMUncensored

glm-5.3-flash-uncensored

Context:1MMax Out: 66K
In / Out:$0.05 / $0.05per 1M tokens
Cached:$0.005up to 90% savings
GLM 5.3 AbliteratedGLMUncensored

glm-5.3-abliterated

Context:1MMax Out: 130K
In / Out:$1.60 / $1.60per 1M tokens
Cached:$0.50up to 90% savings
Kimi K3Kimi

kimi-k3

Context:1MMax Out: 66K
In / Out:$0.30 / $0.30per 1M tokens
Cached:$0.06up to 90% savings
Kimi K3.1 ProKimi

kimi-k3.1-pro

Context:1MMax Out: 32K
In / Out:$0.60 / $0.60per 1M tokens
Cached:$0.10up to 90% savings
Billing policy: Pay per token from a prepaid USD balance. No subscription commitments. Top-ups start at $5.
Architecture & Gateway

Integrate once. Switch models when you need to.

Eliminate vendor lock-in and brittle custom adapters. Toknix normalizes request schemas, authentication headers, error payloads, and token consumption across all major AI labs.

Toknix Gateway Pipeline
ACTIVE_ROUTING
01
Client App (Your Service)
Standard OpenAI SDK or simple HTTP client
1 API Key
↓ api.toknix.com/v1
02
Toknix Unified Edge Router
• Real-time token metering & wallet balance enforcement
• Automatic upstream failover & smart retries
• Uniform error code normalization
↓ Zero Client Configuration
03
Upstream Labs
7+ Providers Integrated
Anthropic
OpenAI
Google
DeepSeek
Dynamic Fallbacks

Define fallback models if an upstream provider experiences a temporary outage.

Zero-Data Retention

Payloads pass directly through in-memory proxy pipes without database storage.

CODE DEMONSTRATION
// One clean client instance. Swap models effortlessly by passing any model ID:
import OpenAI from "openai";

const toknix = new OpenAI({
  apiKey: process.env.TOKNIX_API_KEY,
  baseURL: "https://api.toknix.com/v1",
});

// 1. Run Claude 3.5 Sonnet
const sonnet = await toknix.chat.completions.create({
  model: "anthropic/claude-3-5-sonnet",
  messages: [{ role: "user", content: "Optimize this SQL query..." }],
  stream: true,
});

// 2. Or DeepSeek V3 with ZERO SDK or auth modifications
const deepseek = await toknix.chat.completions.create({
  model: "deepseek/deepseek-v3",
  messages: [{ role: "user", content: "Write a rust CLI parser..." }],
  stream: true,
});

// 3. Or Google Gemini 1.5 Pro with 2M context
const gemini = await toknix.chat.completions.create({
  model: "google/gemini-1.5-pro",
  messages: [{ role: "user", content: "Analyze these 50 code files..." }],
});
Drop-in compatible with standard OpenAI SDKszero code refactoring
Prepaid Economy & Control

Your usage. Your budget.

Eliminate unexpected billing surprises. Prepay your balance, execute requests across any model, and pay strictly for raw token consumption with real-time auditability.

Top-ups from $5

Top up starting at just $5 via card, wire, or crypto. No credit card overdrafts or surprise monthly invoices.

Microsecond Metering

Every prompt, completion, and cached token is logged down to fractions of a cent as it streams.

Per-Key Spend Limits

Set hard spending limits for staging, production, or individual team members.

Zero Lock-In

Funds never expire. Spend credits freely across all 34 foundation models in our catalog.

CONSOLE PREVIEW // WORKSPACE: productionACTIVE WORKSPACE
Available Balance
$248.50
Autoload: ActiveMin Top-up: $5.00
Monthly Spend Cap$500.00
Spent: $248.50Cap: 49.7%
Recent Telemetry & Logs
Live Stream [200 OK]
IDModelTokensLatencyCostStatus
req_99812claude-sonnet-5-52,410 tok128ms$0.0024200
req_99811deepseek-v4.1-flash4,820 tok135ms$0.00019200
req_99810gpt-6-astra1,150 tok115ms$0.0014200
req_99809gemini-4-carbon12,800 tok122ms$0.0012200
Illustrative developer preview. Pay per token from prepaid USD balance. Top-ups start at $5.
Developer Experience

Built for the way developers work.

Engineered from first principles for performance, reliability, and minimal friction. Integrate with familiar idioms, standard tooling, and zero runtime surprises.

100% standard OpenAI API compatibility
API SPECIFICATION
// Change exactly TWO lines in your codebase:
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.TOKNIX_API_KEY,    // [1] Use Toknix Key
  baseURL: "https://api.toknix.com/v1", // [2] Unified Gateway
});
Latency overhead: < 4ms global p95Strict TypeScript types provided
Transparent Pricing

Pay for what you use.

You pay per token from a prepaid USD balance. There's no subscription. Top-ups start at $5. Unused balance never expires.

How Billing Works

1
Prepaid USD Balance
Add funds to your account starting at $5. Top up via credit card, ACH wire, or crypto.
2
Pay Per Raw Token
No monthly tier restrictions. Every token is metered down to microcents according to the public rate.
3
Cached Token Savings
Re-read prompts and documents automatically bill at up to 90% discount (as low as $0.0025/1M).
Toknix Commitments:
  • • Top-ups start at $5
  • • Zero monthly minimum fees
  • • No subscription lock-in
  • • Unused balance never expires
  • • Per-key hard spend limits
SIMULATED TOP-UP AMOUNTS:INSTANT CREDIT
Interactive Cost Calculator
REAL PASS-THROUGH RATES
PROJECTED MONTHLY VOLUME:10 Million Tokens
1M Tokens25M Tokens50M Tokens100M Tokens
ESTIMATED PROMPT CACHING RATIO:40% Cached
0% (No Caching)40% (Typical Agentic Flow)80% (Heavy System Prompt / Long Context)
Estimated Monthly Balance Burn
$7.54USD
Prompt Cache Savings
+$2.46 saved
INPUT RATE$1.00 / 1M
OUTPUT RATE$1.00 / 1M
CACHED RATE$0.12 / 1M
PRODUCTION READY GATEWAY

Your next AI integration starts here.

One API. Multiple models. A simpler way to build. Integrate once and run with the world's leading foundation models.

$curl -sSL https://api.toknix.com/v1/health
Returns JSON status, active model catalog, and ping latency