gateway · liveOpenAI-compatible · 400+ models

Every model.One bill.85% less.

Drop in the OpenAI SDK base URL. Get instant access to GPT-5.5 Pro, Claude-Opus-4.7, Gemini 3.1, Veo 3.1, Kling 3, Mistral and 400 more — at a fraction of list price. We pass through upstream cost; you keep the savings.

no subscriptionno markup mathcrypto top-ups
85% off
launch pricing
$15$100

of pure AI compute. No subscription. No expiry.

  • Pass-through cost — we charge exactly what the upstream charges us. Zero markup, Zero Hidden multipliers.
  • Bulk buying power — our $15 funds $100 of upstream credit.
  • Itemized usage — see exact tokens & USD per request.
Claim my $100 of credit
01 · capabilities

Everything AI can do — one endpoint.

Tap any tile to see the top models for each capability. Swap the model string — keep your code, prompts, tools.

01

Chat & reasoning

Frontier chat with function-calling, tool use, structured output.

120+ chat models
hover to see top picks
02

Vision

Images, PDFs, screenshots → structured understanding.

20+ vision models
hover to see top picks
03

Image generation

Concept art, product mocks, brand assets. One endpoint.

8 image models
hover to see top picks
04

Speech → text

Diarization, timestamps, 99+ languages. Realtime or batch.

4 transcription models
hover to see top picks
05

Text → speech

Natural voices in 30+ languages. Stream or batch hours of audio.

3 voice + 2 music
hover to see top picks
06

Video

Generate, extend, image-to-video. Sora-class quality.

20+ video models
hover to see top picks
07

Realtime voice

Sub-300ms voice agents. Two-way audio with function calling.

Live audio stack
hover to see top picks
08

Web search & enrichment

Live grounding, structured extraction, real-time facts.

Sonar + 10 enrichers
hover to see top picks
02 · catalog

300+ models.
Zero contracts.

Frontier, fast, open-weight, specialty — switch by changing one string.

claude-opus-4.7Anthropic
gpt-5.5-proOpenAI
gpt-5.5OpenAI
grok-4.20xAI
gemini-3-pro-previewGoogle
deepseek-v4-proDeepSeek
qwen3-maxAlibaba
mistral-large-3Mistral
claude-sonnet-4.6Anthropic
claude-haiku-4.5Anthropic
gpt-5.4-miniOpenAI
gpt-5.4-nanoOpenAI
gemini-3-flashGoogle
mistral-medium-3.5Mistral
deepseek-v4-flashDeepSeek
kimi-k2.6Moonshot
llama-4-maverickMeta
llama-4-scoutMeta
claude-opus-4.7Anthropic
gpt-5.5-proOpenAI
gpt-5.5OpenAI
grok-4.20xAI
gemini-3-pro-previewGoogle
deepseek-v4-proDeepSeek
qwen3-maxAlibaba
mistral-large-3Mistral
claude-sonnet-4.6Anthropic
claude-haiku-4.5Anthropic
gpt-5.4-miniOpenAI
gpt-5.4-nanoOpenAI
gemini-3-flashGoogle
mistral-medium-3.5Mistral
deepseek-v4-flashDeepSeek
kimi-k2.6Moonshot
llama-4-maverickMeta
llama-4-scoutMeta
hermes-4-405bNous
qwen3-next-80bAlibaba
gpt-oss-120bOpenAI
phi-4Microsoft
o4-mini-highOpenAI
gpt-5.3-codexOpenAI
qwen3-vl-235bAlibaba
flux-2-proBlack Forest
gpt-image-1.5OpenAI
nano-banana-proGoogle
veo-3.1-qualityGoogle
kling-3.0Kuaishou
runway-gen-4-turboRunway
seedance-2.0ByteDance
elevenlabs-v3ElevenLabs
deepgram-nova-3Deepgram
sonar-reasoning-proPerplexity
hermes-4-405bNous
qwen3-next-80bAlibaba
gpt-oss-120bOpenAI
phi-4Microsoft
o4-mini-highOpenAI
gpt-5.3-codexOpenAI
qwen3-vl-235bAlibaba
flux-2-proBlack Forest
gpt-image-1.5OpenAI
nano-banana-proGoogle
veo-3.1-qualityGoogle
kling-3.0Kuaishou
runway-gen-4-turboRunway
seedance-2.0ByteDance
elevenlabs-v3ElevenLabs
deepgram-nova-3Deepgram
sonar-reasoning-proPerplexity
frontierfastopen-weightspecialty
03 · the math

You pay $15.
You get $100 of compute.

Our buying power becomes your pricing edge. Then every request bills at the upstream's actual cost — no markup, no padded tokens.

minimum top-up
you pay0
you receive0
save$85/ top-up
Top up now →
the mechanics

How $15 becomes $100.

01

You buy $100 of credit

Pay $15 in crypto or via redeem code. We seed your wallet with $100 of upstream credit immediately.

02

Every call bills at upstream cost

A chat request that costs us $0.0042 bills your wallet for $0.0042. Itemized in USD + tokens, no rounding tricks.

03

No expiry, no minimums after

Credit doesn't disappear. Re-top whenever — same 85%-off ratio applies.

launch pricing · while supplies last ·first 1,000 wallets

04 · drop-in

Three lines.
That's the migration.

Change the base URL. Change the API key. Swap the model name to anything in the catalog. Your code, your prompts, your tools — unchanged.

  • 100% schema-compatible with the OpenAI SDK
  • Streaming, function-calling, structured output
  • Vision, audio, image — same endpoint shape
  • Auto-retries, fallback models, request IDs
from openai import OpenAI

client = OpenAI(
    base_url="https://api.echotokens.com/v1",
    api_key="sk-echo-...",
)

response = client.chat.completions.create(
    model="claude-opus-4.7",
    messages=[{"role": "user", "content": "Hello, world."}],
)
05 · integrations

Already in your
favorite tool.

Anywhere the OpenAI SDK runs, echotokens runs. Paste your key, change the base URL — works in seconds across editors, agents, desktop apps, and self-hosted UIs.

Cursor

AI-first code editor

code editor

Claude Code

Anthropic's CLI agent

code editor

OpenCode

Open-source coding agent

code editor

Cline

Autonomous VS Code agent

autonomous agent

Roo

Multi-mode AI dev assistant

autonomous agent

Kilo Code

Open-source code agent

autonomous agent

Aider

AI pair programmer in your terminal

autonomous agent

Goose

On-machine AI agent

autonomous agent

OpenClaw

Multi-model orchestrator

autonomous agent

Claude Desktop

Native Anthropic client

desktop app

OpenWebUI

Self-hosted ChatGPT alternative

chat ui

JanitorAI

Roleplay & companion bots

chat ui

Hermes

Personal AI dashboard

chat ui

Shakespeare

Long-form writing studio

chat ui

RxResume

AI-powered resumes

chat ui
06 · built-in

Engineered for production.
Priced like a deal.

Streaming. Fallback. Caching. Schemas. Spend limits. Webhooks. The infrastructure you'd build yourself — already built.

Real-time streaming

Server-Sent Events from every chat model. First-token p50 under 400ms.

Smart fallback

Upstream rate-limited? We retry on a sibling model. You set the priority list.

Prompt caching

Anthropic & OpenAI cache discounts honored. Repeated context bills at the discounted rate.

Structured output

JSON-schema mode and function-calling on every model that supports it — uniform error shape.

Spending limits

Cap a key at $5/day or $50/month. Hard ceilings, soft warnings, rolling windows.

Itemized usage

Every request: input + output tokens, USD cost, latency, status, request ID — exportable as CSV.

Webhooks

Long-running video and image jobs ping your endpoint when ready. No polling.

IP allowlisting

Lock keys to specific CIDR ranges. Per-key, per-environment, zero downtime to update.

Bring your own data

Self-host the dashboard on Firebase + your own Firestore. The portal is open-source.

$15 unlocks $100

Ship in five minutes.

Sign up, drop in a key, point your SDK. The next hundred dollars of compute is on us — at fifteen.

© 2026 echotokens