SaaS

One API for hundreds of LLMs

A unified proxy to OpenAI, Anthropic, Google, and hundreds of other LLM providers. Minimal latency, zero markup on model costs, and a single API key for everything.

Get Started

Unified API

One endpoint, one API key, hundreds of models. Switch between OpenAI, Anthropic, Google, Mistral, and others without changing your code.

◆OpenAI
◇Anthropic
▲Google
●Mistral
⬡
Flutch Gateway
One endpoint
POST /v1/chat
Your App

Minimal Latency

Optimized routing and connection pooling ensure requests reach LLM providers with minimal overhead. Sub-millisecond proxy latency.

LLM Latency

4.35s

Agent Latency

13.4s

Error Rate

0.8%
Last 24 hours

Zero Markup

Pay only what the model providers charge. No hidden fees, no per-token markup. Transparent pass-through pricing.

Cost Breakdown

This Week:$136.00
$24.50
Dec 1
$28.20
Dec 2
$26.80
Dec 3
$31.40
Dec 4
$25.10
Dec 5
Avg cost per call:$1.13
Total agent calls:120
Most used model:Claude Sonnet 4.5

Automatic Fallbacks

Configure fallback chains across providers. If one model is down or rate-limited, requests automatically route to your backup.

Fallback Chain

Active
1
GPT-4.1
OpenAI
Primary
~1.2s
if unavailable
2
Claude Sonnet 4
Anthropic
Standby
~1.4s
if unavailable
3
Gemini 2.5 Pro
Google
Standby
~0.9s
Zero downtime — automatic model switching

Available LLM models

Current prices for tokens of popular language models

+
ProviderModelRequestResponse
anthropicclaude-haiku-4-5-20251001$5 per 1M tokens$1 per 1M tokens
claude-opus-4-1-20250805$75 per 1M tokens$15 per 1M tokens
claude-opus-4-5-20251101$25 per 1M tokens$5 per 1M tokens
claude-opus-4-6$25 per 1M tokens$5 per 1M tokens
claude-opus-5$25 per 1M tokens$5 per 1M tokens
claude-sonnet-4-5-20250929$15 per 1M tokens$3 per 1M tokens
claude-sonnet-4-6$15 per 1M tokens$3 per 1M tokens
claude-sonnet-4-20250514$15 per 1M tokens$3 per 1M tokens
claude-sonnet-5$15 per 1M tokens$3 per 1M tokens
coherererank-english-v3.0$0 per 1M tokens$0 per 1M tokens
rerank-multilingual-v3.0$0.002 per 1M tokens$0.002 per 1M tokens
mistralcodestral-embed-2505$0 per 1M tokens$0.15 per 1M tokens
codestral-latest$0.9 per 1M tokens$0.3 per 1M tokens
devstral-medium-2507$2 per 1M tokens$0.4 per 1M tokens
devstral-medium-latest$2 per 1M tokens$0.4 per 1M tokens
devstral-small-2505$0.3 per 1M tokens$0.1 per 1M tokens
devstral-small-2507$0.3 per 1M tokens$0.1 per 1M tokens
magistral-medium-latest$5 per 1M tokens$2 per 1M tokens
magistral-small-latest$1.5 per 1M tokens$0.5 per 1M tokens
ministral-3b-latest$0.04 per 1M tokens$0.04 per 1M tokens
ministral-8b-latest$0.1 per 1M tokens$0.1 per 1M tokens
mistral-embed$0 per 1M tokens$0.1 per 1M tokens
mistral-large-latest$6 per 1M tokens$2 per 1M tokens
mistral-medium-latest$2 per 1M tokens$0.4 per 1M tokens
mistral-moderation-latest$0 per 1M tokens$0.1 per 1M tokens
mistral-saba-latest$0.6 per 1M tokens$0.2 per 1M tokens
mistral-small-latest$0.3 per 1M tokens$0.1 per 1M tokens
open-mistral-7b$0.25 per 1M tokens$0.25 per 1M tokens
open-mixtral-8x7b$0.7 per 1M tokens$0.7 per 1M tokens
open-mixtral-8x22b$6 per 1M tokens$2 per 1M tokens
pixtral-12b$0.15 per 1M tokens$0.15 per 1M tokens
pixtral-large-latest$6 per 1M tokens$2 per 1M tokens
voxtral-mini-2507$0.04 per 1M tokens$0.04 per 1M tokens
voxtral-small-2507$0.3 per 1M tokens$0.1 per 1M tokens
openaibabbage-002$0.6 per 1M tokens$0.15 per 1M tokens
chatgpt-4o-latest$15 per 1M tokens$5 per 1M tokens
codex-mini-latest$6 per 1M tokens$1.5 per 1M tokens
computer-use-preview-2025-03-11$12 per 1M tokens$3 per 1M tokens
davinci-002$2 per 1M tokens$2 per 1M tokens
gpt-3.5-turbo-0125$1.5 per 1M tokens$0.5 per 1M tokens
gpt-3.5-turbo-instruct$2 per 1M tokens$1.5 per 1M tokens
gpt-4-turbo-2024-04-09$30 per 1M tokens$10 per 1M tokens
gpt-4.1$8 per 1M tokens$2 per 1M tokens
gpt-4.1-2025-04-14$8 per 1M tokens$2 per 1M tokens
gpt-4.1-mini$1.6 per 1M tokens$0.4 per 1M tokens
gpt-4.1-mini-2025-04-14$1.6 per 1M tokens$0.4 per 1M tokens
gpt-4.1-nano$0.4 per 1M tokens$0.1 per 1M tokens
gpt-4.1-nano-2025-04-14$0.4 per 1M tokens$0.1 per 1M tokens
gpt-4.5-preview-2025-02-27$150 per 1M tokens$75 per 1M tokens
gpt-4o$10 per 1M tokens$2.5 per 1M tokens
gpt-4o-2024-08-06$10 per 1M tokens$2.5 per 1M tokens
gpt-4o-audio-preview-2024-12-17$10 per 1M tokens$2.5 per 1M tokens
gpt-4o-mini-2024-07-18$0.6 per 1M tokens$0.15 per 1M tokens
gpt-4o-mini-audio-preview-2024-12-17$0.6 per 1M tokens$0.15 per 1M tokens
gpt-4o-mini-realtime-preview-2024-12-17$2.4 per 1M tokens$0.6 per 1M tokens
gpt-4o-mini-search-preview-2025-03-11$0.6 per 1M tokens$0.15 per 1M tokens
gpt-4o-mini-transcribe$5 per 1M tokens$1.25 per 1M tokens
gpt-4o-mini-tts$0 per 1M tokens$0.6 per 1M tokens
gpt-4o-realtime-preview-2024-12-17$20 per 1M tokens$5 per 1M tokens
gpt-4o-search-preview-2025-03-11$10 per 1M tokens$2.5 per 1M tokens
gpt-4o-transcribe$10 per 1M tokens$2.5 per 1M tokens
gpt-5$10 per 1M tokens$1.25 per 1M tokens
gpt-5-chat-latest$0 per 1M tokens$0 per 1M tokens
gpt-5-mini$2 per 1M tokens$0.25 per 1M tokens
gpt-5-nano$0.4 per 1M tokens$0.05 per 1M tokens
gpt-5.1$— per 1M tokens$— per 1M tokens
gpt-5.1-chat-latest$— per 1M tokens$— per 1M tokens
gpt-5.1-codex$— per 1M tokens$— per 1M tokens
gpt-5.1-codex-max$— per 1M tokens$— per 1M tokens
gpt-5.1-codex-mini$— per 1M tokens$— per 1M tokens
gpt-5.2$— per 1M tokens$— per 1M tokens
gpt-5.2-chat-latest$— per 1M tokens$— per 1M tokens
gpt-5.2-codex$— per 1M tokens$— per 1M tokens
gpt-5.2-pro$— per 1M tokens$— per 1M tokens
gpt-image-1$0 per 1M tokens$5 per 1M tokens
o1-2024-12-17$60 per 1M tokens$15 per 1M tokens
o1-mini-2024-09-12$4.4 per 1M tokens$1.1 per 1M tokens
o1-pro-2025-03-19$600 per 1M tokens$150 per 1M tokens
o3-mini-2025-01-31$4.4 per 1M tokens$1.1 per 1M tokens
o4-mini-2025-04-16$4.4 per 1M tokens$1.1 per 1M tokens
o4-mini-deep-research-2025-06-26$8 per 1M tokens$2 per 1M tokens

Need help with setup?

Our team will configure, integrate, and launch AI agents for your business.

View Services