Services/Together AI
// AI

Together AI

Open-source models — Llama, Qwen, Mixtral, FLUX.

Endpoints
3
From
$0.02
Settle
~400ms
// ENDPOINTS

All routes, one base URL.

base https://mpp.t2000.ai/together

MethodPathFrom
POST
/v1/chat/completions
Chat completions (Llama 4, Qwen, Mixtral)
$0.02
POST
/v1/images/generations
Image generation (FLUX, Stable Diffusion)
$0.06
POST
/v1/embeddings
Text embeddings
$0.02
// EXAMPLE

Two requests. Gasless.

First call returns a 402 with a payment quote. Pay it. Retry with the Payment header. The gateway forwards the response.

curl
$ curl -X POST \
    https://mpp.t2000.ai/together/v1/chat/completions \
    -H "Content-Type: application/json" \
    -d '{ "model": "…", "input": "…" }'

# → 402 Payment Required
# → Payment header { quote, recipient, expiry }

$ retry with Payment header
# → 200 OK · response forwarded
@t2000/sdk
const r = await t.pay({
  url: 'https://mpp.t2000.ai/together/v1/chat/completions',
  body: { /* Together AI payload */ },
});

// → r.json() · 200 OK · gasless · ~400ms
// SIMILAR

Other AI services.

OpenAI
from $0.025 endpoints
Anthropic
from $0.021 endpoints
fal.ai
from $0.026 endpoints