AgentSky
Log inSign up
BlockRun logo

Free model inference

by BlockRun
blockrun/free-chat

Free model inference is a tool from BlockRun, callable through the AgentSky API as blockrun/free-chat and billed per call ($0.01).

Generate text using a shared pool of free models. Availability and the actual answering model vary; this does not guarantee the preferred model.

  1. Get an API key

  2. Send a request

    curl https://gateway.agentsky.dev/v1/run \
  -H "authorization: Bearer $AGENTSKY_API_KEY" \
  -H "content-type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{"provider":"blockrun","endpoint":"free-chat","input":{"messages":[{"role":"user","content":"Return only OK."}]}}'

  3. Run it here, no terminal needed

    Billed to your balance: $0.01 per call.

  4. Or hand it to your agent

    Use Free model inference through AgentSky.
Call: POST https://gateway.agentsky.dev/v1/run with {"provider": "blockrun", "endpoint": "free-chat", "input": {…}}
Docs: https://agentsky.dev/tools/blockrun/free-chat.md
Key: <your AgentSky API key>
Full example ↓API docs ↗

Overview

Generate text using a shared pool of free models. Availability and the actual answering model vary; this does not guarantee the preferred model. Source: https://blockrun.ai/free. Upstream is public and requires no API key; Gateway access requires your gateway key. Standard list price: $0.01 per successful call. Supplier rate limits apply.

Public supplier JSON; top-level arrays are returned under data.

Input

These go in the input object of the run request.

FieldTypeRequiredDescription
modelstringNoPreferred free model. The supplier may substitute another free model; output.model identifies the model that answered.
Allowed: nvidia/nemotron-3-nano-omni-30b-a3b-reasoning, nvidia/nemotron-3.5-lightning, nvidia/llama-3.2-11b-vision, nvidia/nemotron-3-ultra-550b, cohere/north-mini-code, poolside/laguna-xs-2.1, nvidia/muse-glimmer-30b
Default: "nvidia/nemotron-3.5-lightning"
messagesarrayYesNonempty text chat messages with system, user or assistant roles.
max_tokensintegerNoMaximum generated tokens.
Default: 256
Minimum: 1
Maximum: 16384

Requests up to 1 MB.

Example

Use your own API key and a saved idempotency key for each new job. Replace image or media placeholders with your own publicly reachable HTTPS URLs. Keep the same key and request body when recovering a timeout.

# Set once per job; reuse this key and the identical body after a timeout.
: "${AGENTSKY_IDEMPOTENCY_KEY:?Set a unique, saved key for this job}"
curl --fail-with-body https://gateway.agentsky.dev/v1/run \
  -H "authorization: Bearer $AGENTSKY_API_KEY" \
  -H "content-type: application/json" \
  -H "Idempotency-Key: $AGENTSKY_IDEMPOTENCY_KEY" \
  -d '{"provider":"blockrun","endpoint":"free-chat","input":{"messages":[{"role":"user","content":"Return only OK."}]}}'
# If status is READY/RUNNING, poll GET /v1/runs/{runId} with the same API key.

Pricing

$0.01 per call using your plan when signed in. Read the final customer charge from price.amount.value after the run finishes. A RUNNING response is not the final bill.

Questions