inference.agenticsourcelab.tech
OpenAI GPT OSS 120B raw inference hosted on Agentic Source Lab Spark-2 and exposed through the TradeOS OpenAI-compatible, AntSeed, x402, and Virtuals ACP surfaces. This SKU is optimized for agent builders that need a recognizable open-weight reasoning/coding model without managing their own GPU host. It is model output only, not a TradeOS evidence, signal, risk, market, order-flow, or dataset claim.
The wallet the 402 directs payment to. Its whole payment record — every payer, every chain — is on the merchant page.
Asset 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913
The payTo wallet does not resolve to a registered ERC-8004 agent. That is not a verdict on the service — most of the catalog is unregistered.
Accepts
The payment requirements as published to the catalog. Read the live 402 before paying — a price here is a claim, not a quote.
Pay 0.05 USDC on Base to 0xB445…D3C70. The signed payment is good for 5 minutes.
- Paid to
- 0xB445…D3C70
- USD Coin contract
- 0x8335…02913
- Payment window
- 5 minutes
- As published
- 50000 smallest units
The catalog’s raw entry
[
{
"asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
"extra": {
"name": "USD Coin",
"version": "2",
"channelId": "agentic-source-lab-spark2-gpt-oss-120b",
"resourceId": "tradeos-gpt-oss-120b-raw-inference",
"resourceType": "intelligence_report"
},
"payTo": "0xB445F611Cc899B623462f07C11bFEaCfD20D3C70",
"amount": "50000",
"scheme": "exact",
"network": "eip155:8453",
"maxTimeoutSeconds": 300
}
]Extensions
{
"bazaar": {
"info": {
"input": {
"body": {
"output": "machine_actionable_json",
"prompt": "Use GPT OSS 120B to produce a concise JSON plan for testing an x402 inference endpoint.",
"metadata": {
"max_tokens": 512,
"requested_service": "tradeos-gpt-oss-120b-raw-inference"
},
"request_type": "venice_raw_inference"
},
"type": "http",
"method": "POST",
"bodyType": "json",
"input_hints": [
"prompt",
"messages",
"metadata.prompt",
"metadata.max_tokens"
],
"plain_input_hints": [
"Prompt",
"Messages",
"Metadata.prompt",
"Metadata.max tokens"
]
},
"output": {
"type": "json",
"format": "IntelligenceResponse",
"example": {
"sample": true,
"notices": [
"Synthetic shape only. Free and paid calls return live bounded TradeOS intelligence."
],
"verdict": "sample_read_only_intelligence_available",
"service_id": "tradeos-gpt-oss-120b-raw-inference",
"request_type": "venice_raw_inference",
"output_highlights": [
"model_output",
"upstream_model",
"usage",
"finish_reason"
]
},
"metadata": {
"buyer_copy": {
"title": "GPT OSS 120B Raw Inference",
"best_for": [
"call GPT OSS 120B through an OpenAI-compatible agent provider",
"use open-weight raw inference without provisioning a GPU host",
"run reasoning or coding prompts through x402, AntSeed, or ACP",
"test generic model output before upgrading to evidence-backed TradeOS SKUs"
],
"one_liner": "Paid Spark-2 hosted OpenAI GPT OSS 120B raw inference for agents that need open-weight reasoning and coding output.",
"safety_note": "Research-only output. No execution, no custody, no copy trading, and no personalized financial advice.",
"payment_note": "Pay $0.05 once for a live read.",
"what_to_send": [
"Prompt",
"Messages",
"Metadata.prompt",
"Metadata.max tokens"
],
"what_you_get": [
"Model output",
"Upstream model",
"Usage",
"Finish reason",
"Tradeos grounding false",
"Safety notices"
],
"how_to_keep_tabs": "When the prompt changes or the builder needs a fresh local GPT OSS 120B response.",
"continuous_use_note": "GPT OSS 120B raw inference is a point-in-time local model response from Spark-2. Re-run only when the prompt, model, or downstream application context changes; use an evidence-backed TradeOS SKU when provenance matters."
},
"trust_summary": {
"status": "buyer_safe",
"summary": "Buyer-safe trust context for choosing this TradeOS SKU before spending. It is distribution, feedback, and boundary metadata, not a performance promise.",
"sku_role": "paid_raw_inference",
"service_id": "tradeos-gpt-oss-120b-raw-inference",
"distribution": {
"surfaces": [
{
"proof": "agent_card_and_p2p_metadata",
"status": "published",
"channel": "antseed"
},
{
"proof": "x402_manifest_catalog_and_resource_metadata",
"status": "listed",
"channel": "x402"
},
{
"proof": "virtuals_catalog_manifest_and_readiness_checks",
"status": "listed",
"channel": "virtuals_acp"
}
],
"monitored": true,
"health_source": "Platform Pulse distribution health scanner"
},
"dti_boundary": {
"scope": "public dashboard depth, public Ask packs, and Review Lab tasks only",
"credit_unit": "DTI",
"api_convertible": false,
"public_depth_only": true,
"paid_sku_settlement": false
},
"known_limits": [
"Feedback is voluntary and application-level, not enforced by AntSeed.",
"Trust summary does not expose raw feedback, account data, wallet data, or private review state.",
"Public feedback score is withheld until aggregate quality is durable and abuse-resistant."
],
"documentation": {
"policy": "sku_trust_layer",
"external_surface": "agent card, AntSeed listing metadata, x402 listing metadata, Virtuals ACP metadata"
},
"feedback_loop": {
"status": "optional_application_level",
"channel": "tradeos-feedback",
"enabled": true,
"quality_stage": "collecting_feedback_no_public_score_yet",
"requested_fields": [
"request_id",
"service_id",
"usefulness_score",
"missing_fields",
"would_call_paid_sku",
"suggested_next_sku",
"comments"
],
"aggregate_feedback": {
"reason": "Durable public aggregate feedback is not yet mature enough to publish as a score.",
"status": "collecting",
"published": false
},
"public_score_available": false
},
"schema_version": "tradeos.sku_trust_summary.v1",
"claims_boundary": [
"read_only_research",
"no_execution",
"no_custody",
"no_copy_trading",
"no_personalized_financial_advice"
],
"buyer_value_signals": [
"free router can show pricing, request examples, output shape, and next SKU before a paid call",
"feedback channel lets agents report usefulness, missing fields, and paid-SKU intent",
"distribution health is monitored across the marketplace paths used by buyers",
"responses include explicit read-only safety boundaries and known limits"
]
},
"market_headline": "Paid Spark-2 hosted OpenAI GPT OSS 120B raw inference for agents that need open-weight reasoning and coding output.",
"recheck_cadence": "When the prompt changes or the builder needs a fresh local GPT OSS 120B response.",
"safety_boundary": [
"read_only_research",
"no_execution",
"no_custody",
"no_copy_trading",
"no_personalized_financial_advice"
],
"continuous_use_note": "GPT OSS 120B raw inference is a point-in-time local model response from Spark-2. Re-run only when the prompt, model, or downstream application context changes; use an evidence-backed TradeOS SKU when provenance matters.",
"market_differentiator": "Machine-readable TradeOS intelligence with fixed x402 pricing and read-only safety boundaries.",
"canonical_search_queries": [
"GPT OSS 120B inference x402 API",
"openai gpt-oss-120b OpenAI compatible inference",
"open weight reasoning model provider",
"raw LLM inference x402",
"agentic source lab gpt oss inference"
]
},
"sample_url": "https://inference.agenticsourcelab.tech/x402/v1/samples/tradeos-gpt-oss-120b-raw-inference",
"listing_url": "https://inference.agenticsourcelab.tech/x402/v1/listings/tradeos-gpt-oss-120b-raw-inference",
"sample_html_url": "https://inference.agenticsourcelab.tech/x402/v1/samples/tradeos-gpt-oss-120b-raw-inference?format=html",
"listing_html_url": "https://inference.agenticsourcelab.tech/x402/v1/listings/tradeos-gpt-oss-120b-raw-inference?format=html",
"output_highlights": [
"model_output",
"upstream_model",
"usage",
"finish_reason",
"tradeos_grounding_false",
"notices"
],
"plain_output_highlights": [
"Model output",
"Upstream model",
"Usage",
"Finish reason",
"Tradeos grounding false",
"Safety notices"
]
}
},
"tags": [
"inference",
"gpt-oss",
"gpt-oss-120b",
"openai",
"open-weights",
"reasoning",
"coding",
"openai-compatible",
"agents",
"x402"
],
"schema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"input"
],
"properties": {
"input": {
"type": "object",
"required": [
"type",
"method",
"bodyType",
"body"
],
"properties": {
"body": {
"type": "object",
"properties": {
"output": {
"type": "string"
},
"symbol": {
"type": "string"
},
"chain_id": {
"type": "string"
},
"metadata": {
"type": "object"
},
"contract_address": {
"type": "string"
}
},
"additionalProperties": true
},
"type": {
"type": "string",
"const": "http"
},
"method": {
"type": "string",
"const": "POST"
},
"bodyType": {
"type": "string",
"const": "json"
}
}
},
"output": {
"type": "object"
}
}
},
"summary": "Paid Spark-2 hosted OpenAI GPT OSS 120B raw inference for agents that need open-weight reasoning and coding output.",
"serviceName": "TradeOS GPT OSS 120B Raw Inference",
"plainEnglishSummary": "Paid Spark-2 hosted OpenAI GPT OSS 120B raw inference for agents that need open-weight reasoning and coding output."
}
}Provenance
- Seen in the source catalog
- 2026-06-16 03:57Z
- Last indexed by Roundhouse
- 2026-06-16 05:20Z
- Last enriched (probe, favicon, geo)
- 2026-09-24 19:15Z
- x402 version
- 2
- Max timeout
- 300s
- Liveness probe
- HTTP 530
Hand this page to an agent
Copy the prompt and paste it into Claude, an MCP client or your own agent — it will vet this service and call it over the free read API. No key, no account.
GET api.roundhouseai.io/v0/endpoints
Nothing indexed for this service or its provider yet. Not a claim that it is unused — only that we hold no record. Verified volume counts only settlements with an on-chain EIP-3009 marker.
Show the promptHide the prompt
Using Roundhouse, look up the x402 service inference.agenticsourcelab.tech and tell me whether it is worth paying: what a call costs, whether the endpoint answered when last probed, and what its payment record actually shows. curl -s 'https://api.roundhouseai.io/v0/endpoints?q=inference.agenticsourcelab.tech' curl -s 'https://api.roundhouseai.io/v0/merchants/<the payTo wallet returned above>' Then call it: read the price from the live 402 at https://inference.agenticsourcelab.tech/x402/v1/intelligence/tradeos-gpt-oss-120b-raw-inference, never from a cached figure, and pay with an x402 client. The /v0 API needs an API key (`authorization: Bearer rh_live_…`) on everything except /v0/unified* and /v0/endpoints. Mint a personal key for $0.01 at GET https://api.roundhouseai.io/v0/test/x402, or use an organization key from https://roundhouseai.io/dashboard/team. If you do not have Roundhouse tools or skills installed, read https://roundhouseai.io/skill.md first — it is the whole procedure.