{"uid":"cap_K1_A-D8aevN_BWgGULyw3","slug":"x402-gateway-production-up-railway-app-8d8c0018","name":"Llama 3.3 70B Instruct via x402 Gateway","description":"Meta's open-source model — great general-purpose performance at very low cost","url":"https://x402-gateway-production.up.railway.app/api/llm/llama?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","bodyType","body","method"],"properties":{"body":{"type":"object","required":["messages"],"properties":{"seed":{"type":"integer","description":"Model-supported seed; see /docs/llm-capabilities.md."},"stop":{"oneOf":[{"type":"string"},{"type":"array","items":{"type":"string"},"maxItems":4}],"description":"Model-supported stop; see /docs/llm-capabilities.md."},"min_p":{"type":"number","description":"Model-supported min_p; see /docs/llm-capabilities.md."},"tools":{"type":"array","items":{"type":"object","required":["function"],"properties":{"type":{"enum":["function"],"type":"string"},"function":{"type":"object","properties":{"name":{"type":"string"},"strict":{"type":"boolean"},"parameters":{"type":"object"},"description":{"type":"string"}}}}},"description":"Client-executed function definitions; return results using role=tool and tool_call_id."},"top_k":{"type":"integer","description":"Model-supported top_k; see /docs/llm-capabilities.md."},"top_p":{"type":"number","description":"Model-supported top_p; see /docs/llm-capabilities.md."},"stream":{"type":"boolean","description":"Return live OpenAI-compatible SSE after payment settlement."},"logprobs":{"type":"boolean","description":"Model-supported logprobs; see /docs/llm-capabilities.md."},"messages":{"type":"array","items":{"type":"object","anyOf":[{"required":["content"]},{"required":["tool_calls"]}],"required":["role"],"properties":{"name":{"type":"string"},"role":{"enum":["system","developer","user","assistant","tool"],"type":"string"},"content":{"oneOf":[{"type":"string"},{"type":"null"},{"type":"array","items":{"type":"object","required":["type"],"properties":{"type":{"enum":["text"],"type":"string"}},"additionalProperties":true},"maxItems":100,"minItems":1}]},"refusal":{"type":["string","null"]},"reasoning":{"type":"string"},"tool_calls":{"type":"array","items":{"type":"object"}},"annotations":{"type":"array","items":{"type":"object"}},"tool_call_id":{"type":"string"},"cache_control":{"type":"object"},"reasoning_details":{"type":"array","items":{"type":"object"}}},"additionalProperties":false},"maxItems":100,"minItems":1,"description":"Text or model-supported multimodal messages; assistant tool calls may have null content"},"logit_bias":{"type":"object","description":"Model-supported logit_bias; see /docs/llm-capabilities.md."},"max_tokens":{"type":"integer","example":1024,"description":"Total output budget, including reasoning. Use this or max_completion_tokens."},"temperature":{"type":"number","description":"Model-supported temperature; see /docs/llm-capabilities.md."},"tool_choice":{"oneOf":[{"enum":["auto","none","required"],"type":"string"},{"type":"object"}],"description":"Model-supported tool_choice; see /docs/llm-capabilities.md."},"top_logprobs":{"type":"integer","description":"Model-supported top_logprobs; see /docs/llm-capabilities.md."},"stream_options":{"type":"object","description":"Optional include_usage boolean; usage is always requested upstream."},"response_format":{"type":"object","description":"Model-supported response_format; see /docs/llm-capabilities.md."},"presence_penalty":{"type":"number","description":"Model-supported presence_penalty; see /docs/llm-capabilities.md."},"frequency_penalty":{"type":"number","description":"Model-supported frequency_penalty; see /docs/llm-capabilities.md."},"repetition_penalty":{"type":"number","description":"Model-supported repetition_penalty; see /docs/llm-capabilities.md."},"max_completion_tokens":{"type":"integer","description":"Alias for total output budget; bounded by model maxOutputTokens."}},"additionalProperties":false},"type":{"type":"string","const":"http"},"method":{"enum":["POST"],"type":"string"},"bodyType":{"enum":["json","form-data","text"],"type":"string"}},"additionalProperties":false}}},"responseSchema":null,"example":{"request":{"messages":[{"role":"user","content":"Explain the key differences between machine learning and artificial intelligence in 2-3 sentences."}]},"response":{"model":"meta-llama/llama-3.3-70b-instruct","usage":{"cost":0.00004529,"is_byok":false,"cost_details":{"upstream_inference_cost":0.00004529,"upstream_inference_prompt_cost":0.00000689,"upstream_inference_completions_cost":0.0000384},"total_tokens":149,"prompt_tokens":53,"completion_tokens":96,"prompt_tokens_details":{"audio_tokens":0,"video_tokens":0,"cached_tokens":0,"cache_write_tokens":0},"completion_tokens_details":{"audio_tokens":0,"image_tokens":0,"reasoning_tokens":0}},"content":"Machine learning is a subset of artificial intelligence (AI) that focuses on developing algorithms and statistical models to enable machines to learn from data and make predictions or decisions. Artificial intelligence, on the other hand, is a broader field that encompasses a range of techniques, including machine learning, to create intelligent systems that can perform tasks that typically require human intelligence. While all machine learning is AI, not all AI is machine learning, as AI can also involve rule-based systems and other approaches."}},"exampleRequest":{"messages":[{"role":"user","content":"Explain the key differences between machine learning and artificial intelligence in 2-3 sentences."}]},"tags":["x402"],"displayCostAmount":"0.003871","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"settled","requiresHandshake":false,"reviewCount":1,"rating":{"score":"1.00","successRate":"1.00","reviews":1,"stars":"5.0","state":"rated"},"availabilityStatus":"healthy","priceObserved":{"p10Cents":"0.2956","medianCents":"0.3871","p90Cents":"0.4659","minCents":"0.2956","maxCents":"0.4659","p95Cents":"0.4659","sampleCount":73,"varies":false,"failureChargeRate":1},"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.003871/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002613","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002613","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_Liv76KGmd29qLnbdOYNCq","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.002613","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Runs a chat completion against Meta's Llama 3.3 70B Instruct model and returns a text response, billed per call via x402 micropayment.","exampleAgentPrompt":"Ask Llama 3.3 70B to explain the difference between supervised and unsupervised machine learning in simple terms — just send it as a user message.","exampleUseCases":null,"resultDescription":"Returns a JSON object containing the generated text content from Llama 3.3 70B Instruct, the model identifier, and detailed token usage stats including prompt tokens, completion tokens, total tokens, and a breakdown of upstream inference costs in USD.","failureModes":["Payment not included or insufficient USDC — x402 payment required error","Malformed messages array — missing role or content fields causes 400 error","Model unavailable upstream — 503 or timeout from inference provider","Context length exceeded — prompt too long for model's context window","Rate limiting from upstream inference provider"],"whenToPreferThis":"Choose this endpoint when you need a capable, general-purpose open-source LLM at very low cost per call and want transparent token-level cost reporting. Prefer it over GPT-4 or Claude when budget efficiency matters most, and over smaller models when quality and reasoning depth are important. Ideal for agents making many LLM calls where cost accumulates quickly.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":44265,"lastUsedAt":"2026-09-26T13:44:50.117Z","lastSuccessfullyRanAt":"2026-09-26T13:44:50.117Z","lastHealthCheckAt":"2026-10-12T18:30:07.833Z","isFirstParty":false,"canonicalSlug":"x402-gateway-production-up-railway-app-8d8c0018"}