{"schema":"postcutoff/model@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/m/grok-4-7/","md":"https://postcutoff.com/m/grok-4-7/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"grok-4-7","name":"Grok 4.7","org":"xAI","family":"Grok 4","released":"2026-09-21","status":"current","type":"reasoning-llm","modality_in":["text","image"],"modality_out":["text"],"open_weights":false,"model_license":"proprietary","context_window":500000,"max_output":null,"knowledge_cutoff":"2026-05","pricing":{"input":2,"cached_input":0.5,"output":6,"input_over_200k":4,"output_over_200k":12,"unit":"per 1M tokens (USD); higher tier applies to whole request when prompt >= 200k tokens","source":"https://docs.x.ai/docs/models"},"price_line":"$2 in, $6 out per 1M tokens","access":[{"provider":"xAI API","model_id":"grok-4.7","endpoint":"https://api.x.ai/v1/chat/completions","docs":"https://docs.x.ai/docs/models/grok-4.7"},{"provider":"AWS Bedrock","model_id":"xai.grok-4.7","inference_profiles":["global.xai.grok-4.7","us.xai.grok-4.7"],"docs":"https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-xai-grok-4-7.html"},{"provider":"OpenRouter","model_id":"x-ai/grok-4.7","url":"https://openrouter.ai/x-ai/grok-4.7"},{"provider":"Web app","url":"https://grok.com"}],"capabilities":[{"name":"Four-level reasoning effort incl. xhigh","detail":"Configurable reasoning effort low / medium / high / xhigh (default high) on one model id.","first":false,"discovered":"launch","source":"https://docs.x.ai/docs/models/grok-4.7"},{"name":"500K context at unchanged price","detail":"500K-token context with text+image input; launched at the same $2/$6 price as Grok 4.6 while claiming notable gains.","first":false,"discovered":"launch","source":"https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-xai-grok-4-7.html"},{"name":"Mixed independent benchmark results","detail":"Early third-party evals showed a more mixed picture than xAI's claims, still behind top Claude/GPT-6 models on several tasks.","first":false,"discovered":"later","source":"https://tech.yahoo.com/ai/gemini/articles/xai-launches-grok-4-7-171603280.html"}],"entry":null,"notes":"Alias grok-4.7-latest. xAI flagship as of Sept 2026; no Batch API; logprobs unsupported. Bedrock launched 2026-09-28 (Global CRIS $2/$6, Geo $2.20/$6.60). Max output not published.","verified":"2026-10-13","body_md":"xAI's flagship for coding, agentic tasks and knowledge work (successor to Grok 4.6 / 4.5).\n\n```bash\ncurl https://api.x.ai/v1/chat/completions -H \"Authorization: Bearer $XAI_API_KEY\" -H \"Content-Type: application/json\" \\\n -d '{\"model\":\"grok-4.7\",\"reasoning_effort\":\"high\",\"messages\":[{\"role\":\"user\",\"content\":\"Hello\"}]}'\n```\n\nSources: https://docs.x.ai/docs/models , https://docs.x.ai/docs/models/grok-4.7 , https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-xai-grok-4-7.html\n\nAWS Machine Learning Blog, Oct 13, 2026 (\"Build long-horizon agents with Grok 4.7 on Amazon Bedrock\"): use the cross-Region inference profiles `us.xai.grok-4.7` or `global.xai.grok-4.7`; 500K-token context, text and image input, text output. https://aws.amazon.com/blogs/machine-learning/build-long-horizon-agents-with-grok-4-7-on-amazon-bedrock/","page_url":"https://postcutoff.com/m/grok-4-7/","events_after":1829,"major_after":419,"historic_after":82,"missing_at_launch":387,"events_since_release":null,"you_url":"https://postcutoff.com/you/grok-4-7/","briefings":{"xs":"https://postcutoff.com/briefings/cutoff-2026-05-xs.md","s":"https://postcutoff.com/briefings/cutoff-2026-05-s.md","m":"https://postcutoff.com/briefings/cutoff-2026-05-m.md","full":"https://postcutoff.com/briefings/cutoff-2026-05.md"}}