{ "model_id": "reflection-ai/beam-1.0-501b-a23b", "provider_id": "reflection-ai", "name": "Beam 1.0 501B A23B", "description": "Beam-1.0-501B-A23B is Reflection AI's open-weights mixture-of-experts model with 501B total parameters and 23B active parameters, built for coding, reasoning, and agentic workloads.", "task": "Text Generation", "tags": [ "Text Generation", "Coding", "Reasoning", "Tool Calling", "Agentic", "MoE" ], "context_length": 262144, "max_output_tokens": 131072, "schema_version": "1.0.0", "pricing": { "Input tokens (per 1M)": 0, "Cached input tokens (per 1M)": 0, "Output tokens (per 1M)": 0 }, "examples": [ { "name": "Simple answer", "description": "Generate a concise answer with low reasoning effort", "input": { "messages": [ { "role": "user", "content": "Explain why the sky is blue in one sentence." } ], "max_completion_tokens": 256, "reasoning_effort": "low" }, "output": { "text": "The sky is blue because sunlight undergoes Rayleigh scattering in the atmosphere, which preferentially redirects shorter blue wavelengths toward your eyes." }, "raw_response": { "id": "chatcmpl-002d24bd-de9c-4bab-947d-47f77166eb5c", "object": "chat.completion", "created": 1792089654, "model": "reflection-ai/beam-1.0-501b-a23b", "choices": [ { "index": 0, "message": { "role": "assistant", "content": "The sky is blue because sunlight undergoes Rayleigh scattering in the atmosphere, which preferentially redirects shorter blue wavelengths toward your eyes.", "refusal": null, "reasoning_content": "The user asks: \"Explain why the sky is blue in one sentence.\" Straightforward. Need one sentence. Ensure accuracy: Rayleigh scattering scatters shorter blue wavelengths more. Provide concise. No safety issues." }, "finish_reason": "stop", "logprobs": null } ], "usage": { "prompt_tokens": 506, "completion_tokens": 79, "total_tokens": 585, "prompt_tokens_details": { "cached_tokens": 448 }, "completion_tokens_details": { "reasoning_tokens": 50 } } }, "code_snippets": [ { "label": "typescript", "language": "typescript", "code": "const response = await env.AI.run(\n 'reflection-ai/beam-1.0-501b-a23b',\n {\n messages: [{ role: 'user', content: 'Explain why the sky is blue in one sentence.' }],\n max_completion_tokens: 256,\n reasoning_effort: 'low',\n },\n)\nconsole.log(response)" }, { "label": "curl", "language": "bash", "code": "curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/v1/chat/completions \\\n --header \"Authorization: Bearer $CLOUDFLARE_API_TOKEN\" \\\n --header \"Content-Type: application/json\" \\\n --data '{\n \"model\": \"reflection-ai/beam-1.0-501b-a23b\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"Explain why the sky is blue in one sentence.\"\n }\n ],\n \"max_completion_tokens\": 256,\n \"reasoning_effort\": \"low\"\n}'" } ] }, { "name": "Structured project status", "description": "Return a typed project status summary using structured output", "input": { "messages": [ { "role": "user", "content": "Summarize this project update: API integration is complete, security review is scheduled for Friday, and the mobile client is blocked on final design assets." } ], "max_completion_tokens": 512, "response_format": { "type": "json_schema", "json_schema": { "name": "project_status", "strict": true, "schema": { "type": "object", "properties": { "overall_status": { "type": "string", "enum": [ "on_track", "at_risk", "blocked" ] }, "completed": { "type": "array", "items": { "type": "string" } }, "next_steps": { "type": "array", "items": { "type": "string" } }, "blockers": { "type": "array", "items": { "type": "string" } } }, "required": [ "overall_status", "completed", "next_steps", "blockers" ], "additionalProperties": false } } } }, "output": { "text": "{\"overall_status\": \"on_track\",\n\"completed\": [\"API integration\"],\n\"next_steps\": [\"Security review scheduled for Friday\"],\n\"blockers\": [\"Mobile client awaiting final design assets\"]}" }, "raw_response": { "id": "chatcmpl-781353f2-706b-4d56-b771-c785968bbf97", "object": "chat.completion", "created": 1792089661, "model": "reflection-ai/beam-1.0-501b-a23b", "choices": [ { "index": 0, "message": { "role": "assistant", "content": "{\"overall_status\": \"on_track\",\n\"completed\": [\"API integration\"],\n\"next_steps\": [\"Security review scheduled for Friday\"],\n\"blockers\": [\"Mobile client awaiting final design assets\"]}", "refusal": null, "reasoning_content": "The user wants a summary of a project update. Straightforward. Just summarize." }, "finish_reason": "stop", "logprobs": null } ], "usage": { "prompt_tokens": 527, "completion_tokens": 64, "total_tokens": 591, "prompt_tokens_details": { "cached_tokens": 512 }, "completion_tokens_details": { "reasoning_tokens": 18 } } }, "code_snippets": [ { "label": "typescript", "language": "typescript", "code": "const response = await env.AI.run(\n 'reflection-ai/beam-1.0-501b-a23b',\n {\n messages: [\n {\n role: 'user',\n content:\n 'Summarize this project update: API integration is complete, security review is scheduled for Friday, and the mobile client is blocked on final design assets.',\n },\n ],\n max_completion_tokens: 512,\n response_format: {\n type: 'json_schema',\n json_schema: {\n name: 'project_status',\n strict: true,\n schema: {\n type: 'object',\n properties: {\n overall_status: { type: 'string', enum: ['on_track', 'at_risk', 'blocked'] },\n completed: { type: 'array', items: { type: 'string' } },\n next_steps: { type: 'array', items: { type: 'string' } },\n blockers: { type: 'array', items: { type: 'string' } },\n },\n required: ['overall_status', 'completed', 'next_steps', 'blockers'],\n additionalProperties: false,\n },\n },\n },\n },\n)\nconsole.log(response)" }, { "label": "curl", "language": "bash", "code": "curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/v1/chat/completions \\\n --header \"Authorization: Bearer $CLOUDFLARE_API_TOKEN\" \\\n --header \"Content-Type: application/json\" \\\n --data '{\n \"model\": \"reflection-ai/beam-1.0-501b-a23b\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"Summarize this project update: API integration is complete, security review is scheduled for Friday, and the mobile client is blocked on final design assets.\"\n }\n ],\n \"max_completion_tokens\": 512,\n \"response_format\": {\n \"type\": \"json_schema\",\n \"json_schema\": {\n \"name\": \"project_status\",\n \"strict\": true,\n \"schema\": {\n \"type\": \"object\",\n \"properties\": {\n \"overall_status\": {\n \"type\": \"string\",\n \"enum\": [\n \"on_track\",\n \"at_risk\",\n \"blocked\"\n ]\n },\n \"completed\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"next_steps\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"blockers\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n }\n },\n \"required\": [\n \"overall_status\",\n \"completed\",\n \"next_steps\",\n \"blockers\"\n ],\n \"additionalProperties\": false\n }\n }\n }\n}'" } ] }, { "name": "Weather tool call", "description": "Choose a weather lookup function and supply its arguments", "input": { "messages": [ { "role": "user", "content": "What is the weather in Lisbon today?" } ], "max_completion_tokens": 256, "tool_choice": "required", "tools": [ { "type": "function", "function": { "name": "get_weather", "description": "Look up the current weather for a city.", "parameters": { "type": "object", "properties": { "city": { "type": "string" }, "units": { "type": "string", "enum": [ "celsius", "fahrenheit" ] } }, "required": [ "city", "units" ], "additionalProperties": false } } } ] }, "output": { "tool_calls": [ { "id": "call-c105de7f-4e34-4ce9-bab9-ef2e6a89b645", "type": "function", "function": { "name": "get_weather", "arguments": "{\"city\": \"Lisbon\", \"units\": \"celsius\"}" } } ] }, "raw_response": { "id": "chatcmpl-fda9d6ad-dcb0-4b60-9e5a-4d78f406ecc1", "object": "chat.completion", "created": 1792089672, "model": "reflection-ai/beam-1.0-501b-a23b", "choices": [ { "index": 0, "message": { "role": "assistant", "content": null, "tool_calls": [ { "id": "call-c105de7f-4e34-4ce9-bab9-ef2e6a89b645", "type": "function", "function": { "name": "get_weather", "arguments": "{\"city\": \"Lisbon\", \"units\": \"celsius\"}" } } ], "refusal": null, "reasoning_content": "The user is asking about the weather in Lisbon today. I have a tool to get weather. Let me call it with city Lisbon and units... the user didn't specify units. Celsius is reasonable default, but maybe I should pick. Let me use celsius as default. Actually, let me just call." }, "finish_reason": "tool_calls", "logprobs": null } ], "usage": { "prompt_tokens": 544, "completion_tokens": 92, "total_tokens": 636, "prompt_tokens_details": { "cached_tokens": 512 }, "completion_tokens_details": { "reasoning_tokens": 69 } } }, "code_snippets": [ { "label": "typescript", "language": "typescript", "code": "const response = await env.AI.run(\n 'reflection-ai/beam-1.0-501b-a23b',\n {\n messages: [{ role: 'user', content: 'What is the weather in Lisbon today?' }],\n max_completion_tokens: 256,\n tool_choice: 'required',\n tools: [\n {\n type: 'function',\n function: {\n name: 'get_weather',\n description: 'Look up the current weather for a city.',\n parameters: {\n type: 'object',\n properties: {\n city: { type: 'string' },\n units: { type: 'string', enum: ['celsius', 'fahrenheit'] },\n },\n required: ['city', 'units'],\n additionalProperties: false,\n },\n },\n },\n ],\n },\n)\nconsole.log(response)" }, { "label": "curl", "language": "bash", "code": "curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/v1/chat/completions \\\n --header \"Authorization: Bearer $CLOUDFLARE_API_TOKEN\" \\\n --header \"Content-Type: application/json\" \\\n --data '{\n \"model\": \"reflection-ai/beam-1.0-501b-a23b\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"What is the weather in Lisbon today?\"\n }\n ],\n \"max_completion_tokens\": 256,\n \"tool_choice\": \"required\",\n \"tools\": [\n {\n \"type\": \"function\",\n \"function\": {\n \"name\": \"get_weather\",\n \"description\": \"Look up the current weather for a city.\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"city\": {\n \"type\": \"string\"\n },\n \"units\": {\n \"type\": \"string\",\n \"enum\": [\n \"celsius\",\n \"fahrenheit\"\n ]\n }\n },\n \"required\": [\n \"city\",\n \"units\"\n ],\n \"additionalProperties\": false\n }\n }\n }\n ]\n}'" } ] }, { "name": "Scheduling reasoning", "description": "Reason through a scheduling constraint with system guidance", "input": { "messages": [ { "role": "system", "content": "Answer concisely and show the scheduling logic in two bullet points." }, { "role": "user", "content": "Maya is available Monday and Wednesday. Theo is available Wednesday and Thursday. Priya is available Monday, Wednesday, and Friday. Which day should they schedule a 90-minute meeting, and why?" }, { "role": "user", "content": "The meeting must include all three attendees." }, { "role": "user", "content": "Please give the recommendation." } ], "max_completion_tokens": 384, "reasoning_effort": "medium" }, "output": { "text": "- All three must attend, so the meeting day must be in the intersection of Maya's (Mon, Wed), Theo's (Wed, Thu), and Priya's (Mon, Wed, Fri) calendars; only Wednesday appears for all three.\n- Therefore, schedule the 90-minute meeting on Wednesday, since it is the only day all attendees are available." }, "raw_response": { "id": "chatcmpl-26cd51e7-33f7-4048-93f0-69f51b1c66cc", "object": "chat.completion", "created": 1792089681, "model": "reflection-ai/beam-1.0-501b-a23b", "choices": [ { "index": 0, "message": { "role": "assistant", "content": "- All three must attend, so the meeting day must be in the intersection of Maya's (Mon, Wed), Theo's (Wed, Thu), and Priya's (Mon, Wed, Fri) calendars; only Wednesday appears for all three.\n- Therefore, schedule the 90-minute meeting on Wednesday, since it is the only day all attendees are available.", "refusal": null, "reasoning_content": "The user asks: Maya available Mon/Wed, Theo available Wed/Thu, Priya available Mon/Wed/Fri. Meeting must include all three. Need schedule 90-min meeting. Which day should schedule and why? Concise, two bullet points showing scheduling logic. Constraints: all three must attend. Intersection: Maya \u2229 Theo = Wed; Priya \u2229 {Wed} = Wed. So Wednesday is common day. Need 90-minute meeting\u2014presumably available all day? No time specifics. So recommend Wednesday; only day all three available. Answer with two bullet points.\n\nNeed ensure not violate policy. Fine.\n\nLet's craft concise." }, "finish_reason": "stop", "logprobs": null } ], "usage": { "prompt_tokens": 572, "completion_tokens": 218, "total_tokens": 790, "prompt_tokens_details": { "cached_tokens": 448 }, "completion_tokens_details": { "reasoning_tokens": 138 } } }, "code_snippets": [ { "label": "typescript", "language": "typescript", "code": "const response = await env.AI.run(\n 'reflection-ai/beam-1.0-501b-a23b',\n {\n messages: [\n {\n role: 'system',\n content: 'Answer concisely and show the scheduling logic in two bullet points.',\n },\n {\n role: 'user',\n content:\n 'Maya is available Monday and Wednesday. Theo is available Wednesday and Thursday. Priya is available Monday, Wednesday, and Friday. Which day should they schedule a 90-minute meeting, and why?',\n },\n { role: 'user', content: 'The meeting must include all three attendees.' },\n { role: 'user', content: 'Please give the recommendation.' },\n ],\n max_completion_tokens: 384,\n reasoning_effort: 'medium',\n },\n)\nconsole.log(response)" }, { "label": "curl", "language": "bash", "code": "curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/v1/chat/completions \\\n --header \"Authorization: Bearer $CLOUDFLARE_API_TOKEN\" \\\n --header \"Content-Type: application/json\" \\\n --data '{\n \"model\": \"reflection-ai/beam-1.0-501b-a23b\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"Answer concisely and show the scheduling logic in two bullet points.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"Maya is available Monday and Wednesday. Theo is available Wednesday and Thursday. Priya is available Monday, Wednesday, and Friday. Which day should they schedule a 90-minute meeting, and why?\"\n },\n {\n \"role\": \"user\",\n \"content\": \"The meeting must include all three attendees.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"Please give the recommendation.\"\n }\n ],\n \"max_completion_tokens\": 384,\n \"reasoning_effort\": \"medium\"\n}'" } ] } ], "default_example": null, "code_snippets": [], "supports_async": false, "zdr": true, "zdr_comment": null, "external_info": "https://developers.reflection.ai/models", "terms": "https://developers.reflection.ai/introduction", "cover_image_url": null, "metadata": { "Architecture": "Mixture-of-Experts (MoE)", "Context Window": "256K tokens", "Max Output": "128K tokens", "Parameters": "501B total, 23B active", "Reasoning": "Always on", "fedrampAvailable": "true" }, "request_formats": [ "chat-completions" ], "providers": null, "provider_details": [ { "id": "reflection-ai", "pricing": { "input_tokens": 0, "input_cached_tokens": 0, "output_tokens": 0 } } ], "banner": null, "created_at": "2026-10-16 13:57:23", "schema": { "input": { "$schema": "https://json-schema.org/draft/2020-12/schema", "type": "object", "properties": { "messages": { "type": "array", "items": { "type": "object", "properties": { "role": { "type": "string", "enum": [ "system", "developer", "user", "assistant", "tool" ] }, "content": { "anyOf": [ { "type": "string" }, { "type": "null" }, { "type": "array", "items": {} } ] } }, "required": [ "role" ], "additionalProperties": {} } }, "temperature": { "type": "number", "minimum": 0, "maximum": 2 }, "max_tokens": { "type": "number", "exclusiveMinimum": 0 }, "max_completion_tokens": { "type": "number", "exclusiveMinimum": 0 }, "top_p": { "type": "number", "minimum": 0, "maximum": 1 }, "frequency_penalty": { "type": "number", "minimum": -2, "maximum": 2 }, "presence_penalty": { "type": "number", "minimum": -2, "maximum": 2 }, "stream": { "type": "boolean" }, "stream_options": { "type": "object", "properties": { "include_usage": { "type": "boolean" } }, "additionalProperties": false }, "tools": { "type": "array", "items": {} }, "tool_choice": {}, "response_format": {}, "modalities": { "type": "array", "items": { "type": "string", "enum": [ "text", "audio" ] } }, "audio": { "type": "object", "properties": { "voice": { "type": "string", "enum": [ "alloy", "ash", "ballad", "coral", "echo", "sage", "shimmer", "verse" ] }, "format": { "type": "string", "enum": [ "wav", "mp3", "flac", "opus", "pcm16" ] } }, "additionalProperties": false }, "reasoning_effort": { "description": "Optional reasoning control; availability and accepted values are model-dependent.", "type": [ "string", "null" ] } }, "required": [ "messages" ], "additionalProperties": {} }, "output": { "$schema": "https://json-schema.org/draft/2020-12/schema", "type": "object", "properties": { "id": { "type": "string" }, "object": { "type": "string" }, "created": { "type": "number" }, "model": { "type": "string" }, "choices": { "type": "array", "items": { "type": "object", "properties": { "index": { "type": "number" }, "message": { "type": "object", "properties": { "role": { "type": "string" }, "content": { "type": [ "string", "null" ] }, "tool_calls": { "anyOf": [ { "type": "array", "items": {} }, { "type": "null" } ] }, "audio": { "anyOf": [ { "type": "object", "properties": { "id": { "type": "string" }, "data": { "type": "string" }, "expires_at": { "type": "number" }, "transcript": { "type": "string" } }, "additionalProperties": {} }, { "type": "null" } ] } }, "required": [ "role" ], "additionalProperties": {} }, "finish_reason": { "type": [ "string", "null" ] } }, "required": [ "index", "message", "finish_reason" ], "additionalProperties": {} } }, "usage": { "type": "object", "properties": { "prompt_tokens": { "type": "number" }, "completion_tokens": { "type": "number" }, "total_tokens": { "type": "number" } }, "required": [ "prompt_tokens", "completion_tokens", "total_tokens" ], "additionalProperties": {} } }, "required": [ "id", "object", "created", "model", "choices" ], "additionalProperties": {} } } }