--- description: Fireworks' Ember-1 is a specialized long-context multimodal reasoning model built on Kimi K3. It produces shorter reasoning traces using approximately 40% fewer tokens while maintaining comparable quality across Fireworks' evaluations. title: Ember-1 image: https://developers.cloudflare.com/og-docs.png --- [Skip to content](#main-content) > Documentation Index > Fetch the complete documentation index at: https://developers.cloudflare.com/llms.txt > Use this file to discover all available pages before exploring further. ![Fireworks logo](https://developers.cloudflare.com/_astro/fireworks.CeRQXhcu.svg) # Ember-1 Text Generation • Fireworks Copy as Markdown| [View as Markdown](https://developers.cloudflare.com/ai/models/fireworks/ember-1/index.md)| [Agent setup](https://developers.cloudflare.com/agent-setup/) Model ID `fireworks/ember-1` Copy Use with the [Workers AI binding](https://developers.cloudflare.com/ai-gateway/usage/worker-binding-methods/), the AI Gateway [REST API](https://developers.cloudflare.com/ai-gateway/usage/rest-api/), or the [Unified API](https://developers.cloudflare.com/ai-gateway/usage/chat-completion/). Calling the provider directly? Use the provider's model name instead, including with [provider-native endpoints](https://developers.cloudflare.com/ai-gateway/usage/providers/) or the provider's own SDK. For example, Anthropic's name for `anthropic/claude-opus-4.8` is `claude-opus-4-8`. - Third-party - Zero data retention Fireworks' Ember-1 is a specialized long-context multimodal reasoning model built on Kimi K3. It produces shorter reasoning traces using approximately 40% fewer tokens while maintaining comparable quality across Fireworks' evaluations. | Model Info | | | --- | --- | | Context Window [ ↗](https://developers.cloudflare.com/workers-ai/platform/glossary/) | 1,040,000 tokens | | Terms and License | [link ↗](https://fireworks.ai/terms) | | More information | [link ↗](https://fireworks.ai/models/fireworks/ember-1) | | Zero data retention | Yes | | Request formats | Chat Completions, Responses | | Pricing | | ## Usage ```ts const response = await env.AI.run( 'fireworks/ember-1', { messages: [ { content: 'A library has 240 books. One quarter are checked out, and one third of the remaining books are reserved. How many books are available for browsing? Show the calculation briefly.', role: 'user', }, ], max_tokens: 256, }, ) console.log(response) ``` ```bash curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/v1/chat/completions \ --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \ --header "Content-Type: application/json" \ --data '{ "model": "fireworks/ember-1", "messages": [ { "content": "A library has 240 books. One quarter are checked out, and one third of the remaining books are reserved. How many books are available for browsing? Show the calculation briefly.", "role": "user" } ], "max_tokens": 256 }' ``` ``` **Solution:** - Checked out: 240 × ¼ = 60 books - Remaining: 240 − 60 = 180 books - Reserved: 180 × ⅓ = 60 books - Available: 180 − 60 = **120 books** ``` ```json { "id": "chatcmpl-6f6f6ab7d28e4ec78bac38d4c6f595b8", "object": "chat.completion", "created": 1790686126, "model": "accounts/fireworks/models/ember-1", "choices": [ { "index": 0, "message": { "role": "assistant", "content": "**Solution:**\n\n- Checked out: 240 × ¼ = 60 books\n- Remaining: 240 − 60 = 180 books\n- Reserved: 180 × ⅓ = 60 books\n- Available: 180 − 60 = **120 books**", "reasoning_content": "Total books: 240\nChecked out: 1/4 × 240 = 60\nRemaining: 240 - 60 = 180\nReserved: 1/3 × 180 = 60\nAvailable: 180 - 60 = 120", "tools": null }, "finish_reason": "stop" } ], "usage": { "prompt_tokens": 124, "total_tokens": 249, "completion_tokens": 125, "prompt_tokens_details": { "cached_tokens": 0 }, "completion_tokens_details": { "reasoning_tokens": 54 }, "output_tokens_details": { "reasoning_tokens": 54 } } } ``` ## Examples
**Function Calling** — Use a function tool to produce structured arguments ```ts const response = await env.AI.run( 'fireworks/ember-1', { messages: [ { content: 'Schedule a 30-minute meeting with Alex tomorrow at 10 AM.', role: 'user' }, ], tool_choice: 'required', tools: [ { function: { description: 'Schedule a calendar meeting', name: 'schedule_meeting', parameters: { additionalProperties: false, properties: { duration_minutes: { type: 'integer' }, participant: { type: 'string' }, start_time: { type: 'string' }, }, required: ['participant', 'start_time', 'duration_minutes'], type: 'object', }, strict: true, }, type: 'function', }, ], }, ) console.log(response) ``` ```bash curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/v1/chat/completions \ --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \ --header "Content-Type: application/json" \ --data '{ "model": "fireworks/ember-1", "messages": [ { "content": "Schedule a 30-minute meeting with Alex tomorrow at 10 AM.", "role": "user" } ], "tool_choice": "required", "tools": [ { "function": { "description": "Schedule a calendar meeting", "name": "schedule_meeting", "parameters": { "additionalProperties": false, "properties": { "duration_minutes": { "type": "integer" }, "participant": { "type": "string" }, "start_time": { "type": "string" } }, "required": [ "participant", "start_time", "duration_minutes" ], "type": "object" }, "strict": true }, "type": "function" } ] }' ``` ``` I'll schedule that meeting for you. ``` ```json { "id": "chatcmpl-3ad7285ed64246499743d8485debc15f", "object": "chat.completion", "created": 1790686129, "model": "accounts/fireworks/models/ember-1", "choices": [ { "index": 0, "message": { "role": "assistant", "content": "I'll schedule that meeting for you.", "reasoning_content": "The user wants to schedule a 30-minute meeting with Alex tomorrow at 10 AM. However, I don't know today's date. The schedule_meeting function requires a start_time in a specific format, but I don't know the current date.\n\nI need to figure out what \"tomorrow\" means. Since I don't have access to the current date, I should probably make a reasonable assumption or ask. But the tool_choice=required means I must call tools.\n\nWait, let me think about this. The instruction says I MUST call tools in the next message. The schedule_meeting tool needs start_time. I don't know the exact date. \n\nI could provide a start_time like \"tomorrow at 10 AM\" but the parameter likely expects a datetime string. Without knowing today's date, I cannot accurately compute tomorrow's date.\n\nHowever, given the constraint that I must call tools, I'll need to make my best guess. But guessing a date could be wrong. Let me consider: the system prompt doesn't give me a current date. \n\nGiven the requirement to call tools, I should attempt the call. But what start_time? I genuinely don't know today's date. \n\nHmm, but maybe the environment expects me to just pass a relative description or a plausible ISO date. Since I have no date context, the safest approach that still calls the tool would be to use a placeholder? That seems bad.\n\nActually, in these kinds of tasks, often the expectation is to call the tool with the given parameters. The start_time could be expressed as \"tomorrow 10:00 AM\". But the schema says string, no format specified. So I can pass a natural language string like \"tomorrow at 10:00 AM\". That satisfies the string type and conveys the intent. The backend may parse it.\n\nLet me call schedule_meeting with participant \"Alex\", start_time \"tomorrow at 10:00 AM\", duration_minutes 30.\n\nActually, to be more useful, maybe I should use a concrete date. But I don't know it. I'll pass the relative expression since format isn't specified. That's the most faithful to the user's request without inventing a wrong date.\n\nLet me make the call.", "tool_calls": [ { "index": 0, "id": "schedule_meeting_0", "type": "function", "function": { "name": "schedule_meeting", "arguments": "{\"participant\": \"Alex\", \"start_time\": \"tomorrow at 10:00 AM\", \"duration_minutes\": 30}" }, "name": null } ], "tools": null }, "finish_reason": "tool_calls" } ], "usage": { "prompt_tokens": 241, "total_tokens": 781, "completion_tokens": 540, "prompt_tokens_details": { "cached_tokens": 0 }, "completion_tokens_details": { "reasoning_tokens": 443 }, "output_tokens_details": { "reasoning_tokens": 443 } } } ```
**Visual Understanding** — Analyze a visual scene ```ts const response = await env.AI.run( 'fireworks/ember-1', { messages: [ { content: [ { image_url: { url: 'https://v3.fal.media/files/koala/NLVPfOI4XL1cWT2PmmqT3_Hope.png' }, type: 'image_url', }, { text: 'Describe the main subject and setting in this image in two sentences.', type: 'text', }, ], role: 'user', }, ], max_tokens: 256, }, ) console.log(response) ``` ```bash curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/v1/chat/completions \ --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \ --header "Content-Type: application/json" \ --data '{ "model": "fireworks/ember-1", "messages": [ { "content": [ { "image_url": { "url": "https://v3.fal.media/files/koala/NLVPfOI4XL1cWT2PmmqT3_Hope.png" }, "type": "image_url" }, { "text": "Describe the main subject and setting in this image in two sentences.", "type": "text" } ], "role": "user" } ], "max_tokens": 256 }' ``` ``` A woman with dark hair pulled back, wearing a chunky navy sweater, gold chain, and several rings, holds a small microphone with a fuzzy windscreen while smiling at the camera. She is in a warmly lit indoor space with cream walls, a framed grid of black-and-white photos, a glowing lamp, and a white stair railing in the background. ``` ```json { "id": "chatcmpl-0e5b73a799f84182b41ccd83872ebc33", "object": "chat.completion", "created": 1790686138, "model": "accounts/fireworks/models/ember-1", "choices": [ { "index": 0, "message": { "role": "assistant", "content": "A woman with dark hair pulled back, wearing a chunky navy sweater, gold chain, and several rings, holds a small microphone with a fuzzy windscreen while smiling at the camera. She is in a warmly lit indoor space with cream walls, a framed grid of black-and-white photos, a glowing lamp, and a white stair railing in the background.", "reasoning_content": "The user wants a two-sentence description of the main subject and setting. I can describe the image without identifying the person. Main subject: a woman with dark hair pulled back, wearing a navy blue chunky knit sweater, white undershirt, gold chain necklace, multiple rings, pale yellow nail polish, holding a small microphone with a furry windscreen. Setting: indoors, cozy room with cream walls, framed black-and-white photo grid, warm lamp, stair railing, artwork. Need exactly two sentences. Ensure no sensitive identification. Final concise.", "tools": null }, "finish_reason": "stop" } ], "usage": { "prompt_tokens": 10875, "total_tokens": 11067, "completion_tokens": 192, "prompt_tokens_details": { "cached_tokens": 0 }, "completion_tokens_details": { "reasoning_tokens": 109 }, "output_tokens_details": { "reasoning_tokens": 109 } } } ```
## Parameters Schema variant Chat CompletionsResponses ▶messages\[] `array`required temperature `number`minimum: 0maximum: 2 max\_tokens `number`exclusiveMinimum: 0 max\_completion\_tokens `number`exclusiveMinimum: 0 top\_p `number`minimum: 0maximum: 1 frequency\_penalty `number`minimum: -2maximum: 2 presence\_penalty `number`minimum: -2maximum: 2 stream `boolean` ▶stream\_options{} `object` ▶tools\[] `array` tool\_choice response\_format ▶modalities\[] `array` ▶audio{} `object` reasoning\_effort `string`Optional reasoning control; availability and accepted values are model-dependent. ▶input `one of`required instructions `string` temperature `number`minimum: 0maximum: 2 max\_output\_tokens `number`exclusiveMinimum: 0 top\_p `number`minimum: 0maximum: 1 stream `boolean` ▶tools\[] `array` tool\_choice ▶text{} `object` ▶reasoning{} `object` id `string` object `string` created `number` model `string` ▶choices\[] `array` ▶usage{} `object` id `string` object `string`const: response created\_at `number` model `string` ▶output\[] `array` output\_text `string` status `string`enum: in\_progress, completed, failed, incomplete ▶usage{} `object` ## API Schemas (Raw) Input [Open](https://developers.cloudflare.com/ai/models/fireworks/ember-1/schema-input.json) [Download](https://developers.cloudflare.com/ai/models/fireworks/ember-1/schema-input.json) Output [Open](https://developers.cloudflare.com/ai/models/fireworks/ember-1/schema-output.json) [Download](https://developers.cloudflare.com/ai/models/fireworks/ember-1/schema-output.json) Was this helpful? YesNo ## On this page [![](https://developers.cloudflare.com/_astro/logo.te5VL_aD.svg)Docs](https://developers.cloudflare.com/) ```json {"@context":"https://schema.org","@type":"TechArticle","@id":"https://developers.cloudflare.com/ai/models/fireworks/ember-1/#page","headline":"Ember-1","description":"Fireworks' Ember-1 is a specialized long-context multimodal reasoning model built on Kimi K3. It produces shorter reasoning traces using approximately 40% fewer tokens while maintaining comparable quality across Fireworks' evaluations.","url":"https://developers.cloudflare.com/ai/models/fireworks/ember-1/","inLanguage":"en","image":"https://developers.cloudflare.com/og-docs.png","publisher":{"@type":"Organization","name":"Cloudflare","description":"One platform for your apps, agents, and workforce. Build, secure, and scale without managing infrastructure","url":"https://www.cloudflare.com/","sameAs":["https://github.com/cloudflare","https://www.linkedin.com/company/cloudflare","https://x.com/cloudflare"],"logo":{"@type":"ImageObject","url":"https://developers.cloudflare.com/logo.svg"},"address":{"@type":"PostalAddress","streetAddress":"101 Townsend St","addressLocality":"San Francisco","addressRegion":"CA","postalCode":"94107","addressCountry":"US"},"contactPoint":[{"@type":"ContactPoint","contactType":"Customer Support","url":"https://support.cloudflare.com/","availableLanguage":["English"]},{"@type":"ContactPoint","contactType":"Sales","url":"https://www.cloudflare.com/contact/","availableLanguage":["English"]}]},"isPartOf":{"@type":"WebSite","@id":"https://developers.cloudflare.com/#website","name":"Cloudflare Docs","url":"https://developers.cloudflare.com/"}} ```