The Orchestrator › Models › Fireworks
Fireworks: Ember-1
Ember-1 is a specialized reasoning model from Fireworks Research, built on Kimi K3. It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40%...
Specifications
| Provider | Fireworks |
| Model ID | fireworks/ember-1 |
| Context window | 1.0M tokens (1,048,576) |
| Modalities | text + image → text |
| Tokenizer | Other |
| Router sources | OpenRouter, Vercel AI Gateway, Cloudflare |
| Released | 2026-09-24 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | On by default |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | fireworks/ember-1 | $3.00 | $15.00 | 1.0M |
| standard | Vercel AI Gateway | fireworks/ember-1 | $3.00 | $15.00 | 1.0M |
| standard | Cloudflare | fireworks/ember-1 | $3.00 | $15.00 | — |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $3.00 | $15.00 | — |
| 2026-11-14 | $3.00 | $15.00 | 1.0M |
| 2026-11-14 | $3.00 | $15.00 | 1.0M |
Capabilities
Vision (image input)Agentic tool useStructured outputsReasoning mode1M+ context windowControllable reasoningZero data retentionNo training on inputs (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p