OpenRouter 模型 ↗ · 2026-09-24
fireworks/ember-1
模型发布 OpenRouter 模型 原文语言:中文
OpenRouter 于 2026-09-24 收录该模型(收录时间不等于模型正式发布日期);上下文:1,048,576 tokens;输入价:$3.0000/百万 tokens;输出价:$15.0000/百万 tokens;定位(来源描述):Ember-1 is a specialized reasoning model from Fireworks Research, built on [Kimi K3]( It is…
全文
Fireworks: Ember-1
fireworks/ember-1
Compare
Ember-1 is a specialized reasoning model from Fireworks Research, built on Kimi K3Opens in new tab. It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40% fewer tokens than the base model while maintaining comparable quality across Fireworks' evaluations. It is suited for coding, knowledge work, and agentic workflows where reasoning cost and latency matter.
Modalities
In / out price
$3 / $15per 1M
Context
1.0M
Released
Sep 24, 2026
Compare
Providers
This model is hosted by one provider. OpenRouter forwards every request without routing.
Latency / throughput
$3.00$15.00$0.300.55s79 tok/s
100.00%
ProviderInput / Output /M
Input $3.00 / Output $15.00
79 tok/s100.00% uptime
Pricing
The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.
Weighted average
Input
$1.634/M tokens
Output
$15/M tokens
Ember-1 — Price history
Price history
No effective price data for this selection
$1.63$15.0050.6%100.0%
ProviderInput / Output /M
Token share
Effective in $1.63 / Effective out $15.00
Token share
100.0%
Performance
Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).
Throughput
79tok/s
P50, best across providers
Latency
0.55s
P50, best provider
Reasoning effort
Uptime
Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.
Uptime (3d)The model was reachable. Request routed to a provider.
100.00%
Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.
99.79%
Availability over the last 3 days
Last 72 hours
Availability 99.79%
3 Days Ago2 Days AgoYesterdayNow
Availability over the last 24 hours
OpenRouter Availability
99.96%
When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.
Benchmarks
Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.
Benchmark score summary for Fireworks: Ember-1 (Vals AI)
SourceBenchmarkScore
Vals AIEmber-1 BioMysteryBench67.0%
Vals AIEmber-1 Code Migration32.5%
Vals AIEmber-1 CyberBench v1.169.5%
Vals AIEmber-1 EMB63.4%
Vals AIEmber-1 Finance Agent (v2)51.9%
Vals AIEmber-1 Harvey's Legal Agent Benchmark v19.2%
Vals AIEmber-1 IOI46.3%
Vals AIEmber-1 Legal Research Bench44.7%
Vals AIEmber-1 MysteryMechanism22.5%
Vals AIEmber-1 ProofBench v1.161.0%
Vals AIEmber-1 Public Benefits Bench v1.166.2%
Vals AIEmber-1 SAGE86.4%
Vals AIEmber-1 Vals Science Index31.8%
Vals AIEmber-1 Tax Agent Bench31.1%
Vals AIEmber-1 Terminal-Bench 4.020.7%
Vals AIEmber-1 Terminal-Bench-Science5.7%
Vals AIEmber-1 Vals Index50.9%
Vals AIEmber-1 Vibe Code Bench v1.183.9%
Apps
Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.
1.
Hermes Agent
Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.
2.63Btokens
2.
omp
new
189Mtokens
3.
pi
There are many coding agents, but this one is yours.
137Mtokens
4.
DeepSeek Harness
new
137Mtokens
5.
Traycer
new
53.6Mtokens
Rest of OpenRouter
13.7M
Top 5 Apps
182K
Activity
Token volume and request traffic to this model over time.
API
Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.
Not currently available through EU in-region routing. In-region routing docs
Frequently asked questions
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% fewer tokens than the base model while maintaining comparable quality across Fireworks' evaluations. It is suited for coding, knowledge work, and agentic workflows where reasoning cost and latency matter.
Ember-1 costs $3.00/M input tokens and $15.00/M output tokens, with separate rates for Cache Read at $0.30/M tokens.
Ember-1 has a 1,048,576 token context window.
Yes. Ember-1 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
Ember-1 accepts text and images as input and returns text.
Ember-1 is served by 1 provider on OpenRouter: Fireworks.
Ember-1 was released on September 24, 2026.
正文以来源语言显示。