OpenRouter: Fusion
openrouter/fusionFusion turns your prompt into a small multi-model deliberation.
Modalities
In / out per 1MVariable / Variable
Context1M
ReleasedJun 13, 2026
Pricing
List rates per 1M tokens — what Fusion costs pay-as-you-go elsewhere, not what you pay here.
Input
Variable
per 1M tokens
Output
Variable
per 1M tokens
Cache read
—
not published
Included in every pass
Fusion is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. Its upstream pricing is variable, so there is no fixed per-token rate to quote.
Performance
Time to first token and output speed across every provider.
No measurements published
This measurement has not been published for the model yet. It appears as soon as it is.
Uptime
Share of requests that at least one provider served successfully.
Last 3 days
Oct 11, 2:00 PMNow
Availability over the last 24 hours
100% 98% 97% 95%
Oct 13, 2:50 PMNow
Apps
Tools that most often run Fusion, by tokens this week.
No apps published
This measurement has not been published for the model yet. It appears as soon as it is.
Activity
Tokens processed market-wide.
No activity published
This measurement has not been published for the model yet. It appears as soon as it is.
FAQ
Which model id do I use for Fusion?
openrouter/fusion. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does Fusion hold?
1,000,000 tokens per request, prompt and response together.
What can it accept and return?
Input: text. Output: text.
What does Fusion cost on a pass?
Nothing beyond the pass itself. Its upstream pricing is variable, so no fixed per-token rate is published.
Who built Fusion?
OpenRouter, in the Fusion family.
Explore
Other models your pass can call.
