Ultramarine 1 Flash Us API Pricing
- Input / output
- $0.15 / $0.50 per 1M tokens
- Cache read
- $0.03 / 1M
- Context
- 1M tokens
- Max output
- 1M tokens
As of November 21, 2026, Ultramarine 1 Flash Us costs $0.15 per 1M input tokens and $0.50 per 1M output tokens on Fireworks AI, with cache reads at $0.03 per 1M tokens. It has a 1,048,576-token context window and returns up to 1,048,576 tokens per response.
Ultramarine 1 Flash Us pricing by provider
1 listing across 1 provider. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.
| Provider | Model name in LiteLLM | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| Fireworks AI | fireworks_ai/accounts/fireworks/models/ultramarine-1-flash-us | $0.15 | $0.50 | $0.03 | 1M |
Other Ultramarine 1 Flash Us prices on Fireworks AI
| Priority input | $0.1875 per 1M tokens |
| Priority output | $0.625 per 1M tokens |
What Ultramarine 1 Flash Us costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| Fireworks AI | $0.55 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| Fireworks AI | $1.60 |
Ultramarine 1 Flash Us cost calculator
At Fireworks AI's price ($0.15 input, $0.50 output per 1M tokens), 10,000 requests a day with 1,000 input and 500 output tokens each cost $4.00 a day, about $120 a month. Change the numbers for your workload, or compare it with other models.
- Per request
- $0.0004
- Per day
- $4.00
- Per month (30 days)
- $120
Ultramarine 1 Flash Us features
Input: text, image. Output: text.
- Function calling
- Structured output
- Image input
- Prompt caching
Use Ultramarine 1 Flash Us with LiteLLM
Call Ultramarine 1 Flash Us through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.
from litellm import completion
response = completion(
model="fireworks_ai/accounts/fireworks/models/ultramarine-1-flash-us",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: ultramarine-1-flash-us
litellm_params:
model: fireworks_ai/accounts/fireworks/models/ultramarine-1-flash-us
api_key: os.environ/FIREWORKS_AI_API_KEYcurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $LITELLM_API_KEY" \
-d '{
"model": "ultramarine-1-flash-us",
"messages": [{"role": "user", "content": "Hello!"}]
}'Ultramarine 1 Flash Us price history
| Date | Price |
|---|---|
| October 30, 2026 | $0.225 / $0.75 per 1M tokens |
| November 4, 2026 | $0.15 / $0.50 per 1M tokens |
Ultramarine 1 Flash Us FAQ
How much does Ultramarine 1 Flash Us cost?
Ultramarine 1 Flash Us costs $0.15 per 1M input tokens and $0.50 per 1M output tokens on Fireworks AI, with cache reads at $0.03 per 1M tokens.
What is the context window of Ultramarine 1 Flash Us?
Ultramarine 1 Flash Us has a 1,048,576-token context window and returns up to 1,048,576 tokens per response.
Which providers offer Ultramarine 1 Flash Us?
Ultramarine 1 Flash Us is available from Fireworks AI through LiteLLM, using the model name fireworks_ai/accounts/fireworks/models/ultramarine-1-flash-us.
How do I call Ultramarine 1 Flash Us with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="fireworks_ai/accounts/fireworks/models/ultramarine-1-flash-us", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.
What features does Ultramarine 1 Flash Us support?
Ultramarine 1 Flash Us supports structured output, image input and prompt caching. It does not support function calling.
When did LiteLLM add Ultramarine 1 Flash Us?
Ultramarine 1 Flash Us was added to LiteLLM's model price file on October 30, 2026.
Sources
Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Maintainers update it from each provider's published pricing, and this page is usually rebuilt within 20 minutes of every change. Provider pricing pages:
LiteLLM docs: Fireworks AI.
Provider pages: Fireworks AI.