Ultramarine 1 Flash Us
ultramarine-1-flash-usPricing
List prices at Fireworks AI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.15 | $0.50 | |
| Cached input 80% off input | $0.03 | 80% off input | |
| Priority 25% more | $0.188 | $0.625 | 25% more |
What it costs a month
At Fireworks AI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$71.70
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$61.20
- Coding agent1,000 requests a day, 40K in / 2K out, cached$109
- Overnight batch20,000 requests a day, 4K in / 0.4K out$480
Where to run it
1 host serve Ultramarine 1 Flash Us. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Fireworks AIInference ultramarine-1-flash-us | $0.15 / $0.50 | ultramarine-1-flash-us |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- TextImages
- Produces
- Text
- Features
- Prompt caching
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than Fireworks AI.
Smaller Independent models
No cheaper Independent model keeps its key capabilities.
Other frontier labs
- 16% less
- 16% less
Open-weight picks
- 3% less
- 25% less
- 40% less
- 41% less
Call it
Using Fireworks AI's API.
from litellm import completion
response = completion(
model="fireworks_ai/ultramarine-1-flash-us",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Ultramarine 1 Flash Us cost?
On Fireworks AI, Ultramarine 1 Flash Us costs $0.15 per million input tokens and $0.50 per million output tokens. Cached input costs $0.03 per million tokens.
Which APIs offer Ultramarine 1 Flash Us?
Ultramarine 1 Flash Us runs on 1 API: Fireworks AI.
What is Ultramarine 1 Flash Us's context window?
1M tokens, with up to 1M tokens in one reply.
Is Ultramarine 1 Flash Us being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Ultramarine 1 Flash Us?
Models that cost less and keep most of what it can do: Claude Haiku 5.5 on Anthropic (16% less), GPT-6 Luna on OpenAI (16% less) and Qwen3.8 Omni Flash on Alibaba DashScope (3% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Ultramarine 1 Flash Us's API model id?
Use ultramarine-1-flash-us with Fireworks AI.
Sources
Raw catalog entry for ultramarine-1-flash-us on Fireworks AI
{
"cache_read_input_token_cost": 3e-8,
"cache_read_input_token_cost_priority": 3.75e-8,
"input_cost_per_token": 1.5e-7,
"input_cost_per_token_priority": 1.875e-7,
"litellm_provider": "fireworks_ai",
"max_input_tokens": 1048576,
"max_output_tokens": 1048576,
"mode": "chat",
"output_cost_per_token": 5e-7,
"output_cost_per_token_priority": 6.25e-7,
"source": "https://docs.fireworks.ai/serverless/pricing.md",
"supports_function_calling": false,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_tool_choice": false,
"supports_vision": true
}