Phi 3 Vision 128K Instruct
phi-3-vision-128k-instructPricing
List prices at Fireworks AI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.20 | $0.20 |
What it costs a month
At Fireworks AI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$75.00
- RAG over documents2,000 requests a day, 8K in / 0.6K out$103
- Coding agent1,000 requests a day, 40K in / 2K out$252
- Overnight batch20,000 requests a day, 4K in / 0.4K out$528
Where to run it
2 hosts serve Phi 3 Vision 128K Instruct. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Fireworks AIInference phi-3-vision-128k-instruct | $0.20 / $0.20 | phi-3-vision-128k-instruct | |
NVIDIA NIMInference phi-3-vision-128k-instruct | - | phi-3-vision-128k-instruct |
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
- Text
- Produces
- Text
- Open weights
- License: MITRuntimes: Ollama, llama.cpp, vLLM
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 Microsoft models
No cheaper Microsoft model keeps its key capabilities.
Other frontier labs
No cheaper match from another frontier lab.
Open-weight picks
- 10% less
- 11% less
- 20% less
- 25% less
Call it
Using Fireworks AI's API.
from litellm import completion
response = completion(
model="fireworks_ai/phi-3-vision-128k-instruct",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Phi 3 Vision 128K Instruct cost?
On Fireworks AI, Phi 3 Vision 128K Instruct costs $0.20 per million input tokens and $0.20 per million output tokens.
Which APIs offer Phi 3 Vision 128K Instruct?
Phi 3 Vision 128K Instruct runs on 2 APIs: Fireworks AI and NVIDIA NIM.
What is Phi 3 Vision 128K Instruct's context window?
32K tokens, with up to 32K tokens in one reply.
Is Phi 3 Vision 128K Instruct being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Phi 3 Vision 128K Instruct?
Models that cost less and keep most of what it can do: Qwen3.8 Flash on AIHubMix (10% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Phi 3 Vision 128K Instruct's API model id?
Use phi-3-vision-128k-instruct with Fireworks AI.
Sources
Raw catalog entry for phi-3-vision-128k-instruct on Fireworks AI
{
"max_input_tokens": 32064,
"max_output_tokens": 32064,
"input_cost_per_token": 2e-7,
"output_cost_per_token": 2e-7,
"litellm_provider": "fireworks_ai",
"mode": "chat"
}