Pricing & Performance

Phaseo helps you make informed decisions about which models to use by providing transparent pricing and performance metrics for every model and provider. This page explains how Phaseo calculates, standardises, and presents cost and speed data — allowing you to identify the best value models for your use case.

Why pricing & performance matter

When choosing a model, you’re balancing three key factors:

💰 Price — how much each request costs.
⚙️ Performance — how fast and efficient the model is.
🧠 Quality — how well it performs on benchmarks.

Phaseo gives you clear, comparable metrics for the first two, and links them with benchmark data to help you find the sweet spot between cost, speed, and intelligence.

Pricing structure

Pricing varies depending on the provider, model type, and usage mode.
Phaseo normalises all prices to USD per 1,000 tokens (for text models) or the equivalent unit for other modalities.

Type	Unit	Example
Text Models	Per 1,000 tokens	$0.005 input /$ 0.015 output
Image Models	Per image	$0.02 per 1024×1024 image
Audio Models	Per minute or MB	$0.006 per minute of transcription
Video Models	Per second or frame	$0.01 per second of generated video
Embeddings	Per 1,000 tokens	$0.0001 per 1K tokens

Input vs Output pricing

For most text-based models, you’ll see two separate costs:

Input price — charged per 1,000 tokens you send (the prompt).
Output price — charged per 1,000 tokens the model generates.

Example:

Model	Input (USD / 1K tokens)	Output (USD / 1K tokens)
GPT-4o	$0.005	$0.015
Claude 3.5 Sonnet	$0.003	$0.015
Gemini 1.5 Pro	$0.00125	$0.005
Mistral Large	$0.002	$0.006

Phaseo displays both prices for full transparency and allows filtering or sorting by either.

Cost per request (E2E)

Phaseo also computes an estimated cost per complete request, which factors in:

The average number of input tokens per request.
The average model output length.
The current pricing structure for that provider.

This gives a more realistic “per-call” cost when comparing across models and providers.

Measuring performance

Phaseo tracks the following performance metrics for routed requests:

Metric	Description
Gateway TTFT	Gateway request start to the first content-bearing generated output. Metadata-only stream frames do not count.
Provider TTFT	Selected provider dispatch to the first content-bearing generated output.
Provider duration	Selected provider dispatch to the terminal response.
Gateway E2E	Gateway request start to completion.
Phaseo overhead	Gateway E2E minus provider duration.
Effective throughput	All output tokens divided by the full provider duration.
Output speed	Output tokens after the first divided by the provider time after TTFT.
TPOT / ITL	Request-level average time per token / inter-token latency after the first token.

TTFT, output speed, TPOT, and ITL are only reported when a streaming response exposes a content-bearing first output. Non-streaming responses retain duration and effective-throughput measurements without inventing a TTFT.

How we measure it

Phaseo aggregates operational requests routed through the gateway. These are production observations, not controlled benchmark runs. Performance views can be segmented by:

Streaming versus non-streaming responses.
Input context length buckets.
Provider route.
Cloudflare execution location.

Charts support P01, P05, P10, P25, P50, P75, P90, P95, and P99. P99 is the value at or below which 99% of observations fall. Lower latency is better; higher throughput is better, so lower throughput percentiles show the slow tail.

Interpreting performance

Scenario	What to look for
Interactive chatbots	Prioritise low latency (< 1s TTFT).
Large document summarisation	Focus on high throughput (tokens/sec).
Batch processing	Balance throughput and cost — consider cheaper models with slightly higher latency.
Real-time streaming	Requires providers that support streaming APIs and sub-second TTFT.

Use Phaseo’ performance charts to visualise these trade-offs interactively.

Example performance snapshot

This illustrative snapshot shows the shape of the performance data returned by the catalogue.

{
	"model": "gpt-4o",
	"provider": "OpenAI",
	"input_price_usd_per_1k": 0.005,
	"output_price_usd_per_1k": 0.015,
	"effective_throughput_tps": 420,
	"output_speed_tps": 510,
	"gateway_ttft_ms": 700,
	"provider_duration_ms": 3100,
	"phaseo_overhead_ms": 35,
	"tpot_ms": 1.96,
	"itl_ms": 1.96,
	"uptime_percent": 99.97
}

Cost-to-performance ratio

Phaseo calculates a cost-to-performance ratio (CPR) — a derived metric that helps identify the most efficient models. Formula: math CPR = (Cost per 1K tokens) / (Throughput in tokens/sec) Lower CPR values indicate better cost efficiency for the same throughput.

Data refresh frequency

Pricing and performance data are refreshed regularly:

Data Type	Update Frequency
Pricing	Every 24 hours
Performance	Every 6 hours
Benchmarks	Weekly or on new releases

Each update is timestamped and versioned for transparency.

Example use cases

Goal	Example
Compare models by speed	“Which model has the lowest latency?”
Find the best cost-per-token ratio	“Which model offers the best throughput for under $0.01/1K tokens?”
Identify regional variations	“Does latency differ between EU and US endpoints?”
Balance cost and performance	“What’s the most efficient model for real-time summarisation?”

Contributing or validating data

You can help by submitting verified pricing or performance updates through GitHub.
All submissions are reviewed before being included in the live dataset.

Contribute Pricing & Performance Data

Help maintain the accuracy of cost and performance data across providers.

Next steps

Now that you understand how pricing and performance are measured, you can explore how to integrate models programmatically via the Phaseo Gateway.

Integrate with the Gateway

Learn how to build using the Phaseo Gateway API.

Overview

Models & Routing

Features

Integrations

Workspace & Access

Reliability & Operations

Platform & Research

Migration Guides

Community

Pricing & Performance

Why pricing & performance matter

Pricing structure

Input vs Output pricing

Cost per request (E2E)

Measuring performance

How we measure it

Interpreting performance

Example performance snapshot

Cost-to-performance ratio

Data refresh frequency

Example use cases

Contributing or validating data

Contribute Pricing & Performance Data

Next steps

Integrate with the Gateway

​Why pricing & performance matter

​Pricing structure

​Input vs Output pricing

​Cost per request (E2E)

​Measuring performance

​How we measure it

​Interpreting performance

​Example performance snapshot

​Cost-to-performance ratio

​Data refresh frequency

​Example use cases

​Contributing or validating data

Contribute Pricing & Performance Data

​Next steps

Integrate with the Gateway

Why pricing & performance matter

Pricing structure

Input vs Output pricing

Cost per request (E2E)

Measuring performance

How we measure it

Interpreting performance

Example performance snapshot

Cost-to-performance ratio

Data refresh frequency

Example use cases

Contributing or validating data

Next steps