You are about to ship a feature that calls GPT-5.5 per request. Walk through how you estimate the token cost before launch.

Attempt it

Free · 2 AI evals / day

Quick reference

TL;DR

Resolve encoding via `encoding_for_model('gpt-5.5')` (returns `o200k_base`), encode the full prompt (system + tools + user + per-message overhead), multiply by prices, and validate against `usage.prompt_tokens`.

Memory aid

Sign in for the mnemonic that makes this stick. See Pro pricing.

Easy to grasp

Think of an Uber ride. The fare is per mile, but the meter starts at pickup, not when you sit down at your destination. To estimate the fare you need to know the right rate card (which depends on the city), the actual distance the car will cover (not just the part you remember), and a way to check the estimate against the real receipt. Estimating API cost is the same. You pick the encoding for the specific model (the rate card), tokenize everything the API will send through the model (the full distance), and confirm against the response's usage field (the receipt).

Key concepts

tiktoken Token cost estimation o200k_base encoding

Quick scan · 2–4 min

Everything important, quickly.

5 min: resolve encoding by model, assemble the full prompt (system + tools + user + overhead), count input tokens, estimate output from a real sample, validate against `usage.prompt_tokens`, and adjust for the cached input discount.

Code example

python

import json
import tiktoken

# Step 1: resolve the encoding by model name
enc = tiktoken.encoding_for_model('gpt-5.5')  # o200k_base

# Step 2-3: assemble and count
system_msg = "You are a helpful assistant."
tool_schema = {"name": "search", "parameters": {"q": "string"}}
user_msg = "Find papers on RoPE scaling."

per_message_overhead = 3  # OpenAI chat completion accounting
input_tokens = (
    len(enc.encode(system_msg)) + per_message_overhead
    + len(enc.encode(json.dumps(tool_schema)))
    + len(enc.encode(user_msg)) + per_message_overhead
)

# Step 4: estimate output (use a measured median)
estimated_output_tokens = 400

# Step 5: cost (per 1k token prices in 2026; replace with current)
INPUT_PRICE = 0.0025
OUTPUT_PRICE = 0.010
estimated_cost = (
    input_tokens / 1000 * INPUT_PRICE
    + estimated_output_tokens / 1000 * OUTPUT_PRICE
)

# Validate: send a real call and compare usage.prompt_tokens to input_tokens

Side-by-side

Model family (2026)	Encoding	How to count input
GPT-5.5	o200k_base	`tiktoken.encoding_for_model('gpt-5.5')` + `.encode()`
GPT-4 era (4o, 4-turbo)	o200k_base / cl100k_base	Resolve via `encoding_for_model` per specific model
Claude Opus 4.7	Anthropic internal	`client.messages.count_tokens(...)`
Gemini 3.1 Pro	Google internal	`model.count_tokens(...)` on the Vertex SDK
Llama 4 / open weight	Model specific	`AutoTokenizer.from_pretrained(...).encode(text)`

Real-world examples

Real products, models, and research that use this idea.

OpenAI GPT-5.5: `tiktoken.encoding_for_model('gpt-5.5')` returns `o200k_base`; every response carries `usage.prompt_tokens` and `usage.completion_tokens`.
Anthropic Claude Opus 4.7: `client.messages.count_tokens(model='claude-opus-4-7', messages=[...])` returns the server side input token count without consuming a generation.
GitHub Copilot Chat surfaces per call token counts in its enterprise telemetry so admins can attribute cost per user.
LangSmith and Phoenix observability platforms record `prompt_tokens` and `completion_tokens` per trace and compute rolling per call cost from the published price table.

Interviewer follow-ups

What an interviewer would ask next. Try answering before peeking at the approach.

QIf your estimate disagrees with `usage.prompt_tokens` by 20 percent, what are the first three things you check?

Sign in or go Pro to see the approach for this follow-up.

QHow does the prompt cache discount change the per call math?

Sign in or go Pro to see the approach for this follow-up.

60-second cheat sheet

The night-before-the-interview bullets. Scan these on the way to the call.

Sign in for 5 unlocks/day or go Pro for unlimited revision sheets. See Pro pricing.

References

Primary sources. Skim if you want the original framing.