tinker-training-cost

tinker-training-cost is a skill for Claude Code, Codex from synthetic-sciences/openscience. It costs 55 tokens per session (1,823 once invoked), scanned A, original, Apache-2.0.

A calculator that estimates the price of fine-tuning an AI model with Tinker. It counts the tokens in a JSONL training dataset with the selected model’s tokenizer and applies that model’s current training rate.

In plain words
What is it for?
Use it to count dataset tokens, compare estimated costs across models, and estimate the price of different epoch counts before starting training.
Why use it?
It gives a cost estimate based on the actual dataset size and number of training passes instead of guessing from file size. JSONL is a line-by-line text format commonly used for training examples.

Skill for Claude CodeCodex

About the project

synthetic-sciences/openscience is an AI workbench that carries out scientific research by reading papers, forming hypotheses, writing and running code, conducting experiments, analyzing results, and preparing reports. Researchers use it for work in machine learning, biology, physics, and chemistry with remote or local models. Catalogue add-ons extend its scientific workflows through skills and instructions.

synthetic-sciences/openscience · 3,473 stars · on GitHub

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/synthetic-sciences/openscience/tinker-training-cost
Any agent
npx skills add synthetic-sciences/openscience --skill tinker-training-cost
Clone the repo
git clone --depth 1 https://github.com/synthetic-sciences/openscience

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for tinker-training-cost

README.md
[![agentmods](https://agentmods.dev/badge/skills/synthetic-sciences/openscience/tinker-training-cost.svg)](https://agentmods.dev/skills/synthetic-sciences/openscience/tinker-training-cost)
Your own site
<a href="https://agentmods.dev/skills/synthetic-sciences/openscience/tinker-training-cost"><img src="https://agentmods.dev/badge/skills/synthetic-sciences/openscience/tinker-training-cost.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,823 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00055 $0.01823
Opus 5 $0.00028 $0.00911
Sonnet 5 $0.00011 $0.00365
Haiku 4.5 $0.00006 $0.00182

Measured yesterday against content hash 6b06a4abcce9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tinker-training-cost scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/calculate_cost.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

backend/cli/skills/cloud-compute/tinker-training-cost/SKILL.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tinker Training Cost Calculator

Calculate training costs for Tinker fine-tuning jobs by tokenizing your dataset with the correct model tokenizer and applying current pricing.

Quick Start

Use the bundled script to calculate training costs:

# List available models and pricing
python scripts/calculate_cost.py --list-models

# Calculate cost for a JSONL dataset
python scripts/calculate_cost.py training_data.jsonl --model Qwen3-8B --epochs 3

# Output as JSON
python scripts/calculate_cost.py training_data.jsonl --model Llama-3.1-70B --json

The script:

  1. Loads the correct tokenizer for the selected model
  2. Counts tokens in your JSONL file (supports chat, text, and instruction formats)
  3. Calculates the estimated training cost

Cost Formula

Training Cost = (total_tokens × epochs × train_price_per_million) / 1_000_000

Where:

  • total_tokens = tokens in your training dataset (from tokenization)
  • epochs = number of training passes (default: 3)
  • train_price_per_million = model-specific training rate from pricing table

Tinker Pricing

All prices as of January 5, 2026 Source: https://thinkingmachines.ai/tinker/

All prices are in USD per million tokens.

Category Description
Prefill Processing input context (inference)
Sample Generating output tokens (inference)
Train Training/fine-tuning tokens

Qwen Models

Model Prefill Sample Train
Qwen3-4B-Instruct-2507 $0.07 $0.22 $0.22
Qwen3-8B $0.13 $0.40 $0.40
Qwen3-30B-A3B $0.12 $0.30 $0.36
Qwen3-VL-30B-A3B-Instruct $0.18 $0.44 $0.53
Qwen3-32B $0.49 $1.47 $1.47
Qwen3-235B-Instruct-2507 $0.68 $1.70 $2.04
Qwen3-VL-235B-A22B-Instruct $1.02 $2.56 $3.07

Llama Models

Model Prefill Sample Train
Llama-3.2-1B $0.03 $0.09 $0.09
Llama-3.2-3B $0.06 $0.18 $0.18
Llama-3.1-8B $0.13 $0.40 $0.40
Llama-3.1-70B $1.05 $3.16 $3.16

Read the full file on GitHub · 189 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 189 lines · 55 tokens per session scan A 6b06a4abcce9

Subscribe to this mod's changes

tinker-training-cost is a skill published in the GitHub repository synthetic-sciences/openscience (3,473 stars, last pushed today), licensed Apache-2.0. It adds 55 tokens to every session and 1,823 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.