Tokely

THE COST OF BUILDING WITH AI

AI API price index

An exportable first-party dataset of enabled Tokely models, exact-model OpenRouter token references and supported media variants. Sources, units and dates are included.

Try in Playground Calculate your cost

Published by Tokely · Reviewed

THE SHORT ANSWER

This price index is operated by Tokely and includes Tokely's own rates. It compares enabled models with matching public references where available. It is a reproducible price dataset, not an independent market-wide cheapest-provider ranking.

Choose your cost model

Text API costs ↗

Input, output and cached-input tokens. Compare a matched workload.

39 enabled models

Image API costs ↗

Image variants, quality settings and reference requirements.

18 enabled models

Video API costs ↗

Clip duration, resolution and asynchronous generation jobs.

18 enabled models

Audio API costs ↗

Speech and music with their own published billing units.

3 enabled models

Download the evidence

JSON dataset ↓Text prices CSV ↓October snapshot report →

Tokely text rate date: 2026-10-09. Official references: 2026-10-05. OpenRouter reference check: 2026-10-09. Ownership and exclusions are included in the download.

Use the data, inspect the method

Download JSON for model IDs, input/output/cache-read prices, reference URLs and media units. CSV is available for text rates. The dataset excludes customer usage, supplier purchase costs and credentials. Link back to this index when citing its snapshot.

What this release measures

This release is a dated cross-sectional snapshot. It does not measure historical price changes, year-over-year trends, quality or uptime. Future reports can compare preserved snapshots only when the model version, tier and unit remain comparable.

Compare a matched text workload

USD per 1M tokens. Example: 1M uncached input + 250K output. Tokely rates dated 2026-10-09; OpenRouter references checked 2026-10-09. Platform/checkout fees, taxes, special units and context tiers excluded. Different models are not quality equivalents. Methodology.
ModelTokely input / outputTokely exampleOpenRouter exampleDifference vs OpenRouter
GPT-5.4 MiniOpenAI$0.07425 / $0.4455Cache read: $0.007425$0.185625$1.875$0.75 / $4.5 per 1M90.1% lower
Gemini 3.1 Flash LiteGoogle$0.050552 / $0.303312Cache read: $0.005056$0.12638$0.625$0.25 / $1.5 per 1M79.8% lower
Gemini 2.5 FlashGoogle$0.060663 / $0.505924Cache read: $0.006067$0.187144$0.925$0.3 / $2.5 per 1M79.8% lower
GPT-6 LunaOpenAI$0.09 / $0.45Cache read: $0.009$0.2025$0.225$0.1 / $0.5 per 1M10.0% lower
DeepSeek V4.1 FlashDeepSeek$0.135 / $0.54Cache read: $0.0027$0.27$0.6$0.3 / $1.2 per 1M55.0% lower
Gemini 3.7 FlashGoogle$0.151656 / $0.758279Cache read: $0.015166$0.341226$1.6875$0.75 / $3.75 per 1M79.8% lower
Gemini 3.8 FlashGoogle$0.151656 / $0.758279Cache read: $0.015166$0.341226$1.6875$0.75 / $3.75 per 1M79.8% lower
GPT-5 CodexOpenAI$0.126397 / $1.011175Cache read: $0.01264$0.379191Not matched—
GPT-5.6 LunaOpenAI$0.18 / $1.08Cache read: $0.018$0.45$0.5$0.2 / $1.2 per 1M10.0% lower
Gemini 3.5 Flash LiteGoogle$0.218386 / $1.819882Cache read: $0.021839$0.673357$0.925$0.3 / $2.5 per 1M27.2% lower
Grok 4.3Grok$0.505519 / $1.011038Cache read: $0.18$0.758279$1.875$1.25 / $2.5 per 1M59.6% lower
Gemini 3.5 FlashGoogle$0.303312 / $1.819868Cache read: $0.030332$0.758279$3.75$1.5 / $9 per 1M79.8% lower
GPT-6 SolOpenAI$0.505588 / $1.516763Cache read: $0.040447$0.884779$4.5$2 / $10 per 1M80.3% lower
GPT-6.1 SolOpenAI$0.505588 / $1.516763Cache read: $0.020224$0.884779$4.5$2 / $10 per 1M80.3% lower
GPT-5.6 TerraOpenAI$0.505588 / $1.820115Cache read: $0.040447$0.960617$5$2 / $12 per 1M80.8% lower
Claude Sonnet 5Anthropic$0.48532 / $2.4266Cache read: $0.048532$1.09197$4.5$2 / $10 per 1M75.7% lower
Gemini 2.5 ProGoogle$0.505519 / $3.033113Cache read: $0.050552$1.263797$3.75$1.25 / $10 per 1M66.3% lower
Grok 4.5Grok$0.80883 / $2.42649Cache read: $0.202208$1.415453$3.5$2 / $6 per 1M59.6% lower
Grok 4.6Grok$0.80883 / $2.42649Cache read: $0.202208$1.415453$3.5$2 / $6 per 1M59.6% lower
Grok 4.7Grok$0.80883 / $2.42649Cache read: $0.202208$1.415453$3.5$2 / $6 per 1M59.6% lower
Claude Sonnet 4.6Anthropic$0.72798 / $3.6399Cache read: $0.072798$1.637955$6.75$3 / $15 per 1M75.7% lower
GPT-5.2 CodexOpenAI$0.641667 / $5.133334Cache read: $0.064167$1.925001$5.25$1.75 / $14 per 1M63.3% lower
Gemini 3 ProGoogle$0.75 / $5.25Cache read: $0.75$2.0625Not matched—
GPT-5.5OpenAI$1.011175 / $4.550288Cache read: $0.101118$2.148747$12.5$5 / $30 per 1M82.8% lower
Claude Sonnet 5.5Anthropic$0.970585 / $4.852925Cache read: $0.097059$2.183816$4.5$2 / $10 per 1M51.5% lower
Claude Opus 5.5Anthropic$0.97064 / $4.8532Cache read: $0.048532$2.18394$9$4 / $20 per 1M75.7% lower
Gemini 3.1 ProGoogle$0.833334 / $5.833334Cache read: $0.18$2.291668Not matched—
GPT-5.6 SolOpenAI$1.263969 / $4.550288Cache read: $0.101118$2.401541$4.5$2 / $10 per 1M46.6% lower
GPT-5.1 CodexOpenAI$1.008334 / $8.066667Cache read: $0.100834$3.025001$3.75$1.25 / $10 per 1M19.3% lower
Kimi K3Moonshot$0.45 / $10.8Cache read: $0.27$3.15$3.5$0.5 / $12 per 1M10.0% lower
GPT-5.3 CodexOpenAI$1.05875 / $8.47Cache read: $0.105875$3.17625$5.25$1.75 / $14 per 1M39.5% lower
GPT-6 AstraOpenAI$2.527938 / $7.583813Cache read: $0.202235$4.423891$22.5$10 / $50 per 1M80.3% lower
GPT-5.2OpenAI$1.575 / $12.6Cache read: $0.1575$4.725$5.25$1.75 / $14 per 1M10.0% lower
Claude Opus 4.6Anthropic$2.426463 / $12.132313Cache read: $0.242647$5.459541$11.25$5 / $25 per 1M51.5% lower
Claude Opus 4.8Anthropic$2.426463 / $12.132313Cache read: $0.242647$5.459541$11.25$5 / $25 per 1M51.5% lower
Claude Opus 5Anthropic$2.426463 / $12.132313Cache read: $0.242647$5.459541$11.25$5 / $25 per 1M51.5% lower
GPT-5.4OpenAI$2.25 / $13.5Cache read: $0.225$5.625$6.25$2.5 / $15 per 1M10.0% lower
Claude Opus 4.7Anthropic$3.033079 / $12.132313Cache read: $0.242647$6.066157$11.25$5 / $25 per 1M46.1% lower
Claude Fable 5Anthropic$4.852925 / $24.264625Cache read: $0.485293$10.919081$22.5$10 / $50 per 1M51.5% lower

Change the token mix in the calculator →

Questions before you switch

Is this an independent price comparison site?

No. Tokely publishes this index and operates the API service being compared. The ownership, scope and source dates are disclosed so you can evaluate the data.

How often do prices update?

The rate data is versioned with the site. External-reference dates and Tokely rate dates are shown separately. This release has no automatic daily external-price refresh; the checked-in refresh script prepares a reviewable update.

Keep exploring

AI API pricing. Know what you pay. ↗

Published Tokely rates for text, images, video and audio. Pay from one USD balance, compare exact models and estimate your workload before you switch.

A cost-focused OpenRouter alternative ↗

Compare exact-model rates, supported endpoints and migration requirements before moving to Tokely. One balance for supported text, image, video and audio models.

OpenRouter migration checklist · Billing documentation

START WITH YOUR OWN WORKLOAD

Know the price.
Then make the call.

Check the model, compare the rate, and connect with a Tokely key.

Read the quickstart ↗Explore all models →