LLM Toolkit Model directory
All 22 models, one profile each
Every model we track, grouped by provider. Each profile page has verified per-token rates, the context window in human terms (words and pages), and what the model costs per month at three real workloads. All data verified as of 2026-09-02.
OpenAI
| Model | Input /1M | Output /1M | Context | Verified |
|---|---|---|---|---|
| GPT-5.6 Sol | $4.00 | $20.00 | 400K | 2026-09-02 |
| GPT-5.6 Terra | $2.00 | $12.00 | 400K | 2026-09-02 |
| GPT-5.6 Luna | $0.20 | $1.20 | 400K | 2026-09-02 |
| GPT-5.5 | $5.00 | $30.00 | 400K | 2026-08-26 |
| GPT-5.4 | $2.50 | $15.00 | 400K | 2026-08-26 |
| GPT-5.4 mini | $0.75 | $4.50 | 400K | 2026-08-26 |
| GPT-5.4 nano | $0.20 | $1.25 | 400K | 2026-08-26 |
| GPT-5.2 | $1.75 | $14.00 | 400K | 2026-08-26 |
| GPT-5 | $1.25 | $10.00 | 400K | 2026-08-26 |
| GPT-5 mini | $0.25 | $2.00 | 400K | 2026-08-26 |
| GPT-5 nano | $0.05 | $0.40 | 400K | 2026-08-26 |
| GPT-4o | $2.50 | $10.00 | 128K | 2026-08-26 |
| GPT-4o mini | $0.15 | $0.60 | 128K | 2026-08-26 |
| o3 | $2.00 | $8.00 | 200K | 2026-08-26 |
| o4-mini | $1.10 | $4.40 | 200K | 2026-08-26 |
Anthropic
| Model | Input /1M | Output /1M | Context | Verified |
|---|---|---|---|---|
| Claude Fable 5 | $10.00 | $50.00 | 1M | 2026-09-02 |
| Claude Opus 5 | $5.00 | $25.00 | 1M | 2026-09-02 |
| Claude Sonnet 5 | $2.00 | $10.00 | 1M | 2026-09-02 |
| Claude Haiku 4.5 | $1.00 | $5.00 | 200K | 2026-09-02 |
| Model | Input /1M | Output /1M | Context | Verified |
|---|---|---|---|---|
| Gemini 3.7 Flash | $0.75 | $3.75 | 1M | 2026-09-02 |
| Gemini 3.5 Flash | $1.50 | $9.00 | 1M | 2026-09-02 |
| Gemini 3.5 Flash-Lite | $0.30 | $2.50 | 1M | 2026-09-02 |
Frequently asked questions
How many LLM models does this site track?
22 models across OpenAI, Anthropic and Google — every one with input, cached input and output rates plus its context window. Each profile carries its own verification date from our pricing database, re-checked against official provider pages on the first of every month.
Which model is the cheapest right now?
GPT-5 nano at $0.05 per 1M input tokens and $0.40 per 1M output tokens, verified against OpenAI's official pricing page. Gemini 3.5 Flash-Lite is the cheapest Google option at $0.30 in / $2.50 out, and Claude Haiku 4.5 the cheapest Anthropic model at $1.00 in / $5.00 out.
Why do some models have the same price?
Providers often reuse pricing across generations — Claude Opus 5 and Opus 4.8 both cost $5.00 in / $25.00 out per 1M tokens. Promotional rates happen too: GPT-5.6 Sol runs $4.00 in / $20.00 out at least through Nov 21, 2026. When a provider changes rates, we update the whole affected family in one pass; every row shows the date it was last verified.
Keep exploring
All rates side by side on the Pricing Comparison, model-vs-model verdicts on the comparison hub, or your real numbers through the API Cost Calculator.