Model prices
Every price the analyser uses, in one table. USD per million tokens, first-party API, default routing. Transcribed by hand from published pricing pages and last verified 2026-10-27.
Cache-write columns are what a provider charges to place content in the prompt cache; cache-read is what it charges to reuse it. Where a provider publishes no write surcharge, writes are billed at the base input rate.
Anthropic
| Model | Input | Output | Cache read | Cache write | Context |
|---|---|---|---|---|---|
| Claude Fable 5.1 | $10 | $50 | $0.25 | $12.50 | 1,000k |
| Claude Opus 5.5 | $4 | $20 | $0.20 | $5 | 1,000k |
| Claude Sonnet 5.5 | $2 | $10 | $0.10 | $2.50 | 1,000k |
| Claude Haiku 5.5 | $0.10 | $0.50 | $0.010 | $0.13 | 1,000k |
| Claude Opus 5 | $5 | $25 | $0.50 | $6.25 | 1,000k |
| Claude Sonnet 5 | $2 | $10 | $0.20 | $2.50 | 1,000k |
| Claude Fable 5 | $10 | $50 | $1 | $12.50 | 1,000k |
| Claude Opus 4.8 | $5 | $25 | $0.50 | $6.25 | 1,000k |
| Claude Opus 4.7 | $5 | $25 | $0.50 | $6.25 | 1,000k |
| Claude Opus 4.6 | $5 | $25 | $0.50 | $6.25 | 1,000k |
| Claude Opus 4.5 | $5 | $25 | $0.50 | $6.25 | 200k |
| Claude Sonnet 4.6 | $3 | $15 | $0.30 | $3.75 | 1,000k |
| Claude Sonnet 4.5 | $3 | $15 | $0.30 | $3.75 | 200k |
| Claude Haiku 4.5 | $1 | $5 | $0.10 | $1.25 | 200k |
| Claude Opus 4.1superseded | $15 | $75 | $1.50 | $18.75 | 200k |
| Claude Haiku 3.5superseded | $0.80 | $4 | $0.080 | $1 | 200k |
OpenAI
| Model | Input | Output | Cache read | Cache write | Context |
|---|---|---|---|---|---|
| GPT-6 Astra | $10 | $50 | $1 | $12.50 | — |
| GPT-6.1 Sol | $2 | $10 | $0.10 | $2.50 | — |
| GPT-6.1 Terra | $1 | $5 | $0.050 | $1.25 | — |
| GPT-6 Sol | $2 | $10 | $0.20 | $2.50 | — |
| GPT-6 Luna | $0.10 | $0.50 | $0.010 | $0.13 | — |
| GPT-5.6 Sol | $4 | $20 | $0.40 | $5 | 1,050k |
| GPT-5.6 Terra | $2 | $12 | $0.20 | $2.50 | 1,050k |
| GPT-5.6 Luna | $0.20 | $1.20 | $0.020 | $0.25 | 1,050k |
| GPT-5.5 | $5 | $30 | $0.50 | — | — |
| GPT-5.5 Pro | $30 | $180 | — | — | — |
| GPT-5.4 | $2.50 | $15 | $0.25 | — | — |
| GPT-5.4 mini | $0.75 | $4.50 | $0.075 | — | — |
| GPT-5.4 nano | $0.20 | $1.25 | $0.020 | — | — |
| GPT-5.2 | $1.75 | $14 | $0.17 | — | — |
| GPT-5.1 | $1.25 | $10 | $0.13 | — | — |
| GPT-5 | $1.25 | $10 | $0.13 | — | — |
| GPT-5 mini | $0.25 | $2 | $0.025 | — | — |
| GPT-5 nano | $0.050 | $0.40 | $0.005 | — | — |
| GPT-4.1superseded | $2 | $8 | $0.50 | — | 1,047.576k |
| GPT-4.1 minisuperseded | $0.40 | $1.60 | $0.10 | — | 1,047.576k |
| GPT-4osuperseded | $2.50 | $10 | $1.25 | — | 128k |
| GPT-4o minisuperseded | $0.15 | $0.60 | $0.075 | — | 128k |
| Model | Input | Output | Cache read | Cache write | Context |
|---|---|---|---|---|---|
| Gemini 4 Argon | $2 | $10 | $0.10 | — | — |
| Gemini 3.8 Flash | $0.75 | $3.75 | $0.075 | — | — |
| Gemini 3.6 Flash | $0.75 | $3.75 | $0.075 | — | — |
| Gemini 3.5 Flashsuperseded | $1.50 | $9 | $0.15 | — | — |
| Gemini 3.5 Flash-Lite | $0.30 | $2.50 | $0.030 | — | — |
| Gemini 3.1 Pro Preview | $2 | $12 | $0.20 | — | — |
| Gemini 3.1 Flash-Lite | $0.25 | $1.50 | $0.025 | — | — |
| Gemini 3 Flash Previewsuperseded | $0.50 | $3 | $0.050 | — | — |
| Gemini 2.5 Prosuperseded | $1.25 | $10 | $0.13 | — | 1,048.576k |
| Gemini 2.5 Flashsuperseded | $0.30 | $2.50 | $0.030 | — | 1,048.576k |
| Gemini 2.5 Flash-Litesuperseded | $0.10 | $0.40 | $0.010 | — | 1,048.576k |
Two models can look the same price and cost you differently
Models count tokens differently. Claude models from Opus 4.7 onward produce roughly 30% more tokens for identical text than earlier ones, so two models at the same headline rate can differ meaningfully on the same prompt. To compare what you will actually pay, price your own prompt.
Compare on your prompt