ByteScope

LLM Pricing

Per-million token rates, a cache-hit slider, and the day the card was checked.

The rate card is read in this tab. Nothing is uploaded and no model API is called.

Last updated 2026-09-22

USD / 1M tokens
chat-latestopenai5 USD30 USD0.5 USD——400,000 tokens128,000 tokens——Source
Claude Fable 5anthropic10 USD50 USD1 USD12.5 USD20 USD1,000,000 tokens128,000 tokens×0.5—Source
Claude Fable 5.1anthropic10 USD50 USD0.25 USD12.5 USD20 USD1,000,000 tokens128,000 tokens×0.5—Source
Claude Haiku 4.5anthropic1 USD5 USD0.1 USD1.25 USD2 USD200,000 tokens64,000 tokens×0.5—Source
Claude Mythos 5anthropic10 USD50 USD1 USD12.5 USD20 USD1,000,000 tokens128,000 tokens×0.5—Source
Claude Mythos 5.1anthropic10 USD50 USD0.25 USD12.5 USD20 USD1,000,000 tokens128,000 tokens×0.5—Source
Claude Opus 4.5anthropic5 USD25 USD0.5 USD6.25 USD10 USD200,000 tokens64,000 tokens×0.5—Source
Claude Opus 4.6anthropic5 USD25 USD0.5 USD6.25 USD10 USD1,000,000 tokens128,000 tokens×0.5—Source
Claude Opus 4.7anthropic5 USD25 USD0.5 USD6.25 USD10 USD1,000,000 tokens128,000 tokens×0.5—Source
Claude Opus 4.8anthropic5 USD25 USD0.5 USD6.25 USD10 USD1,000,000 tokens128,000 tokens×0.5—Source
Claude Opus 5anthropic5 USD25 USD0.5 USD6.25 USD10 USD1,000,000 tokens128,000 tokens×0.5—Source
Claude Sonnet 4.5anthropic3 USD15 USD0.3 USD3.75 USD6 USD200,000 tokens64,000 tokens×0.5—Source
Claude Sonnet 4.6anthropic3 USD15 USD0.3 USD3.75 USD6 USD1,000,000 tokens128,000 tokens×0.5—Source
Claude Sonnet 5anthropic2 USD10 USD0.2 USD2.5 USD4 USD1,000,000 tokens128,000 tokens×0.5—Source
Gemini 2.5 Flashgoogle0.3 USD2.5 USD0.03 USD——1,048,576 tokens65,536 tokens×0.5—Source
Gemini 2.5 Flash-Litegoogle0.1 USD0.4 USD0.01 USD——1,048,576 tokens65,536 tokens×0.5—Source
Gemini 2.5 Progoogle1.25 USD10 USD0.125 USD——1,048,576 tokens65,536 tokens×0.5YesSource
Gemini 3 Flash Previewgoogle0.5 USD3 USD0.05 USD——1,048,576 tokens65,536 tokens×0.5—Source
Gemini 3.1 Flash-Litegoogle0.25 USD1.5 USD0.025 USD——1,048,576 tokens65,536 tokens×0.5—Source
Gemini 3.1 Pro Previewgoogle2 USD12 USD0.2 USD——1,048,576 tokens65,536 tokens×0.5YesSource
Gemini 3.5 Flashgoogle1.5 USD9 USD0.15 USD——1,048,576 tokens65,536 tokens×0.5—Source
Gemini 3.5 Flash-Litegoogle0.3 USD2.5 USD0.03 USD——1,048,576 tokens65,536 tokens×0.5—Source
Gemini 3.6 Flashgoogle0.75 USD3.75 USD0.075 USD——1,048,576 tokens65,536 tokens×0.5—Source
Gemini 3.7 Flashgoogle0.75 USD3.75 USD0.075 USD——1,048,576 tokens65,536 tokens×0.5—Source
Gemini 3.8 Flashgoogle0.75 USD3.75 USD0.075 USD——1,048,576 tokens65,536 tokens×0.5—Source
Gemini Robotics ER 2 Previewgoogle1 USD5 USD0.1 USD——131,072 tokens65,536 tokens×0.5—Source
GPT-3.5 Turboopenai0.5 USD1.5 USD———16,385 tokens4,096 tokens×0.5—Source
GPT-3.5 Turbo (1106)openai1 USD2 USD———16,385 tokens4,096 tokens——Source
GPT-3.5 Turbo Instructopenai1.5 USD2 USD———4,096 tokens4,096 tokens——Source
GPT-4 (0613)openai30 USD60 USD———8,192 tokens8,192 tokens×0.5—Source
GPT-4 Turboopenai10 USD30 USD———128,000 tokens4,096 tokens×0.5—Source
GPT-4.1openai2 USD8 USD0.5 USD——1,047,576 tokens32,768 tokens×0.5—Source
GPT-4.1 miniopenai0.4 USD1.6 USD0.1 USD——1,047,576 tokens32,768 tokens×0.5—Source
GPT-4.1 nanoopenai0.1 USD0.4 USD0.025 USD——1,047,576 tokens32,768 tokens×0.5—Source
GPT-4oopenai2.5 USD10 USD1.25 USD——128,000 tokens16,384 tokens×0.5—Source
GPT-4o (2024-05-13)openai5 USD15 USD———128,000 tokens16,384 tokens×0.5—Source
GPT-4o miniopenai0.15 USD0.6 USD0.075 USD——128,000 tokens16,384 tokens×0.5—Source
GPT-5openai1.25 USD10 USD0.125 USD——400,000 tokens128,000 tokens×0.5—Source
GPT-5 miniopenai0.25 USD2 USD0.025 USD——400,000 tokens128,000 tokens×0.5—Source
GPT-5 nanoopenai0.05 USD0.4 USD0.005 USD——400,000 tokens128,000 tokens×0.5—Source
GPT-5 Proopenai15 USD120 USD———400,000 tokens272,000 tokens×0.5—Source
GPT-5.1openai1.25 USD10 USD0.125 USD——400,000 tokens128,000 tokens×0.5—Source
GPT-5.2openai1.75 USD14 USD0.175 USD——400,000 tokens128,000 tokens×0.5—Source
GPT-5.2 Proopenai21 USD168 USD———400,000 tokens128,000 tokens×0.5—Source
GPT-5.3 Codexopenai1.75 USD14 USD0.175 USD——400,000 tokens128,000 tokens×0.5—Source
GPT-5.4openai2.5 USD15 USD0.25 USD——1,050,000 tokens128,000 tokens×0.5YesSource
GPT-5.4 miniopenai0.75 USD4.5 USD0.075 USD——400,000 tokens128,000 tokens×0.5—Source
GPT-5.4 nanoopenai0.2 USD1.25 USD0.02 USD——400,000 tokens128,000 tokens×0.5—Source
GPT-5.4 Proopenai30 USD180 USD———1,050,000 tokens128,000 tokens×0.5YesSource
GPT-5.5openai5 USD30 USD0.5 USD——1,050,000 tokens128,000 tokens×0.5YesSource
GPT-5.5 Proopenai30 USD180 USD———1,050,000 tokens128,000 tokens×0.5YesSource
GPT-5.6 Cyberopenai12.5 USD75 USD1.25 USD15.625 USD—400,000 tokens128,000 tokens——Source
GPT-5.6 Lunaopenai0.2 USD1.2 USD0.02 USD0.25 USD—1,050,000 tokens128,000 tokens×0.5YesSource
GPT-5.6 Solopenai4 USD20 USD0.4 USD5 USD—1,050,000 tokens128,000 tokens×0.5YesSource
GPT-5.6 Terraopenai2 USD12 USD0.2 USD2.5 USD—1,050,000 tokens128,000 tokens×0.5YesSource
GPT-6 Astraopenai10 USD50 USD1 USD12.5 USD—1,050,000 tokens128,000 tokens×0.5YesSource
Grok 4.20 (0309) Non-Reasoningxai1.25 USD2.5 USD0.2 USD——1,000,000 tokens——YesSource
Grok 4.20 (0309) Reasoningxai1.25 USD2.5 USD0.2 USD——1,000,000 tokens——YesSource
Grok 4.20 Multi-Agent (0309)xai1.25 USD2.5 USD0.2 USD——1,000,000 tokens——YesSource
Grok 4.3xai1.25 USD2.5 USD0.2 USD——1,000,000 tokens——YesSource
Grok 4.5xai2 USD6 USD0.3 USD——500,000 tokens——YesSource
Grok 4.6xai2 USD6 USD0.5 USD——500,000 tokens——YesSource
Grok 4.7xai2 USD6 USD0.5 USD——500,000 tokens——YesSource
Grok Build 0.1xai1 USD2 USD0.2 USD——256,000 tokens——YesSource
o1openai15 USD60 USD7.5 USD——200,000 tokens100,000 tokens×0.5—Source
o1-proopenai150 USD600 USD———200,000 tokens100,000 tokens×0.5—Source
o3openai2 USD8 USD0.5 USD——200,000 tokens100,000 tokens×0.5—Source
o3-miniopenai1.1 USD4.4 USD0.55 USD——200,000 tokens100,000 tokens×0.5—Source
o3-proopenai20 USD80 USD———200,000 tokens100,000 tokens×0.5—Source
o4-miniopenai1.1 USD4.4 USD0.275 USD——200,000 tokens100,000 tokens×0.5—Source

Scenario

Models

anthropic

openai

google

xai

Cost

  • Gemini 3.8 Flash$1.03 USD
  • Grok 4.7$2.89 USD
  • Claude Sonnet 5$3.25 USD
  • GPT-5.6 Sol$6.50 USD

About this tool

The table is the checked rate card: input, output, cache read, a five-minute cache write, a one-hour cache write, the context window, max output when the card publishes one, the batch factor when it publishes one, and a mark when a long-context tier exists. An empty cell is a line the vendor did not publish. It is not a zero, and it is not a guess. Every number in the table is read from that card.

The calculator is the part a price list does not do. Pick one of the four scenarios, move the cache-hit slider, and tick the models you want side by side. One model from each vendor starts ticked. The totals come from the same cost function the model pages use. Batch is shown in the table and is not applied to the totals, because a batch job is a different purchase from the interactive loop.

Every rate here was confirmed on 2026-09-22, and the link on each row is the vendor page that confirmation used. A model that quotes a price without a date is how stale numbers spread. This page keeps that date with the numbers wherever they go, including the structured data and the Markdown copy.

Frequently asked questions

Why is the date above the table?

Prices on the open web go stale, and a model will repeat an old number without noticing. The date is when this card was last checked against each vendor's own page. The link on the row is that page.

Does the scenario include the batch discount?

No. Batch is a different way to buy the same tokens, shown as a factor when the card has one. The calculator prices the interactive loop. Folding the factor into the total would make the two purchases look like one.

What is the cache hit rate?

The share of the repeated context that is read from cache instead of written again. Zero means every turn writes the prefix. Ninety means most of it is a read. A card with no write price still accounts for the miss, billed as input, and says so.