LLM API pricing comparison
List prices of GPT, Claude, Gemini, DeepSeek and more, per 1 million tokens
Every provider prices its models per token, but each in its own table. This page puts the public list prices side by side: input and output price per 1 million tokens, cached input, context window and what each model can do. Enter your own usage in the calculator to see the monthly cost per model.
Cheapest model
Nemotron 3 Nano 30B
NVIDIA
$0.0875 per 1M tokens, blended 3:1
Cheapest with vision
Gemma 4 26B A4B IT
Google Gemini
$0.1425 per 1M tokens, blended 3:1
Cheapest reasoning model
Nemotron 3 Nano 30B
NVIDIA
$0.0875 per 1M tokens, blended 3:1
Largest context window
GPT 5.4
OpenAI
1.1M tokens of context
Cost calculator
Enter your average request and monthly volume. The last column shows what each model would cost per month.
Presety:
| Model | Poskytovatel | Vstup na 1M tokenů |
Výstup na 1M tokenů |
Cached input na 1M tokenů |
Kontext | Schopnosti | Per month your scenario |
|---|---|---|---|---|---|---|---|
Nemotron 3 Nano 30B
nvidia/nvidia/nemotron-3-nano-30b-a3b |
NVIDIA | $0.05 | $0.20 | $0.025 | 262K | Nástroje Uvažování | $1.30 |
DeepSeek V4 Flash
deepseek/deepseek-v4-flash |
DeepSeek | $0.088606 | $0.177212 | $0.017721 | 1M | Nástroje Uvažování | $1.59 |
GPT OSS 20B
groq/openai/gpt-oss-20b |
Groq | $0.075 | $0.30 | $0.0375 | 131K | Nástroje Uvažování | $1.95 |
Gemma 4 26B A4B IT
google/gemma-4-26b-a4b-it |
Google Gemini | $0.09 | $0.30 | $0.05 | 262K | Vize Nástroje Uvažování | $2.10 |
Gemma 4 31B IT
google/gemma-4-31b-it |
Google Gemini | $0.09 | $0.34 | $0.05 | 262K | Vize Nástroje Uvažování | $2.26 |
Nemotron 3 Super 120B
nvidia/nvidia/nemotron-3-super-120b-a12b |
NVIDIA | $0.08 | $0.45 | $0.06 | 262K | Nástroje Uvažování | $2.60 |
GPT OSS 120B
groq/openai/gpt-oss-120b |
Groq | $0.15 | $0.60 | $0.075 | 131K | Nástroje Uvažování | $3.90 |
Magistral Small
mistral/magistral-small-latest |
Mistral | $0.15 | $0.60 | $0.015 | 262K | Vize Nástroje Uvažování | $3.90 |
Mistral Small
mistral/mistral-small-latest |
Mistral | $0.15 | $0.60 | $0.015 | 262K | Vize Nástroje Uvažování | $3.90 |
GLM 4.5 Air
zai/glm-4.5-air |
Z.AI | $0.13 | $0.85 | $0.025 | 131K | Nástroje Uvažování | $4.70 |
deepseek-v4-flash-vision-exp
deepseek/deepseek-v4-flash-vision-exp |
DeepSeek | $0.22 | $0.66 | $0.007 | 1M | Vize Nástroje Uvažování | $4.84 |
Llama 3.3 Nemotron Super 49B
nvidia/nvidia/llama-3.3-nemotron-super-49b-v1.5 |
NVIDIA | $0.40 | $0.40 | 131K | Nástroje Uvažování | $5.60 | |
MiniMax-M2
minimax/MiniMax-M2 |
MiniMax | $0.255 | $1.02 | $0.03 | 205K | Nástroje Uvažování | $6.63 |
GPT 5.4 Nano
openai/gpt-5.4-nano |
OpenAI | $0.20 | $1.25 | $0.02 | 400K | Vize Nástroje Uvažování | $7.00 |
MiniMax-M2.5
minimax/MiniMax-M2.5 |
MiniMax | $0.27 | $1.08 | $0.027 | 205K | Nástroje Uvažování | $7.02 |
MiniMax-M2.1
minimax/MiniMax-M2.1 |
MiniMax | $0.30 | $1.20 | $0.03 | 205K | Nástroje Uvažování | $7.80 |
MiniMax-M2.7
minimax/MiniMax-M2.7 |
MiniMax | $0.30 | $1.20 | $0.06 | 205K | Nástroje Uvažování | $7.80 |
MiniMax-M3
minimax/MiniMax-M3 |
MiniMax | $0.30 | $1.20 | $0.06 | 1M | Vize Nástroje Uvažování | $7.80 |
GPT 5.5
yunwu/gpt-5.5 |
Yunwu | $0.30 | $1.50 | Nástroje | $9.00 | ||
Moonshot V1 8K
moonshot/moonshot-v1-8k |
Moonshot | $0.20 | $2.00 | 8K | Nástroje | $10.00 | |
GPT 4.1 Mini
openai/gpt-4.1-mini |
OpenAI | $0.40 | $1.60 | $0.10 | 1M | Vize Nástroje | $10.40 |
GLM 4.7
zai/glm-4.7 |
Z.AI | $0.40 | $1.75 | $0.08 | 205K | Nástroje Uvažování | $11.00 |
GPT 3.5 Turbo
openai/gpt-3.5-turbo |
OpenAI | $0.50 | $1.50 | 16K | Nástroje | $11.00 | |
Mistral Large
mistral/mistral-large-latest |
Mistral | $0.50 | $1.50 | $0.05 | 262K | Vize Nástroje | $11.00 |
mistral-large-2512
mistral/mistral-large-2512 |
Mistral | $0.50 | $1.50 | $0.05 | 262K | Vize Nástroje | $11.00 |
GLM 4.6
zai/glm-4.6 |
Z.AI | $0.43 | $1.75 | $0.08 | 205K | Nástroje Uvažování | $11.30 |
Devstral
mistral/devstral-latest |
Mistral | $0.40 | $2.00 | 256K | Nástroje | $12.00 | |
Devstral Medium
mistral/devstral-medium-latest |
Mistral | $0.40 | $2.00 | 256K | Nástroje | $12.00 | |
Gemini Flash-Lite Latest
google/gemini-flash-lite-latest |
Google Gemini | $0.30 | $2.50 | $0.03 | 1M | Vize Nástroje Uvažování | $13.00 |
GLM 5
zai/glm-5 |
Z.AI | $0.60 | $1.92 | $0.12 | 205K | Nástroje Uvažování | $13.68 |
Perplexity Sonar
sonar |
Perplexity | $1.00 | $1.00 | 127K | $14.00 | ||
GLM 4.5
zai/glm-4.5 |
Z.AI | $0.60 | $2.20 | $0.11 | 131K | Nástroje Uvažování | $14.80 |
Grok Build 0.1
xai/grok-build-0.1 |
xAI | $1.00 | $2.00 | $0.20 | 256K | Vize Nástroje Uvažování | $18.00 |
Kimi 2.5
moonshot/kimi-k2.5 |
Moonshot | $0.60 | $3.00 | $0.10 | 262K | Vize Nástroje Uvažování | $18.00 |
Qwen/Qwen3.6-27B
groq/qwen/qwen3.6-27b |
Groq | $0.60 | $3.00 | 131K | Vize Nástroje Uvažování | $18.00 | |
Nemotron 3 Ultra 550B
nvidia/nvidia/nemotron-3-ultra-550b-a55b |
NVIDIA | $0.625 | $3.13 | $0.1875 | 262K | Nástroje Uvažování | $18.75 |
GLM 5.1
zai/glm-5.1 |
Z.AI | $0.966 | $3.04 | $0.1794 | 205K | Nástroje Uvažování | $21.80 |
Moonshot V1 32K
moonshot/moonshot-v1-32k |
Moonshot | $1.00 | $3.00 | 33K | Nástroje | $22.00 | |
Gemini Flash Latest
google/gemini-flash-latest |
Google Gemini | $0.75 | $3.75 | $0.075 | 1M | Vize Nástroje Uvažování | $22.50 |
Grok 4.3
xai/grok-4.3 |
xAI | $1.25 | $2.50 | $0.20 | 1M | Vize Nástroje Uvažování | $22.50 |
GPT 5.4 Mini
openai/gpt-5.4-mini |
OpenAI | $0.75 | $4.50 | $0.075 | 400K | Vize Nástroje Uvažování | $25.50 |
Kimi 2.6
moonshot/kimi-k2.6 |
Moonshot | $0.95 | $4.00 | $0.16 | 262K | Vize Nástroje Uvažování | $25.50 |
GLM 5 Turbo
zai/glm-5-turbo |
Z.AI | $1.20 | $4.00 | $0.24 | 203K | Nástroje Uvažování | $28.00 |
DeepSeek V4 Pro
deepseek/deepseek-v4-pro |
DeepSeek | $1.60 | $3.20 | $0.135 | 1M | Nástroje Uvažování | $28.80 |
Claude Haiku 4.5
anthropic/claude-haiku-4-5-20251001 |
Anthropic | $1.00 | $5.00 | $0.10 | 200K | Vize Nástroje Uvažování | $30.00 |
GLM 5.2
zai/glm-5.2 |
Z.AI | $1.40 | $4.40 | $0.14 | 1M | Nástroje Uvažování | $31.60 |
Moonshot V1 128k
moonshot/moonshot-v1-128k |
Moonshot | $2.00 | $5.00 | 131K | Nástroje | $40.00 | |
Moonshot V1 Auto
moonshot/moonshot-v1-auto |
Moonshot | $2.00 | $5.00 | 131K | Nástroje | $40.00 | |
Mistral Medium
mistral/mistral-medium-latest |
Mistral | $1.50 | $7.50 | $0.15 | 262K | Vize Nástroje Uvažování | $45.00 |
Perplexity Sonar Deep Research
sonar-deep-research |
Perplexity | $2.00 | $8.00 | 127K | $52.00 | ||
Perplexity Sonar Reasoning Pro
sonar-reasoning-pro |
Perplexity | $2.00 | $8.00 | 127K | $52.00 | ||
GPT 5.1
openai/gpt-5.1 |
OpenAI | $1.25 | $10.00 | $0.125 | 400K | Vize Nástroje Uvažování | $52.50 |
Claude Sonnet 5
anthropic/claude-sonnet-5 |
Anthropic | $2.00 | $10.00 | $0.20 | 1M | Vize Nástroje Uvažování | $60.00 |
Nano Banana Pro
google/gemini-3-pro-image |
Google Gemini | $2.00 | $12.00 | $0.20 | 131K | Vize Nástroje Uvažování | $68.00 |
Claude Opus 4.8
yunwu/claude-opus-4-8 |
Yunwu | $2.50 | $12.00 | $0.30 | Vize Nástroje | $73.00 | |
GPT 5.2
openai/gpt-5.2 |
OpenAI | $1.75 | $14.00 | $0.175 | 400K | Vize Nástroje Uvažování | $73.50 |
GPT 5.4
openai/gpt-5.4 |
OpenAI | $2.50 | $15.00 | $0.25 | 1.1M | Vize Nástroje Uvažování | $85.00 |
Claude Sonnet 4.6
anthropic/claude-sonnet-4-6 |
Anthropic | $3.00 | $15.00 | $0.30 | 1M | Vize Nástroje Uvažování | $90.00 |
claude-sonnet-5
yunwu/claude-sonnet-5 |
Yunwu | $3.00 | $15.00 | $0.30 | Vize | $90.00 | |
Kimi 3
moonshot/kimi-k3 |
Moonshot | $3.00 | $15.00 | $0.30 | 1M | Vize Nástroje Uvažování | $90.00 |
Perplexity Sonar Pro
sonar-pro |
Perplexity | $3.00 | $15.00 | 127K | $90.00 | ||
Claude Fable 5
yunwu/claude-fable-5 |
Yunwu | $5.00 | $25.00 | $1.00 | Nástroje Uvažování | $150.00 | |
Claude Opus 4.6
anthropic/claude-opus-4-6 |
Anthropic | $5.00 | $25.00 | $0.50 | 1M | Vize Nástroje Uvažování | $150.00 |
Claude Opus 4.7
anthropic/claude-opus-4-7 |
Anthropic | $5.00 | $25.00 | $0.50 | 1M | Vize Nástroje Uvažování | $150.00 |
Claude Opus 4.8
anthropic/claude-opus-4-8 |
Anthropic | $5.00 | $25.00 | $0.50 | 1M | Vize Nástroje Uvažování | $150.00 |
Claude Opus 5
anthropic/claude-opus-5 |
Anthropic | $5.00 | $25.00 | $0.50 | 1M | Vize Nástroje Uvažování | $150.00 |
GPT 5.5
openai/gpt-5.5 |
OpenAI | $5.00 | $30.00 | $0.50 | 1.1M | Vize Nástroje Uvažování | $170.00 |
GPT Image 2
openai/gpt-image-2 |
OpenAI | $5.00 | $30.00 | $1.25 | Vize | $170.00 | |
GPT Image 1.5
openai/gpt-image-1.5 |
OpenAI | $5.00 | $32.00 | $1.25 | Vize | $178.00 | |
GPT Image 1
openai/gpt-image-1 |
OpenAI | $5.00 | $40.00 | $1.25 | $210.00 | ||
Claude Fable 5
anthropic/claude-fable-5 |
Anthropic | $10.00 | $50.00 | $1.00 | 1M | Vize Nástroje Uvažování | $300.00 |
GPT 5.5 Pro
openai/gpt-5.5-pro |
OpenAI | $30.00 | $180.00 | $3.00 | 1.1M | Vize Nástroje Uvažování | $1,020.00 |
Vašemu hledání neodpovídají žádné modely.
List prices in USD per 1 million tokens as published by the providers, without volume or batch discounts. Prices as of čtvrtek 17. září 2026.
How LLM API pricing works
Four things to know before comparing numbers.
-
01
Tokens, not words
Models read and write tokens, pieces of about four characters. 1 million tokens is roughly 750,000 English words; German and Czech need a few more tokens per word.
-
02
Input and output are priced separately
Reading your prompt is cheap, generating the answer is expensive. Output tokens usually cost three to five times more than input tokens.
-
03
Cached input is cheaper
If the same long prefix (system prompt, document, chat history) is sent again and again, providers reuse it and bill those tokens at a fraction of the input price.
-
04
Reasoning tokens count as output
Reasoning models think before they answer. The hidden thinking tokens are billed as output, so a single request can cost several times more than the list price suggests.
Často kladené otázky
Short answers on tokens, prices and how this table is built.
A short question with a short answer uses about 500 to 1,500 tokens in total. On a mid-priced model that is a fraction of a cent. Long documents, large code files and reasoning models push a single request into the cent range.
The highlights at the top show the cheapest model overall, with vision and with reasoning, based on a 3:1 mix of input and output tokens. Cheapest is not always most economical: a small model may need more retries and longer prompts on hard tasks. Use the calculator with your real token counts.
From the providers' public price lists, synchronized regularly. They are on-demand list prices in USD per 1 million tokens, without volume, batch or regional discounts. The date below the table shows the last update. Check the provider's page before a purchase decision.
The prices on this page are the providers' list prices. Our own prices per model are on the pricing page. They include one account for every provider, invoicing with VAT, prepaid credit with no minimum spend and cost tracking to the cent.
Keep system prompts short, cap the maximum output length, route simple tasks to a small model and reserve large or reasoning models for the hard ones. Prompt caching pays off as soon as the same prefix is sent repeatedly, and batch APIs are often half price for jobs that can wait.
Not in the list prices. Some providers offer batch processing at around half price for asynchronous jobs, and enterprise contracts with negotiated rates. This page shows the standard on-demand prices everybody gets.
Every model on this page, one account
One credit for all providers, billed to the cent. No credit card to start.