LLM API cost · prices as of Oct 29, 2026

What will your AI feature cost per month?

Set your traffic and prompt sizes. Fourteen models are priced side by side, with long-context surcharges, batch discounts and the specs that decide whether a model fits.

Monthly bill range
$18$1,800/month

108M tokens a month. DeepSeek V4 Flash is the cheapest option; GPT-6 Astra costs 102× more.

Start from a common workload
Calls your app sends to the model
Prompt, history and context · 1,000 tokens ≈ 750 words
Reply length, including reasoning tokens
%
System prompts and documents reused across requests. Cache write fees are not included.
Providers
Must have
Bars use a log scale so cheap models stay visible.
DeepSeek V4 FlashCheapestDeepSeek · Budget · in $0.14 · out $0.28 per 1M · 1M context
$18<$0.01 per request
Claude Haiku 5.5Anthropic · Fast · in $0.10 · out $0.50 per 1M · 1M context
$18<$0.01 per request
GPT-6 LunaOpenAI · Fast · in $0.10 · out $0.50 per 1M · 1.05M context
$18<$0.01 per request
Llama 4 MaverickMeta · Mid · in $0.19 · out $0.65 per 1M · via OpenRouter · 524K context
$29<$0.01 per request
Gemini 3.5 Flash-LiteGoogle · Budget · in $0.30 · out $2.50 per 1M
$72<$0.01 per request
Qwen3.8-27BQwen · Mid · in $0.40 · out $3.00 per 1M · via OpenRouter (Chutes) · 262K context
$90<$0.01 per request
Gemini 3.8 FlashPromoGoogle · Workhorse · in $0.75 · out $3.75 per 1M · 1M context · Promo until Dec 31, 2026, then in $1.50 · out $7.50
$135<$0.01 per request
GPT-6.1 TerraOpenAI · Mid · in $1.00 · out $5.00 per 1M · 1.05M context
$180<$0.01 per request
DeepSeek V4 ProDeepSeek · Reasoning · in $1.74 · out $3.48 per 1M · 1.05M context
$219<$0.01 per request
Claude Sonnet 5.5Anthropic · Balanced · in $2.00 · out $10.00 per 1M · 1M context
$360<$0.01 per request
GPT-6.1 SolOpenAI · Balanced · in $2.00 · out $10.00 per 1M · 1.05M context
$360<$0.01 per request
Gemini 4 ArgonPromoGoogle · Flagship · in $2.00 · out $10.00 per 1M · 1M context · Promo until Nov 30, 2026, then in $4.00 · out $20.00
$360<$0.01 per request
Gemini 3.1 ProGoogle · Preview · in $2.00 · out $12.00 per 1M
$396<$0.01 per request
Claude Opus 5.5Anthropic · Flagship · in $4.00 · out $20.00 per 1M · 1M context
$720$0.01 per request
Claude Fable 5.1Anthropic · Frontier · in $10.00 · out $50.00 per 1M · 1M context
$1,800$0.03 per request
GPT-6 AstraOpenAI · Frontier · in $10.00 · out $50.00 per 1M · 1.05M context
$1,800$0.03 per request

Routing planner

Send simple requests to a cheap model and only the hard ones to a strong model. Uses your traffic, cache and batch settings above.

%
Routed bill$37480% on DeepSeek V4 Flash · 20% on GPT-6 Astra
Everything on GPT-6 Astra$1,800
You save$1,42679%
DeepSeek V4 Flash · $14GPT-6 Astra · $360

Assumes simple and hard requests use the same token sizes. Check answer quality on your own data before you switch.

LLM API price list

List prices per million tokens, standard rate, before batch or caching discounts.

ModelProvidersInput $/1MCached $/1MOutput $/1MContext
Claude Fable 5.1 Anthropic $10.00 $0.25 $50.00 1M
Claude Opus 5.5 Anthropic $4.00 $0.20 $20.00 1M
Claude Sonnet 5.5 Anthropic $2.00 $0.10 $10.00 1M
Claude Haiku 5.5 Anthropic $0.10 $0.01 $0.50 1M
DeepSeek V4 Pro DeepSeek $1.74 ? $3.48 1.05M
DeepSeek V4 Flash DeepSeek $0.14 $0.0028 $0.28 1M
Gemini 4 Argon Google $2.00 ? $10.00 1M
Gemini 3.1 Pro Google $2.00 ? $12.00 ?
Gemini 3.8 Flash Google $0.75 $0.08 $3.75 1M
Gemini 3.5 Flash-Lite Google $0.30 $0.03 $2.50 ?
Llama 4 Maverick Meta $0.19 ? $0.65 524K
GPT-6 Astra OpenAI $10.00 $1.00 $50.00 1.05M
GPT-6.1 Sol OpenAI $2.00 $0.10 $10.00 1.05M
GPT-6.1 Terra OpenAI $1.00 $0.05 $5.00 1.05M
GPT-6 Luna OpenAI $0.10 $0.01 $0.50 1.05M
Qwen3.8-27B Qwen $0.40 ? $3.00 262K