LLM API price reference

Claude Fable 5

input: $10 / 1M tokens

cached input: $1 / 1M tokens

output: $50 / 1M tokens

Claude Fable 5.1

input: $10 / 1M tokens

cached input: $0.25 / 1M tokens

output: $50 / 1M tokens

Claude Haiku 4.5

input: $1 / 1M tokens

cached input: $0.1 / 1M tokens

output: $5 / 1M tokens

Claude Mythos 5

input: $10 / 1M tokens

cached input: $1 / 1M tokens

output: $50 / 1M tokens

Claude Opus 4.5

input: $5 / 1M tokens

cached input: $0.5 / 1M tokens

output: $25 / 1M tokens

Claude Opus 4.6

input: $5 / 1M tokens

cached input: $0.5 / 1M tokens

output: $25 / 1M tokens

Claude Opus 4.7

input: $5 / 1M tokens

cached input: $0.5 / 1M tokens

output: $25 / 1M tokens

Claude Opus 4.8

input: $5 / 1M tokens

cached input: $0.5 / 1M tokens

output: $25 / 1M tokens

Claude Opus 5

input: $5 / 1M tokens

cached input: $0.5 / 1M tokens

output: $25 / 1M tokens

Claude Opus 5.5

input: $4 / 1M tokens

cached input: $0.2 / 1M tokens

output: $20 / 1M tokens

Claude Sonnet 4.5

input: $3 / 1M tokens

cached input: $0.3 / 1M tokens

output: $15 / 1M tokens

Claude Sonnet 4.6

input: $3 / 1M tokens

cached input: $0.3 / 1M tokens

output: $15 / 1M tokens

Claude Sonnet 5

input: $2 / 1M tokens

cached input: $0.2 / 1M tokens

output: $10 / 1M tokens

Claude Sonnet 5.5

input: $2 / 1M tokens

cached input: $0.2 / 1M tokens

output: $10 / 1M tokens

DeepSeek-V4-Flash

peak

input: $0.3 / 1M tokens

cached input: $0.006 / 1M tokens

output: $1.2 / 1M tokens

DeepSeek-V4-Flash

off-peak

input: $0.15 / 1M tokens

cached input: $0.003 / 1M tokens

output: $0.6 / 1M tokens

DeepSeek-V4-Flash-Vision-Exp

peak

input: $0.3 / 1M tokens

cached input: $0.006 / 1M tokens

output: $1.2 / 1M tokens

DeepSeek-V4-Flash-Vision-Exp

off-peak

input: $0.15 / 1M tokens

cached input: $0.003 / 1M tokens

output: $0.6 / 1M tokens

DeepSeek-V4-Pro

peak

input: $1.32 / 1M tokens

cached input: $0.044 / 1M tokens

output: $3.96 / 1M tokens

DeepSeek-V4-Pro

off-peak

input: $0.66 / 1M tokens

cached input: $0.022 / 1M tokens

output: $1.98 / 1M tokens

Gemini 2.5 Flash

input: $0.3 / 1M tokens

cached input: $0.03 / 1M tokens

output: $2.5 / 1M tokens

Gemini 2.5 Flash-Lite

input: $0.1 / 1M tokens

cached input: $0.01 / 1M tokens

output: $0.4 / 1M tokens

Gemini 2.5 Pro

up-to-200k

Prompt length up to 200,000 tokens

input: $1.25 / 1M tokens

cached input: $0.125 / 1M tokens

output: $10 / 1M tokens

Gemini 2.5 Pro

over-200k

Prompt length over 200,000 tokens

input: $2.5 / 1M tokens

cached input: $0.25 / 1M tokens

output: $15 / 1M tokens

Gemini 3 Flash Preview

input: $0.5 / 1M tokens

cached input: $0.05 / 1M tokens

output: $3 / 1M tokens

Gemini 3.1 Flash-Lite

input: $0.25 / 1M tokens

cached input: $0.025 / 1M tokens

output: $1.5 / 1M tokens

Gemini 3.1 Pro Preview

up-to-200k

Prompt length up to 200,000 tokens

input: $2 / 1M tokens

cached input: $0.2 / 1M tokens

output: $12 / 1M tokens

Gemini 3.1 Pro Preview

over-200k

Prompt length over 200,000 tokens

input: $4 / 1M tokens

cached input: $0.4 / 1M tokens

output: $18 / 1M tokens

Gemini 3.5 Flash

input: $1.5 / 1M tokens

cached input: $0.15 / 1M tokens

output: $9 / 1M tokens

Gemini 3.5 Flash-Lite

input: $0.3 / 1M tokens

output: $2.5 / 1M tokens

Gemini 3.6 Flash

input: $1.5 / 1M tokens

cached input: $0.15 / 1M tokens

output: $7.5 / 1M tokens

Gemini 3.7 Flash

introductory

Introductory pricing through 2026-12-31

input: $0.75 / 1M tokens

cached input: $0.075 / 1M tokens

output: $3.75 / 1M tokens

Gemini 3.7 Flash

from-2027-01-01

Effective from 2027-01-01

input: $1.5 / 1M tokens

cached input: $0.15 / 1M tokens

output: $7.5 / 1M tokens

Gemini 3.8 Flash

introductory

Introductory pricing through 2026-12-31

input: $0.75 / 1M tokens

cached input: $0.075 / 1M tokens

output: $3.75 / 1M tokens

Gemini 3.8 Flash

from-2027-01-01

Effective from 2027-01-01

input: $1.5 / 1M tokens

cached input: $0.15 / 1M tokens

output: $7.5 / 1M tokens

Kimi K2.6

input: $0.95 / 1M tokens

cached input: $0.16 / 1M tokens

output: $4 / 1M tokens

Kimi K2.7 Code

input: $0.95 / 1M tokens

cached input: $0.19 / 1M tokens

output: $4 / 1M tokens

Kimi K2.7 Code HighSpeed

input: $1.9 / 1M tokens

cached input: $0.38 / 1M tokens

output: $8 / 1M tokens

Kimi K3

input: $3 / 1M tokens

cached input: $0.3 / 1M tokens

output: $15 / 1M tokens

GLM 5.3

input: $1.4 / 1M tokens

cached input: $0.14 / 1M tokens

output: $4.4 / 1M tokens

Ministral 3 14B

input: $0.2 / 1M tokens

cached input: $0.02 / 1M tokens

output: $0.2 / 1M tokens

Ministral 3 3B

input: $0.1 / 1M tokens

cached input: $0.01 / 1M tokens

output: $0.1 / 1M tokens

Ministral 3 8B

input: $0.15 / 1M tokens

cached input: $0.015 / 1M tokens

output: $0.15 / 1M tokens

Mistral Large 3

input: $0.5 / 1M tokens

cached input: $0.05 / 1M tokens

output: $1.5 / 1M tokens

Mistral Medium 3.5

input: $1.5 / 1M tokens

cached input: $0.15 / 1M tokens

output: $7.5 / 1M tokens

Mistral Small 4

input: $0.15 / 1M tokens

cached input: $0.015 / 1M tokens

output: $0.6 / 1M tokens

GPT-4.1

input: $2 / 1M tokens

cached input: $0.5 / 1M tokens

output: $8 / 1M tokens

GPT-4.1 mini

input: $0.4 / 1M tokens

cached input: $0.1 / 1M tokens

output: $1.6 / 1M tokens

GPT-4.1 nano

input: $0.1 / 1M tokens

cached input: $0.025 / 1M tokens

output: $0.4 / 1M tokens

GPT-4o

input: $2.5 / 1M tokens

cached input: $1.25 / 1M tokens

output: $10 / 1M tokens

GPT-4o mini

input: $0.15 / 1M tokens

cached input: $0.075 / 1M tokens

output: $0.6 / 1M tokens

GPT-5

input: $1.25 / 1M tokens

cached input: $0.125 / 1M tokens

output: $10 / 1M tokens

GPT-5-mini

input: $0.25 / 1M tokens

cached input: $0.025 / 1M tokens

output: $2 / 1M tokens

GPT-5-nano

input: $0.05 / 1M tokens

cached input: $0.005 / 1M tokens

output: $0.4 / 1M tokens

GPT-5.1

input: $1.25 / 1M tokens

cached input: $0.125 / 1M tokens

output: $10 / 1M tokens

GPT-5.2

input: $1.75 / 1M tokens

cached input: $0.175 / 1M tokens

output: $14 / 1M tokens

GPT-5.4

input: $2.5 / 1M tokens

cached input: $0.25 / 1M tokens

output: $15 / 1M tokens

GPT-5.4 Pro

up-to-272k

Prompt length up to 272,000 tokens

input: $30 / 1M tokens

output: $180 / 1M tokens

GPT-5.4 Pro

over-272k

Prompt length over 272,000 tokens

input: $60 / 1M tokens

output: $270 / 1M tokens

GPT-5.4-mini

input: $0.75 / 1M tokens

cached input: $0.075 / 1M tokens

output: $4.5 / 1M tokens

GPT-5.4-nano

input: $0.2 / 1M tokens

cached input: $0.02 / 1M tokens

output: $1.25 / 1M tokens

GPT-5.5

Context up to 272,000 tokens

input: $5 / 1M tokens

cached input: $0.5 / 1M tokens

output: $30 / 1M tokens

GPT-5.6-luna

input: $0.2 / 1M tokens

cached input: $0.02 / 1M tokens

output: $1.2 / 1M tokens

GPT-5.6-sol

input: $5 / 1M tokens

cached input: $0.5 / 1M tokens

output: $30 / 1M tokens

GPT-5.6-terra

input: $2 / 1M tokens

cached input: $0.2 / 1M tokens

output: $12 / 1M tokens

GPT-6 Astra

input: $10 / 1M tokens

cached input: $1 / 1M tokens

output: $50 / 1M tokens

GPT-6 Luna

up-to-272k

Prompt length up to 272,000 tokens

input: $0.1 / 1M tokens

cached input: $0.01 / 1M tokens

output: $0.5 / 1M tokens

GPT-6 Luna

over-272k

Prompt length over 272,000 tokens

input: $0.2 / 1M tokens

cached input: $0.02 / 1M tokens

output: $0.75 / 1M tokens

GPT-6 Sol

up-to-272k

Prompt length up to 272,000 tokens

input: $2 / 1M tokens

cached input: $0.2 / 1M tokens

output: $10 / 1M tokens

GPT-6 Sol

over-272k

Prompt length over 272,000 tokens

input: $4 / 1M tokens

cached input: $0.4 / 1M tokens

output: $15 / 1M tokens

GPT-6.1 Sol

up-to-272k

Prompt length up to 272,000 tokens

input: $2 / 1M tokens

cached input: $0.1 / 1M tokens

output: $10 / 1M tokens

GPT-6.1 Sol

over-272k

Prompt length over 272,000 tokens

input: $4 / 1M tokens

cached input: $0.2 / 1M tokens

output: $15 / 1M tokens

PLaMo 3.0 Prime

Prices apply up to 128,000 tokens (Standard plan)

Official pricing is published in JPY only; no USD price exists, so this model is listed for reference and excluded from USD ranking and estimates. No cached-input pricing is offered.

input: ¥60 / 1M tokens

output: ¥250 / 1M tokens

Fugu Ultra V1.1

Context up to 272,000 tokens

input: $5 / 1M tokens

cached input: $0.5 / 1M tokens

output: $30 / 1M tokens

Sakana Namazu V1.0

input: $0.95 / 1M tokens

cached input: $0.15 / 1M tokens

output: $4 / 1M tokens

Grok 4.20 (non-reasoning)

under-200k

Context length under 200,000 tokens

input: $1.25 / 1M tokens

cached input: $0.2 / 1M tokens

output: $2.5 / 1M tokens

Grok 4.20 (non-reasoning)

at-least-200k

Context length at least 200,000 tokens

input: $2.5 / 1M tokens

cached input: $0.4 / 1M tokens

output: $5 / 1M tokens

Grok 4.20 (reasoning)

under-200k

Context length under 200,000 tokens

input: $1.25 / 1M tokens

cached input: $0.2 / 1M tokens

output: $2.5 / 1M tokens

Grok 4.20 (reasoning)

at-least-200k

Context length at least 200,000 tokens

input: $2.5 / 1M tokens

cached input: $0.4 / 1M tokens

output: $5 / 1M tokens

Grok 4.20 Multi-Agent

under-200k

Context length under 200,000 tokens

input: $1.25 / 1M tokens

cached input: $0.2 / 1M tokens

output: $2.5 / 1M tokens

Grok 4.20 Multi-Agent

at-least-200k

Context length at least 200,000 tokens

input: $2.5 / 1M tokens

cached input: $0.4 / 1M tokens

output: $5 / 1M tokens

Grok 4.3

under-200k

Context length under 200,000 tokens

input: $1.25 / 1M tokens

cached input: $0.2 / 1M tokens

output: $2.5 / 1M tokens

Grok 4.3

at-least-200k

Context length at least 200,000 tokens

input: $2.5 / 1M tokens

cached input: $0.4 / 1M tokens

output: $5 / 1M tokens

Grok 4.5

under-200k

Context length under 200,000 tokens

input: $2 / 1M tokens

cached input: $0.3 / 1M tokens

output: $6 / 1M tokens

Grok 4.5

at-least-200k

Context length at least 200,000 tokens

input: $4 / 1M tokens

cached input: $0.6 / 1M tokens

output: $12 / 1M tokens

Grok 4.6

under-200k

Context length under 200,000 tokens

input: $2 / 1M tokens

cached input: $0.5 / 1M tokens

output: $6 / 1M tokens

Grok 4.6

at-least-200k

Context length at least 200,000 tokens

input: $4 / 1M tokens

cached input: $1 / 1M tokens

output: $12 / 1M tokens

Grok 4.7

under-200k

Context length under 200,000 tokens

input: $2 / 1M tokens

cached input: $0.5 / 1M tokens

output: $6 / 1M tokens

Grok 4.7

at-least-200k

Context length at least 200,000 tokens

input: $4 / 1M tokens

cached input: $1 / 1M tokens

output: $12 / 1M tokens

Grok Build 0.1

under-200k

Context length under 200,000 tokens

input: $1 / 1M tokens

cached input: $0.2 / 1M tokens

output: $2 / 1M tokens

Grok Build 0.1

at-least-200k

Context length at least 200,000 tokens

input: $2 / 1M tokens

cached input: $0.4 / 1M tokens

output: $4 / 1M tokens

GLM-4.5-Air

input: $0.2 / 1M tokens

cached input: $0.03 / 1M tokens

output: $1.1 / 1M tokens

GLM-4.7

input: $0.6 / 1M tokens

cached input: $0.11 / 1M tokens

output: $2.2 / 1M tokens

GLM-4.7-FlashX

input: $0.07 / 1M tokens

cached input: $0.01 / 1M tokens

output: $0.4 / 1M tokens

GLM-5

input: $1 / 1M tokens

cached input: $0.2 / 1M tokens

output: $3.2 / 1M tokens

GLM-5.1

input: $1.4 / 1M tokens

cached input: $0.26 / 1M tokens

output: $4.4 / 1M tokens

GLM-5.2

input: $1.4 / 1M tokens

cached input: $0.26 / 1M tokens

output: $4.4 / 1M tokens

GLM-5.3

input: $1.4 / 1M tokens

cached input: $0.26 / 1M tokens

output: $4.4 / 1M tokens

GLM-5.3-Flash

input: $0.15 / 1M tokens

cached input: $0.03 / 1M tokens

output: $0.5 / 1M tokens

GLM-5.3-FlashX

input: $0.37 / 1M tokens

cached input: $0.075 / 1M tokens

output: $1.25 / 1M tokens