Skip to main content

LLM Pricing: API Prices for 50+ Models

50 models from 10 providers · prices checked Oct 21, 2026

Claude API pricing — monthly cost for Claude (Anthropic) models

What are you using it for?

Usage scenario

800 input · 300 output · 20,000 requests/month · 40% of input cached

★ Most people pick this

Claude Sonnet 5.5

$79.84/month

✓ Official price checked Oct 6, 2026 · Official pricing

Good for everyday chat and coding. Not good for high-volume jobs on a tight budget.

DeepSeek-V4.1-Flash

$10.12/month

✓ Official price checked Oct 6, 2026 · Official pricing

Peak-hour price; 50% off outside peak hours.

Good for high-volume chat on a small budget. Not good for work that needs a flagship.

GPT-6.1 Sol

$79.84/month

✓ Official price checked Oct 6, 2026 · Official pricing

Good for general API work with cheap cached input. Not good for the lowest list price.

MidOpenAI
Adjust usage800 in · 300 out · 20,000 requests/month
800
300
20,000

Standard rates. Cached input uses this scenario's cached share. Open the full calculator →

50 models · USD per 1M tokens
LLM API prices
ModelProviderTierChecked
GPT-6 Astra
OpenAI · $10 in / $50 out
$0.023OpenAIFlagship$10*$50*$11.05MOct 21, 2026$0.023
GPT-5.6 Sol
OpenAI · $4 in / $20 out · Promo price
Promotional price, available at least through Nov 21, 2026.
$0.0092OpenAIFlagship$4*$20*$0.401.05MOct 6, 2026$0.0092
GPT-5.5
OpenAI · $5 in / $30 out
$0.013OpenAIFlagship$5*$30*$0.501.05MOct 6, 2026$0.013
GPT-6.1 Sol
OpenAI · $2 in / $10 out
$0.0046OpenAIMid$2*$10*$0.101.05MOct 6, 2026$0.0046
GPT-6 Sol
OpenAI · $2 in / $10 out
$0.0046OpenAIMid$2*$10*$0.201.05MOct 6, 2026$0.0046
GPT-5.6 Terra
OpenAI · $2 in / $12 out
$0.0052OpenAIMid$2*$12*$0.201.05MOct 6, 2026$0.0052
GPT-6 Luna
OpenAI · $0.10 in / $0.50 out
$0.00023OpenAISmall$0.10*$0.50*$0.011.05MOct 6, 2026$0.00023
GPT-5.6 Luna
OpenAI · $0.20 in / $1.20 out
$0.00052OpenAISmall$0.20*$1.20*$0.021.05MOct 6, 2026$0.00052
Claude Opus 5.5
Anthropic · $4 in / $20 out
$0.0092AnthropicFlagship$4$20$0.201MOct 6, 2026$0.0092
Claude Fable 5.1
Anthropic · $10 in / $50 out
$0.023AnthropicFlagship$10$50$0.251MOct 6, 2026$0.023
Show the other 40 models
Remaining LLM API prices
ModelProviderTierChecked
Claude Sonnet 5.5
Anthropic · $2 in / $10 out
$0.0046AnthropicMid$2$10$0.101MOct 6, 2026$0.0046
Claude Haiku 4.5
Anthropic · $1 in / $5 out
$0.0023AnthropicSmall$1$5$0.10200KOct 6, 2026$0.0023
Gemini 3.1 Pro Preview
Google · $2 in / $12 out
$0.0052GoogleFlagship$2*$12*$0.201.05MOct 6, 2026$0.0052
Gemini 4 Argon
Google · $2 in / $10 out · Announced
Announced, not yet in the API. Introductory price; then $4 / $20.
$0.0046GoogleFlagship$2$10$0.10—Oct 6, 2026$0.0046
Gemini 3.8 Flash
Google · $0.75 in / $3.75 out · Promo price
Promotional price until Dec 31, 2026; then $1.50 / $7.50.
$0.0017GoogleMid$0.75$3.75$0.0751.05MOct 6, 2026$0.0017
Gemini 3.7 Flash
Google · $0.75 in / $3.75 out · Promo price
Promotional price until Dec 31, 2026; then $1.50 / $7.50.
$0.0017GoogleMid$0.75$3.75$0.0751.05MOct 6, 2026$0.0017
Gemini 3.6 Flash
Google · $0.75 in / $3.75 out · Promo price
Promotional price until Dec 31, 2026; then $1.50 / $7.50.
$0.0017GoogleMid$0.75$3.75$0.0751.05MOct 6, 2026$0.0017
Gemini 3.5 Flash-Lite
Google · $0.30 in / $2.50 out
$0.00099GoogleSmall$0.30$2.50$0.031.05MOct 6, 2026$0.00099
Gemini 3.1 Flash-Lite
Google · $0.25 in / $1.50 out
$0.00065GoogleSmall$0.25$1.50$0.0251.05MOct 6, 2026$0.00065
DeepSeek-V4-Pro
DeepSeek · $1.32 in / $3.96 out · Peak-hour price
Peak-hour price; 50% off outside peak hours.
$0.0022DeepSeekFlagship$1.32$3.96$0.0441MOct 6, 2026$0.0022
DeepSeek-V4.1-Flash
DeepSeek · $0.30 in / $1.20 out · Peak-hour price
Peak-hour price; 50% off outside peak hours.
$0.0006DeepSeekSmall$0.30$1.20$0.0061MOct 6, 2026$0.0006
Grok 4.7
xAI · $2 in / $6 out
$0.0034xAIFlagship$2*$6*$0.50500KOct 6, 2026$0.0034
Grok 4.6
xAI · $2 in / $6 out
$0.0034xAIFlagship$2*$6*$0.50500KOct 6, 2026$0.0034
Grok 4.5
xAI · $2 in / $6 out
$0.0034xAIFlagship$2*$6*$0.30500KOct 6, 2026$0.0034
Grok 4.3
xAI · $1.25 in / $2.50 out
$0.0018xAIMid$1.25*$2.50*$0.201MOct 6, 2026$0.0018
Grok 4.20
xAI · $1.25 in / $2.50 out
$0.0018xAIMid$1.25*$2.50*$0.201MOct 6, 2026$0.0018
Grok Build 0.1Preview
xAI · $1 in / $2 out
$0.0014xAISmall$1*$2*$0.20256KOct 6, 2026$0.0014
Qwen3.8-Max
Alibaba (Qwen) · $2 in / $6 out
$0.0034Alibaba (Qwen)Flagship$2$6$0.251MOct 6, 2026$0.0034
Qwen3.7-Plus
Alibaba (Qwen) · $0.40 in / $1.60 out · List price
List price; limited-time 20% off currently.
$0.0008Alibaba (Qwen)Mid$0.40*$1.60*$0.081MOct 6, 2026$0.0008
Qwen3.8-Flash
Alibaba (Qwen) · $0.15 in / $0.47 out
$0.00026Alibaba (Qwen)Small$0.15$0.47$0.0161MOct 6, 2026$0.00026
Qwen3.8-27B
Alibaba (Qwen) · $0.50 in / $3 out
$0.0013Alibaba (Qwen)Small$0.50$3$0.101MOct 1, 2026$0.0013
Qwen3.7-Flash
Alibaba (Qwen) · $0.03 in / $0.13 out
$0.000063Alibaba (Qwen)Small$0.03*$0.13*$0.0061MOct 6, 2026$0.000063
GLM-5.3
Zhipu (GLM) · $1.40 in / $4.40 out
$0.0024Zhipu (GLM)Flagship$1.40$4.40$0.261MOct 6, 2026$0.0024
GLM-5.2
Zhipu (GLM) · $1.40 in / $4.40 out
$0.0024Zhipu (GLM)Flagship$1.40$4.40$0.261MOct 6, 2026$0.0024
GLM-5.3-Flash
Zhipu (GLM) · $0.15 in / $0.50 out
$0.00027Zhipu (GLM)Small$0.15$0.50$0.031MOct 6, 2026$0.00027
GLM-5.3-FlashX
Zhipu (GLM) · $0.37 in / $1.25 out
$0.00067Zhipu (GLM)Small$0.37$1.25$0.0751MOct 6, 2026$0.00067
Kimi K3
Moonshot (Kimi) · $3 in / $15 out
$0.0069Moonshot (Kimi)Flagship$3$15$0.301.05MOct 6, 2026$0.0069
Kimi K2.6
Moonshot (Kimi) · $0.95 in / $4 out
$0.002Moonshot (Kimi)Mid$0.95$4$0.16262KOct 6, 2026$0.002
Kimi K2.7 Code
Moonshot (Kimi) · $0.95 in / $4 out
$0.002Moonshot (Kimi)Mid$0.95$4$0.19262KOct 6, 2026$0.002
Kimi K2.7 Code HighSpeed
Moonshot (Kimi) · $1.90 in / $8 out
$0.0039Moonshot (Kimi)Mid$1.90$8$0.38262KOct 6, 2026$0.0039
MiniMax-M3
MiniMax · $0.30 in / $1.20 out
$0.0006MiniMaxFlagship$0.30*$1.20*$0.061MOct 6, 2026$0.0006
MiniMax-M2.7
MiniMax · $0.30 in / $1.20 out
$0.0006MiniMaxMid$0.30$1.20$0.06205KOct 6, 2026$0.0006
MiniMax-M2.7-highspeed
MiniMax · $0.60 in / $2.40 out
$0.0012MiniMaxMid$0.60$2.40$0.06205KOct 6, 2026$0.0012
Mistral Medium 3.5
Mistral · $1.50 in / $7.50 out
$0.0034MistralFlagship$1.50$7.50$0.15256KOct 6, 2026$0.0034
Mistral Large 3
Mistral · $0.50 in / $1.50 out
$0.00085MistralMid$0.50$1.50$0.05256KOct 6, 2026$0.00085
Mistral Small 4
Mistral · $0.15 in / $0.60 out
$0.0003MistralSmall$0.15$0.60$0.015256KOct 6, 2026$0.0003
Ministral 3 14B
Mistral · $0.20 in / $0.20 out
$0.00022MistralSmall$0.20$0.20$0.02256KOct 6, 2026$0.00022
Ministral 3 8B
Mistral · $0.15 in / $0.15 out
$0.00016MistralSmall$0.15$0.15$0.015256KOct 6, 2026$0.00016
Ministral 3 3B
Mistral · $0.10 in / $0.10 out
$0.00011MistralSmall$0.10$0.10$0.01256KOct 6, 2026$0.00011
Codestral
Mistral · $0.30 in / $0.90 out
$0.00051MistralSmall$0.30$0.90$0.03128KOct 6, 2026$0.00051

Standard pay-as-you-go rates. * Higher rates apply above a context-length threshold. Click a date to open the official pricing page it was checked against. Your cost is one request at the usage selected above.

Browse by provider

Tools & guides

How LLM API pricing works

What is a token?

A token is the unit LLM APIs bill by: a word fragment of about four characters in English, so 1,000 words come to roughly 1,300 tokens. Prices are quoted per million tokens.

At GPT-6.1 Sol's $10 per 1M output tokens, generating a 1,000-word article costs about $0.013.

Why output costs more than input

The model reads your prompt in one pass but writes its answer one token at a time, so output takes more compute and costs more.

Claude Opus 5.5 charges $4 for input and $20 for output, 5 times as much. DeepSeek-V4-Pro charges $1.32 and $3.96, 3 times as much. For long answers, compare output prices first.

Cached input pricing

When you resend the same prefix, such as a system prompt or a document, providers can serve it from a cache and bill it at a lower cached input rate.

GPT-6.1 Sol bills cached input at $0.10 instead of $2; Claude Opus 5.5 at $0.20 instead of $4. Some providers also charge for writing to the cache, at $5 per 1M tokens for Claude Opus 5.5.

Batch discounts

If you can wait minutes or hours for results, batch APIs process requests asynchronously at a discount. 26 of the 50 models in the table offer 50% off this way; a few providers offer smaller discounts or none.

Long-context tiered pricing

Some models charge more once a request passes a context-length threshold, and the higher rate usually applies to the whole request. These models are marked with * in the table.

GPT-6.1 Sol goes from $2 / $10 to $4 / $15 above 272K input tokens; Gemini 3.1 Pro Preview to $4 / $18 above 200K; Qwen3.7-Plus to $1.20 / $4.80 above 256K.

FAQ