LLMCost
SKU ladder

Same model, very different prices

Most frontier models ship in multiple SKUs: Standard (interactive), Batch (~50% off, 24-hour turnaround), Flex (cheaper, tolerates throttling), and sometimes Free tiers with strict limits. Picking the right SKU for the right job is the single biggest bill lever — here is the full ladder for 87 model families.

Batch
~50% off both directions; results within 24h. Best for evals, backfills, offline processing.
Flex
Discounted for tolerating throttling/queueing. Check our batch reality check for providers that don't actually discount.
Free
Rate-limited variants of open models. Great for prototyping; see all free models.

The full matrix (87 families)

Anthropic: Claude Fable 5

anthropic · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$10.00$50.00$1.001M
Batch$5.00$25.00$0.5001M

Anthropic: Claude Fable 5.1

anthropic · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$10.00$50.00$0.2501M
Batch$5.00$25.00$0.1251M

Anthropic: Claude Haiku 4.5

anthropic · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$1.00$5.00$0.100200K
Batch$0.500$2.50$0.050200K

Anthropic: Claude Haiku 5.5

anthropic · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$0.100$0.500$0.0101M
Batch$0.050$0.250$0.00501M

Anthropic: Claude Opus 4.1

anthropic · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$15.00$75.00$1.50200K
Batch$7.50$37.50$0.750200K

Anthropic: Claude Opus 4.5

anthropic · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$5.00$25.00$0.500200K
Batch$2.50$12.50$0.250200K

Anthropic: Claude Opus 4.6

anthropic · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$5.00$25.00$0.5001M
Batch$2.50$12.50$0.2501M

Anthropic: Claude Opus 4.7

anthropic · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$5.00$25.00$0.5001M
Batch$2.50$12.50$0.2501M

Anthropic: Claude Opus 4.8

anthropic · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$5.00$25.00$0.5001M
Batch$2.50$12.50$0.2501M

Anthropic: Claude Opus 5

anthropic · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$5.00$25.00$0.5001M
Batch$2.50$12.50$0.2501M

Anthropic: Claude Opus 5.5

anthropic · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$4.00$20.00$0.2001M
Batch$2.00$10.00$0.1001M

Anthropic: Claude Sonnet 4.5

anthropic · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$3.00$15.00$0.3001M
Batch$1.50$7.50$0.1501M

Anthropic: Claude Sonnet 4.6

anthropic · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$3.00$15.00$0.3001M
Batch$1.50$7.50$0.1501M

Anthropic: Claude Sonnet 5

anthropic · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$2.00$10.00$0.2001M
Batch$1.00$5.00$0.1001M

Anthropic: Claude Sonnet 5.5

anthropic · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$2.00$10.00$0.1001M
Batch$1.00$5.00$0.0501M
SKUInput /1MOutput /1MCache readContext
Standard$0.049$0.375$0.00101.0M
Batch$0.050$0.150$0.00401.0M

Google: Gemini 2.5 Flash Lite

google · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$0.100$0.400$0.0101.0M
Batch$0.050$0.200$0.0101.0M

Google: Gemini 3 Flash Preview

google · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$0.500$3.00$0.0501.0M
Batch$0.250$1.50—1.0M

Google: Gemini 3.1 Flash Lite

google · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$0.250$1.50$0.0251.0M
Batch$0.125$0.750$0.0131.0M

Google: Gemini 3.1 Pro Preview

google · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$2.00$12.00$0.2001.0M
Batch$1.00$6.00—1.0M

Google: Gemini 3.5 Flash

google · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$1.50$9.00$0.1501.0M
Batch$0.750$4.50$0.0751.0M

Google: Gemini 3.5 Flash Lite

google · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$0.300$2.50$0.0301.0M
Batch$0.150$1.25$0.0151.0M

Google: Gemini 3.6 Flash

google · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$0.750$3.75$0.0751.0M
Batch$0.375$1.88$0.0371.0M

Google: Gemini 3.7 Flash

google · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$0.750$3.75$0.0751.0M
Batch$0.375$1.88$0.0371.0M

Google: Gemini 3.8 Flash

google · 2 SKUs · batch −55%
SKUInput /1MOutput /1MCache readContext
Standard$0.825$4.13$0.0831.0M
Batch$0.375$1.88$0.0371.0M

Google: Gemini 4 Argon

google · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$2.00$10.00$0.1001.0M
Batch$1.00$5.00$0.0501.0M

Google: Gemma 4 26B A4B

google · 2 SKUs
SKUInput /1MOutput /1MCache readContext
Standard$0.090$0.300$0.050262K
FreeFreeFree—262K

Google: Gemma 4 31B

google · 2 SKUs
SKUInput /1MOutput /1MCache readContext
Standard$0.200$0.400—262K
FreeFreeFree—262K

Mistral: Codestral 2508

mistralai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$0.300$0.900$0.030256K
Batch$0.150$0.450$0.015256K

Mistral: Ministral 3 8B 2512

mistralai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$0.150$0.150$0.015262K
Batch$0.075$0.075$0.0075262K

Mistral: Mistral Large 3 2512

mistralai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$0.500$1.50$0.050262K
Batch$0.250$0.750$0.025262K

Mistral: Mistral Medium 3.1

mistralai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$0.400$2.00$0.040131K
Batch$0.200$1.00$0.020131K

Mistral: Mistral Medium 3.5

mistralai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$1.50$7.50—262K
Batch$0.750$3.75—262K

Mistral: Mistral Small 4

mistralai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$0.150$0.600$0.015262K
Batch$0.075$0.300$0.0075262K

MoonshotAI: Kimi K3

moonshotai · 2 SKUs
SKUInput /1MOutput /1MCache readContext
Standard$0.239$11.94$0.2101.0M
Batch$2.28$11.40$0.2281.0M

NVIDIA: Nemotron 3 Super

nvidia · 2 SKUs
SKUInput /1MOutput /1MCache readContext
Standard$0.300$2.40$0.150262K
FreeFreeFree—262K

NVIDIA: Nemotron 3 Ultra

nvidia · 2 SKUs
SKUInput /1MOutput /1MCache readContext
Standard$0.600$2.40$0.120262K
FreeFreeFree—1M
SKUInput /1MOutput /1MCache readContext
Standard$0.200$0.200—131K
FreeFreeFree—128K
SKUInput /1MOutput /1MCache readContext
Standard$0.070$0.200$0.040262K
FreeFreeFree—1M
SKUInput /1MOutput /1MCache readContext
Standard$0.150$0.500$0.0201.0M
FreeFreeFree—1M

OpenAI: GPT-3.5 Turbo

openai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$0.500$1.50—16K
Batch$0.250$0.750—16K

OpenAI: GPT-4 Turbo

openai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$10.00$30.00—128K
Batch$5.00$15.00—128K

OpenAI: GPT-4.1

openai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$2.00$8.00$0.5001.0M
Batch$1.00$4.00$0.2501.0M

OpenAI: GPT-4.1 Mini

openai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$0.400$1.60$0.1001.0M
Batch$0.200$0.800$0.0501.0M

OpenAI: GPT-4.1 Nano

openai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$0.100$0.400$0.0251.0M
Batch$0.050$0.200$0.0131.0M

OpenAI: GPT-4o

openai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$2.50$10.00$1.25128K
Batch$1.25$5.00$0.625128K

OpenAI: GPT-4o-mini

openai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$0.150$0.600$0.075128K
Batch$0.075$0.300$0.037128K

OpenAI: GPT-5

openai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$1.25$10.00$0.125400K
Batch$0.625$5.00$0.063400K

OpenAI: GPT-5 Mini

openai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$0.250$2.00$0.025400K
Batch$0.125$1.00$0.013400K

OpenAI: GPT-5 Nano

openai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$0.050$0.400$0.0050400K
Batch$0.025$0.200$0.0025400K

OpenAI: GPT-5 Pro

openai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$15.00$120.00—400K
Batch$7.50$60.00—400K

OpenAI: GPT-5.1

openai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$1.25$10.00$0.125400K
Batch$0.625$5.00$0.063400K

OpenAI: GPT-5.2

openai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$1.75$14.00$0.175400K
Batch$0.875$7.00$0.087400K

OpenAI: GPT-5.2 Pro

openai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$21.00$168.00—400K
Batch$10.50$84.00—400K

OpenAI: GPT-5.4

openai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$2.50$15.00$0.2501.1M
Batch$1.25$7.50$0.1251.1M

OpenAI: GPT-5.4 Mini

openai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$0.750$4.50$0.075400K
Batch$0.375$2.25$0.037400K

OpenAI: GPT-5.4 Nano

openai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$0.200$1.25$0.020400K
Batch$0.100$0.625$0.010400K

OpenAI: GPT-5.4 Pro

openai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$30.00$180.00—1.1M
Batch$15.00$90.00—1.1M

OpenAI: GPT-5.5

openai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$5.00$30.00$0.5001.1M
Batch$2.50$15.00$0.2501.1M

OpenAI: GPT-5.5 Pro

openai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$30.00$180.00—1.1M
Batch$15.00$90.00—1.1M

OpenAI: GPT-5.6 Luna

openai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$0.200$1.20$0.0201.1M
Batch$0.100$0.600$0.0101.1M

OpenAI: GPT-5.6 Luna Pro

openai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$0.200$1.20$0.0201.1M
Batch$0.100$0.600$0.0101.1M

OpenAI: GPT-5.6 Sol

openai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$4.00$20.00$0.4001.1M
Batch$2.00$10.00$0.2001.1M

OpenAI: GPT-5.6 Sol Pro

openai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$4.00$20.00$0.4001.1M
Batch$2.00$10.00$0.2001.1M

OpenAI: GPT-5.6 Terra

openai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$2.00$12.00$0.2001.1M
Batch$1.00$6.00$0.1001.1M

OpenAI: GPT-5.6 Terra Pro

openai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$2.00$12.00$0.2001.1M
Batch$1.00$6.00$0.1001.1M

OpenAI: GPT-6 Astra

openai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$10.00$50.00$1.001.1M
Batch$5.00$25.00$0.5001.1M

OpenAI: GPT-6 Astra Pro

openai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$10.00$50.00$1.001.1M
Batch$5.00$25.00$0.5001.1M

OpenAI: GPT-6 Luna

openai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$0.100$0.500$0.0101.1M
Batch$0.050$0.250$0.00501.1M

OpenAI: GPT-6 Luna Pro

openai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$0.100$0.500$0.0101.1M
Batch$0.050$0.250$0.00501.1M

OpenAI: GPT-6 Sol

openai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$2.00$10.00$0.2001.1M
Batch$1.00$5.00$0.1001.1M

OpenAI: GPT-6 Sol Pro

openai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$2.00$10.00$0.2001.1M
Batch$1.00$5.00$0.1001.1M

OpenAI: GPT-6.1 Sol

openai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$2.00$10.00$0.1001.1M
Batch$1.00$5.00$0.0501.1M

OpenAI: GPT-6.1 Sol Pro

openai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$2.00$10.00$0.1001.1M
Batch$1.00$5.00$0.0501.1M

OpenAI: gpt-oss-120b

openai · 2 SKUs · batch −80%
SKUInput /1MOutput /1MCache readContext
Standard$0.150$0.600$0.075131K
Batch$0.030$0.136—131K

OpenAI: gpt-oss-20b

openai · 2 SKUs
SKUInput /1MOutput /1MCache readContext
Standard$0.018$0.090$0.0090131K
Batch$0.024$0.112—131K

OpenAI: o3

openai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$2.00$8.00$0.500200K
Batch$1.00$4.00$0.250200K

OpenAI: o3 Mini

openai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$1.10$4.40$0.550200K
Batch$0.550$2.20$0.275200K

OpenAI: o4 Mini

openai · 2 SKUs · batch −50%
SKUInput /1MOutput /1MCache readContext
Standard$1.10$4.40$0.275200K
Batch$0.550$2.20$0.138200K

Poolside: Laguna S 2.1

poolside · 2 SKUs
SKUInput /1MOutput /1MCache readContext
Standard$0.090$0.180$0.00901.0M
FreeFreeFree—262K

Poolside: Laguna XS 2.1

poolside · 2 SKUs
SKUInput /1MOutput /1MCache readContext
Standard$0.060$0.120$0.030262K
FreeFreeFree—262K

Qwen: Qwen3.7 Plus

qwen · 2 SKUs · batch −28%
SKUInput /1MOutput /1MCache readContext
Standard$0.320$1.28$0.0641M
Batch$0.230$0.920—262K

Thinking Machines: Inkling

thinkingmachines · 2 SKUs
SKUInput /1MOutput /1MCache readContext
Standard$1.00$4.05$0.170524K
FreeFreeFree—1.0M

Thinking Machines: Inkling Small

thinkingmachines · 2 SKUs
SKUInput /1MOutput /1MCache readContext
Standard$0.450$1.20$0.100524K
FreeFreeFree—1.0M

xAI: Grok 4.3

x-ai · 2 SKUs · batch −20%
SKUInput /1MOutput /1MCache readContext
Standard$1.25$2.50$0.2001M
Batch$1.00$2.00$0.1601M

Z.ai: GLM 5.3

z-ai · 2 SKUs
SKUInput /1MOutput /1MCache readContext
Standard$0.079$1.40$0.0781.0M
Batch$0.450$2.00$0.1001.0M

Z.ai: GLM 5.3 Flash

z-ai · 2 SKUs · batch −67%
SKUInput /1MOutput /1MCache readContext
Standard$0.150$0.500$0.0301.0M
Batch$0.050$0.180$0.0101.0M