↑↓ move↵ openesc close

Overage / LLM APIs

LLM APIs pricing comparison

17 services, one row each: what it costs, the tightest limit you will hit, and when it last changed. Sorted by price per normalized unit; click a column header to re-sort.

Verified 2026-10-23 (2 days ago)Source: AI21 Labs, Anthropic API, Azure OpenAI Service, Baseten and 13 more, linked on each service pageVerified shows the oldest date in this category.
LLM APIs: one row per service, sortable
Perplexity APIno base feepay as you go6 modelsper-model pricing$0.004 inunlisted out / 1M tokensunlisted2026-10-24none
Coherenone listed6 modelsper-model pricing$0.02 in$0.15 out / 1M tokensunlisted2026-10-24none
DeepInfranone listed60 modelsper-model pricing$0.02 in$0.03 out / 1M tokensunlisted2026-10-24none
Groqnone listed6 modelsper-model pricing$0.03 in$0.03 out / 1M tokens100 api requests / minute2026-10-24none
Azure OpenAI Servicenone listed110 modelsper-model pricing$0.05 in$0.40 out / 1M tokensunlisted2026-10-24none
Anthropic APInone listed21 modelsper-model pricing$0.10 in$0.50 out / 1M tokensunlisted2026-10-242026-10-23
Basetenyes16 modelsper-model pricing$0.10 in$0.26 out / 1M tokensunlisted2026-10-24none
Google Gemini APIyes37 modelsper-model pricing$0.10 in$0.40 out / 1M tokensunlisted2026-10-24none
Mistral AI APIyes13 modelsper-model pricing$0.10 in$0.10 out / 1M tokensunlisted2026-10-23none
OpenAI APInone listed11 modelsper-model pricing$0.10 in$0.50 out / 1M tokensunlisted2026-10-24none
DeepSeek APInone listed4 modelsper-model pricing$0.15 in$0.60 out / 1M tokensunlisted2026-10-24none
AI21 Labsyes2 modelsper-model pricing$0.20 in$0.40 out / 1M tokensunlisted2026-10-23none
SambaNova Cloudnone listed6 modelsper-model pricing$0.22 in$0.59 out / 1M tokensunlisted2026-10-24none
Cerebras Inferencenone listed2 modelsper-model pricing$0.35 in$0.75 out / 1M tokensunlisted2026-10-23none
xAI APInone listed1 modelper-model pricing$2 in$6 out / 1M tokensunlisted2026-10-24none
Replicatenone listed1 modelper-model pricing$3.75 in$10 out / 1M tokensunlisted2026-10-24none
Hugging Face Inferencenone listed$9 / moPRO Accountunlistedunlisted2026-10-24none

Plan services: the lowest overage rate on any tier at the normalized unit shown. Model services: the cheapest input and cheapest output price per 1M tokens across all of the service's models (not necessarily the same model; see every model on the token pages). Services with no listed rate show "unlisted" and sort last. All categories.

Compare

Every pair in this category has a page, for example Perplexity API vs Cohere. All comparisons.