Background
Ranking · data through 2026-11-18

The cheapest LLM APIs, ranked.

Every provider’s lightest tier, ranked by list-price input rate from the nightly checked record. Each row states whether its latest observation was verified or carried forward. As of 2026-11-18, the cheapest tracked rate is Llama 3.1 8B on DeepInfra at $0.02 per 1M input tokens.

#ProviderLightest tierInput / 1MOutput / 1MContextThe Hobbit*
1DeepInfra
TokenScale observation: verified 2026-11-18
Llama 3.1 8B$0.02$0.04128K$0.0051
2Cohere
TokenScale observation: verified 2026-11-18
Command R7B (12-2024)$0.0375$0.15128K$0.0191
3Groq
TokenScale observation: carried 2026-11-18
GPT-OSS 20B$0.075$0.3131K$0.0381
4OpenRouter
TokenScale observation: verified 2026-11-18
Llama 3.3 70B$0.1$0.32128K$0.0407
5OpenAI
TokenScale observation: verified 2026-11-18
GPT-6 Luna$0.1$0.51.05M$0.0636
6Fireworks AI
TokenScale observation: verified 2026-11-18
GLM 5.3 Flash$0.15$0.51040K$0.0636
7Mistral AI
TokenScale observation: verified 2026-11-18
Mistral Small 4$0.15$0.632K$0.0763
8Together AI
TokenScale observation: verified 2026-11-18
GPT-OSS 120B$0.15$0.6128K$0.0763
9Zhipu GLM
TokenScale observation: verified 2026-11-18
GLM-4.5-Air$0.2$1.10200K$0.1399
10SambaNova
TokenScale observation: verified 2026-11-18
GPT-OSS 120B$0.22$0.59128K$0.075
11Alibaba Qwen
TokenScale observation: verified 2026-11-18
Qwen3.6-Flash$0.25$1.501M$0.1907
12DeepSeek
TokenScale observation: verified 2026-11-18
V4.1 Flash · peak rate$0.3$1.201M$0.1526
13MiniMax
TokenScale observation: carried 2026-11-18
MiniMax M2$0.3$1.20200K$0.1526
14Google Gemini
TokenScale observation: verified 2026-11-18
Flash-Lite 3.5$0.3$2.501M$0.3179
15Cerebras
TokenScale observation: verified 2026-11-18
GPT-OSS 120B$0.35$0.75128K$0.0954
16Moonshot Kimi
TokenScale observation: verified 2026-11-18
Kimi K2.6$0.95$4.00256K$0.5086
17Sakana AI
TokenScale observation: verified 2026-11-18
Sakana Namazu$0.95$4.00256K$0.5086
18Perplexity†
TokenScale observation: carried 2026-11-18
Sonar$1.00$1.00127K$0.1271
19xAI Grok
TokenScale observation: verified 2026-11-18
Grok Build 0.1$1.00$2.00256K$0.2543
20Anthropic
TokenScale observation: verified 2026-11-18
Claude Haiku 4.5$1.00$5.00200K$0.6357
21AWS Bedrock
TokenScale observation: verified 2026-11-18
Claude Haiku 4.5 (Bedrock)$1.00$5.00200K$0.6357
22Meta
TokenScale observation: verified 2026-11-18
Muse Spark 1.3$1.25$4.251M$0.5403

Scroll the table sideways to see every column.

* Cost to generate The Hobbit (95,356 words ≈ 127,141 tokens) as output. † Perplexity bills web search separately per request; token prices exclude that fee.

How to read this table

About these numbers. Provider pages are authoritative for current published prices. TokenScale checks those sources nightly and independently records what was verified, changed, corrected or carried forward (data through 2026-11-18). List prices only: promotions never enter the ranking. Corrections are published, not buried: see the methodology.

Use this ranking with

More pricing pages