1stTop pick
Researched 29d agoLlama 3.1 8B Instruct
- Input $/1M
- $0.020
- Output (from)
- $0.050 / 1M
Cheapest LLM APIs You Can Call Right Now (2026)
Last refreshed 2026-05-18. Next refresh: weekly.
Cheapest LLM APIs you can call right now, ranked by strict lowest tracked input price with an MMLU or GPQA quality watermark beside each row.
Use this page when token price is the first constraint and quality still matters. The rows below exclude zero-dollar tiers and surface a quality watermark beside tracked input prices.
Need no-cost options? Compare the free-model leaderboard separately from paid API pricing.
Top three picks
Opinionated short stack for this category — scroll for the full leaderboard, pricing, and compare links.
2ndShortlist
Researched 25d agoMistral NeMo Instruct (2407)
- Input $/1M
- $0.020
- Output (from)
- $0.040 / 1M
3rdShortlist
Researched 29d agoGemma 3n 4B (free)
- Input $/1M
- $0.020
- Output (from)
- $0.040 / 1M
How we rank
Cheapest LLM APIs stay a strict price board, with a quality watermark so low-cost rows do not hide weak benchmark coverage.
- Eligibility — Chat-completion style APIs with positive priced tiers (we exclude zero-dollar rows here because `/best/free` covers that intent).
- Primary ranking — Ascending input $/1M tokens using consolidated provider data.
- Quality watermark — Rows show the first available MMLU or GPQA Diamond score as a capability check, but the score does not change cheap-page order.
- Variant collapse — We keep one row per model family (`familySlug` + parameter tier). When headline scores tie within ±0.5 pt (±10 Elo on Chatbot Arena), we pick the canonical SKU by lowest tracked input price, then GA over preview or limited access, then newest `release`. A folded sibling within the benchmark noise band can show a "Tied within margin" chip on that score cell.
- Coverage caveat — Ultra-cheap models may lack frontier benchmarks — pair this list with `/best/coding` or another task board for quality guardrails.
| # | Model | Input $/1M | Output $/1M | |
|---|---|---|---|---|
| 1 | Llama 3.1 8B Instruct Quality watermark: — | $0.02 | $0.05 | |
| 2 | Mistral NeMo Instruct (2407) Quality watermark: MMLU 81.5% | $0.02 | $0.04 | |
| 3 | Aleph Alpha Luminous Base Quality watermark: — | $0.02 | $0.06 | |
| 4 | Gemma 3n 4B (free) Quality watermark: — | $0.02 | $0.04 | |
| 5 | Together AI - Gemma 3n-e4B Tools Quality watermark: — | $0.02 | $0.04 | |
| 6 | Llama 3.2 1B Instruct Quality watermark: MMLU 49.3% | $0.03 | $0.10 | |
| 7 | gpt-oss-20b Tools Quality watermark: GPQA Diamond 68.8% | $0.03 | $0.14 | |
| 8 | Llama 3 8B Instruct Quality watermark: MMLU 76.9% | $0.03 | $0.04 | |
| 9 | Qwen2.5-7B-Instruct Quality watermark: MMLU 81.2% | $0.03 | $0.03 | |
| 10 | Granite 3.3 8B Instruct Tools Quality watermark: — | $0.03 | $0.25 | |
| 11 | LFM2-24B-A2B Tools Quality watermark: — | $0.03 | $0.12 | |
| 12 | ERNIE Lite Pro Quality watermark: — | $0.03 | $0.06 | |
| 13 | Nova Micro Quality watermark: — | $0.04 | $0.14 | |
| 14 | Gemini 1.5 Flash on Google Vertex AI Vision Quality watermark: — | $0.04 | $0.10 | |
| 15 | Gemini 1.5 Flash 8B Quality watermark: — | $0.04 | $0.15 | |
| 16 | gpt-oss-120b Tools Quality watermark: GPQA Diamond 78.2% | $0.04 | $0.18 | |
| 17 | Aleph Alpha Luminous Extended Quality watermark: — | $0.04 | $0.12 | |
| 18 | Qwen3-9B Quality watermark: — | $0.04 | $0.20 | |
| 19 | Nemotron-Nano-9B-v2 Quality watermark: — | $0.04 | $0.16 | |
| 20 | ERNIE Speed Pro Quality watermark: — | $0.04 | $0.09 |
Honorable mentions
Next seats in this ranking. Lines below are from each model's stored description in LLMReference seed data—spot-check the model page before relying on a capability claim.
Efficient 4B parameter model from Google, available on Together AI. Gemma 3 nano-edge model optimized for low-latency inference.
$0.020
Input $/1M
Llama 3.2 1B Instruct available on AWS Bedrock
$0.027
Input $/1M
OpenAI open-weight model with 20 billion parameters. Lightweight, efficient text-only model with reasoning and function calling. Free for self-hosting. Released August 5, 2025.
$0.030
Input $/1M
Compare Top Picks
Llama 3.1 8B Instruct vs Mistral NeMo Instruct (2407)Llama 3.1 8B Instruct vs Aleph Alpha Luminous BaseLlama 3.1 8B Instruct vs Gemma 3n 4B (free)Llama 3.1 8B Instruct vs Together AI - Gemma 3n-e4BMistral NeMo Instruct (2407) vs Aleph Alpha Luminous BaseMistral NeMo Instruct (2407) vs Gemma 3n 4B (free)
Browse Other Categories
Best LLMs for Code GenerationBest LLMs for RAGBest AI Agents & Agentic ModelsBest LLMs for ClassificationBest Open Source LLMsBest Multimodal / Vision LLMsBest LLMs for Reasoning & MathBest Small Language Models (SLMs)Best LLMs for Function Calling & Tool UseBest Long Context LLMsBest Mainstream LLM APIs, RankedBest LLMs for EnterpriseBest Free LLMs You Can Use Right NowBest LLMs for WritingBest LLMs for MarketingBest LLMs for Customer Support