1stTop pick
Researched todayGranite 4.0 H Micro
- Input $/1M
- $0.017
- Output (from)
- $0.112 / 1M
Cheapest LLM APIs You Can Call Right Now (2026)
Last refreshed 2026-09-30. Next refresh: weekly.
The cheapest LLM APIs you can call today, ranked by input price with a quality score beside each so you see the trade-off.
Ranking rule. 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.
Related intent. Need no-cost options? Compare the free-model leaderboard separately from paid API pricing.
Verdict
Use Granite 4.0 H Micro for low-cost API calls today.
Ling 3.0 Flash is the runner-up: $0.017 vs $0.021 on Input $/1M.
2ndShortlist
Researched 23d agoLing 3.0 Flash
- Input $/1M
- $0.021
- Output (from)
- $0.063 / 1M
3rdShortlist
Researched 6d agoGLiNER2.5-Decide
- Input $/1M
- $0.030
- Output (from)
- Free
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 | Ling-2.6-Flash Tools Quality watermark: — | $0.01 | $0.03 | |
| 2 | Granite 4.0 H Micro Quality watermark: — | $0.02 | $0.11 | |
| 3 | Aleph Alpha Luminous Base Quality watermark: — | $0.02 | $0.06 | |
| 4 | Together AI - Gemma 3n-e4B Tools Quality watermark: — | $0.02 | $0.04 | |
| 5 | Gemma 3n 4B (free) Quality watermark: — | $0.02 | $0.04 | |
| 6 | Llama 3 8B Instruct Quality watermark: MMLU 76.9% | $0.02 | $0.04 | |
| 7 | Llama 3.1 8B Instruct Quality watermark: — | $0.02 | $0.05 | |
| 8 | Mistral NeMo (2407) Quality watermark: — | $0.02 | $0.03 | |
| 9 | Ling 3.0 Flash ReasoningTools Quality watermark: — | $0.02 | $0.06 | |
| 10 | Llama 3.2 1B Instruct Quality watermark: MMLU 49.3% | $0.03 | $0.10 | |
| 11 | ERNIE Lite Pro Quality watermark: — | $0.03 | $0.06 | |
| 12 | GLiNER2.5-Decide Quality watermark: — | $0.03 | Free | |
| 13 | Granite 3.3 8B Instruct Tools Quality watermark: — | $0.03 | $0.25 | |
| 14 | KAT Coder Pro V1 Tools Quality watermark: — | $0.03 | $1.20 | |
| 15 | LFM2-24B-A2B Tools Quality watermark: — | $0.03 | $0.12 | |
| 16 | Llama 3.2 3B Instruct Quality watermark: — | $0.03 | $0.05 | |
| 17 | Qwen2.5-7B-Instruct Quality watermark: MMLU 81.2% | $0.03 | $0.03 | |
| 18 | Amazon Nova Micro Quality watermark: — | $0.04 | $0.14 | |
| 19 | AutoGLM Phone 9B Multilingual VisionTools Quality watermark: — | $0.04 | $0.14 | |
| 20 | Nova Micro Quality watermark: — | $0.04 | $0.14 |
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.
IBM Granite 3.3 8B with improved reasoning capabilities. Part of IBM's enterprise-focused Granite model family optimized for instruction following.
$0.030
Input $/1M
KAT-Coder-Pro V1 is Kwaipilot's first high-performance agentic coding model, achieving 73.4% on SWE-Bench Verified. It uses a Mixture-of-Experts architecture with approximately 72B active parameters. Context: 256K tokens. Proprietary, available via Vercel AI Gateway and OpenRouter.
$0.030
Input $/1M
LFM2-24B-A2B is the largest model in LiquidAI's LFM-2 hybrid-architecture family, designed for efficient on-device deployment with 24B total parameters and 2B active per token.
$0.030
Input $/1M
Compare Top Picks
Side-by-side comparison of the top picks by price, benchmark, and API access.
Browse Other Categories
Best LLMs for Code GenerationBest LLMs for RAGBest LLMs for Agents vs Agent Products (2026)Best LLMs for ClassificationBest Open Source LLMsBest Multimodal / Vision LLMsBest LLM for Translation in 2026Best AI Image Models in 2026Best AI Video Models in 2026Best LLMs for Reasoning & MathBest Small Language Models (SLMs)Best LLMs for JSON / 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