Best Models
Gemma 3n E4B Instruct is currently the highest-ranked model for Input Price in the available data.
Use the top-ranked model as a starting point, not an automatic decision.
Compare the top choices on price, speed, availability, and your own constraints.
Open the linked result page and methodology before quoting the ranking.
Provider price for processing 1M input tokens, such as prompts and context sent to the model. Lower is cheaper.
| Rank | Model | Provider | Value |
|---|---|---|---|
| #1 | Gemma 3n E4B Instruct | $0.02 / 1M | |
| #2 | Sarvam 30B (high) | Sarvam | $0.026 / 1M |
| #3 | Qwen3.5 4B (Non-reasoning) | Alibaba | $0.03 / 1M |
| #4 | Qwen3.5 4B (Reasoning) | Alibaba | $0.03 / 1M |
| #5 | Granite 3.3 8B (Non-reasoning) | IBM | $0.03 / 1M |
This answer uses the exact same metric and live database ranking as the linked Easy Benchmarks leaderboard.
Source: Artificial Analysis Input Price. Updated: Jul 16, 2026.
| #6 | Nova Micro | Amazon | $0.035 / 1M |
| #7 | NVIDIA Nemotron Nano 9B V2 (Reasoning) | NVIDIA | $0.04 / 1M |
| #8 | HyperNova 60B 2605 | Multiverse Computing | $0.04 / 1M |
| #9 | Sarvam 105B (high) | Sarvam | $0.042 / 1M |
| #10 | Llama 3 Instruct 8B | Meta | $0.045 / 1M |
| #11 | gpt-oss-20b (high) | OpenAI | $0.05 / 1M |
| #12 | NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) | NVIDIA | $0.05 / 1M |
| #13 | NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) | NVIDIA | $0.05 / 1M |
| #14 | NVIDIA Nemotron Nano 9B V2 (Non-reasoning) | NVIDIA | $0.05 / 1M |
| #15 | Granite 4.1 8B | IBM | $0.05 / 1M |
| #16 | GPT-5 nano (minimal) | OpenAI | $0.05 / 1M |
| #17 | GPT-5 nano (medium) | OpenAI | $0.05 / 1M |
| #18 | GPT-5 nano (high) | OpenAI | $0.05 / 1M |
| #19 | Llama 2 Chat 7B | Meta | $0.05 / 1M |
| #20 | Qwen2.5 Turbo | Alibaba | $0.05 / 1M |