Cheapest models with 128K context
206 models qualify. This ranking is ordered by blended 3:1 price among models with at least 128K context, using input and output prices from the index.
What the data shows
The spread runs from about $6.22 to $43.66 per million tokens on a blended 3:1 basis. The median across the set is $24.25.
The top of the list mixes small models with long-context models. A low blended price and a 128K window do not usually arrive together, so the leaders are worth checking on the benchmarks that matter to you.
How to read the ranking
Blended price weights input and output at 3:1. If your workload is output-heavy, the ranking can change, so check the output price column as well.
- Filter by context window before comparing price.
- Check whether the model is open weights or API-only.
- Test the cheapest candidate on your own task before switching.
- Keep a fallback model for quality-sensitive requests.
Blended 3:1 price among models with at least 128K context
| # | Model | Provider | Input / 1M | Output / 1M | Context | Avg score |
|---|---|---|---|---|---|---|
| 1 | Llama 3 Baseten | Baseten | $3.62 | $14.04 | 128,000 | 74.9 |
| 2 | Llama 3 Replicate | Replicate | $3.75 | $13.86 | 200,000 | 75.7 |
| 3 | Gemma 3 Instruct | Google DeepMind | $3.72 | $14.33 | 128,000 | 74.1 |
| 4 | Llama 3 DeepInfra | DeepInfra | $3.67 | $14.87 | 128,000 | 74.0 |
| 5 | Llama 3 Anyscale Instruct | Anyscale | $3.91 | $14.49 | 200,000 | 75.7 |
| 6 | Llama 3 DeepInfra Chat | DeepInfra | $3.74 | $15.32 | 200,000 | 75.0 |
| 7 | Llama 3.1 Cerebras | Cerebras | $4.01 | $15.13 | 128,000 | 76.0 |
| 8 | Llama 3 Baseten Chat | Baseten | $3.55 | $16.64 | 200,000 | 73.2 |
| 9 | Mistral Small 3 Chat | Mistral AI | $3.54 | $16.77 | 200,000 | 73.7 |
| 10 | Llama 3 Hyperbolic Chat | Hyperbolic | $3.64 | $16.55 | 200,000 | 75.1 |
| 11 | Llama 3 Hyperbolic Instruct | Hyperbolic | $3.79 | $16.16 | 200,000 | 76.2 |
| 12 | Llama 3.1 | Meta AI | $4.16 | $15.79 | 200,000 | 76.3 |
| 13 | Llama 3.1 Instruct | Meta AI | $4.05 | $16.24 | 200,000 | 75.7 |
| 14 | Phi-4 Instruct | Microsoft | $3.79 | $17.11 | 128,000 | 75.3 |
| 15 | Llama 3 Replicate Chat | Replicate | $3.74 | $17.46 | 200,000 | 74.7 |
| 16 | Magistral Chat | Mistral AI | $4.33 | $16.06 | 128,000 | 76.8 |
| 17 | Llama 3 Novita | Novita AI | $3.70 | $18.84 | 128,000 | 74.4 |
| 18 | Hunyuan-Large Base | Tencent | $3.64 | $19.08 | 200,000 | 74.0 |
| 19 | Qwen3-Coder Base | Alibaba Cloud | $3.99 | $18.04 | 200,000 | 76.6 |
| 20 | Command R+ Instruct | Cohere | $4.16 | $17.58 | 200,000 | 76.2 |
Methodology
This story uses the AI & LLM Index dataset: 600 models, 40 providers and 12 benchmarks. Prices are listed per million tokens. Scores are modelled estimates on a 0–100 scale and are not official benchmark results. Figures are rounded for readability.
Related
FAQ
What does the Cheapest models with 128K context data show?
206 models qualify. This ranking is ordered by blended 3:1 price among models with at least 128K context, using input and output prices from the index.
Are the numbers official?
No. Prices and scores are compiled for this demo index. Benchmark values are modelled estimates, not official results. Verify figures with the provider or benchmark owner before making decisions.
How should I use this ranking?
Use it to form a shortlist. Check the specific model pages, compare price and context, and test the shortlist on your own examples before committing.