benchr
For high-volume tasks such as RAG document ingestion, user chat routing, and structured data extraction, choosing a budget-friendly model is essential. Below is the ranked list of all models on benchr that cost **$1.00 or less per million input tokens**, or are open-weights intended for free self-hosting.
| Model | Provider | Input / 1M | Output / 1M | License |
|---|---|---|---|---|
| Qwen3.6-27B | Alibaba | Self-hosted | Self-hosted | Open-weight |
| Llama 4 Maverick | Meta | Self-hosted | Self-hosted | Open-weight |
| Llama 4 Scout | Meta | Self-hosted | Self-hosted | Open-weight |
| Phi-4 | Microsoft | Self-hosted | Self-hosted | Open-weight |
| DeepSeek V4-Flash | DeepSeek | $0.140 | $0.280 | Open-weight |
| GPT-5 Mini | OpenAI | $0.250 | $2.00 | Proprietary |
| DeepSeek V4-Pro | DeepSeek | $0.435 | $0.870 | Open-weight |
| Mistral Large 3 | Mistral | $0.500 | $1.50 | Open-weight |
| Kimi K2.6 | Moonshot AI | $0.950 | $4.00 | Open-weight |
| Claude Haiku 4.5 | Anthropic | $1.00 | $5.00 | Proprietary |
Key Highlights in the Low-Cost Space
- DeepSeek V4-Flash ($0.14/$0.28): Disrupted the market by offering a million-token context window at a fraction of standard API prices. It holds strong coding and reasoning scores despite its speed and low cost.
- GPT-5 Mini ($0.25/$2.00): OpenAI's primary low-cost entry, offering high speed (160 tok/s) and full API feature integration (such as Structured Outputs and Batch Jobs).
- Claude Haiku 4.5 ($1.00/$5.00): While pricier than DeepSeek and GPT-5 Mini, it features high prompt caching capabilities and Anthropic's signature safety and formatting alignment.
Want to compare these with the flagship models? Check out the full AI Model Rankings or compute exact volume pricing on our Cost Calculator.
When cheap stops being cheap
The cheapest API is not always the lowest-cost system. A model with a lower token price can still lose if it requires more retries, produces longer-than-needed answers, misses formatting constraints, or needs more human review. For production, the useful metric is cost per accepted answer.
For high-volume routing, extraction, and classification, budget models can be excellent because the task is narrow and failure is easy to detect. For legal review, complex code repair, research synthesis, or agent loops with side effects, pay attention to failure cost before optimizing the token bill.
A practical shortlist strategy
For most teams, the cheapest-model search should produce a shortlist, not a single winner. Pick one model below $0.50/1M input, one between $0.50 and $1.50, and one stronger fallback above that. Route easy work to the cheapest tier and escalate only when confidence, formatting, or safety checks fail.
This keeps the system cheap without betting the whole product on the lowest line in the table. It also gives you a migration path: if the budget model improves, increase its traffic; if it fails on an edge case, the fallback path is already defined.
Keep provider concentration in mind too. Saving a few dollars per million tokens is not worth losing redundancy if the workload is business-critical. For important systems, pair the cheapest default with a second provider that can take over when latency, rate limits, or availability degrade.