benchr
For high-volume work such as RAG ingestion, chat routing, and structured extraction, small rate differences add up. The table includes models in the benchr index priced at $1.00 or less per million input tokens, plus open-weight models intended for 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 |
| Qwen3.8-Flash | Alibaba | $0.150 | $0.47 | — |
| GLM-5.3-Flash | Z.ai | $0.150 | $0.50 | Open-weight |
| Mistral Small 4 | Mistral | $0.150 | $0.60 | Open-weight |
| GPT-5.6 Luna | OpenAI | $0.200 | $1.20 | Proprietary |
| GPT-5 Mini | OpenAI | $0.250 | $2.00 | Proprietary |
| DeepSeek-V4.1-Flash | DeepSeek | $0.300 | $1.20 | Not yet recorded |
| Gemini 3.5 Flash-Lite | $0.300 | $2.50 | Proprietary | |
| DeepSeek V4-Flash (hosted API retired Sep 10, 2026) | DeepSeek | $0.440 | $1.32 | 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 |
| DeepSeek V4-Pro | DeepSeek | $1.32 | $3.96 | Open-weight |
One caveat on the DeepSeek rows: those are peak-hour rates. Anything sent outside 01:00–04:00 and 06:00–10:00 UTC on a weekday costs half as much, which puts DeepSeek-V4.1-Flash at $0.15/$0.60 for about four fifths of the week. The V4-Flash row is the last rate the retired hosted model carried. The GLM-5.3-Flash row is the current list rate; its Aug 26–Sep 9 launch promotion billed $0.075/$0.25.
Key Highlights in the Low-Cost Space
- DeepSeek-V4.1-Flash ($0.30/$1.20 peak, $0.15/$0.60 off-peak): The hosted replacement for V4-Flash since September 10, 2026, with a 1M context and 384K max output. Off-peak it is one of the lowest rates in this set; at peak GPT-5.6 Luna is cheaper on input and level on output. benchr has not yet recorded a benchmark figure or license for it.
- DeepSeek V4-Flash (history): It spent most of 2026 as the cheapest million-token context on the market, tripled its input rate on August 16 to $0.44/$1.32 at peak, and was retired from the API on September 10. Its MIT weights remain available for self-hosting.
- GLM-5.3-Flash ($0.15/$0.50): Z.ai's launch promotion of $0.075/$0.25 ran August 26 to September 9, 2026; the list rate since is $0.15 input / $0.50 output, still among the lowest in this set.
- GPT-5.6 Luna ($0.20/$1.20): OpenAI's volume tier, with a 1.05M context. It is cheaper than GPT-5 Mini on both sides of the meter and has the larger window.
- GPT-5 Mini ($0.25/$2.00): OpenAI's low-cost entry with Structured Outputs, Batch API support, a 400K context window, and 128K max output. Measure latency in your deployment; OpenAI does not publish a universal 160 tok/s guarantee.
- 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.