Value for money
What you actually get for your dollar
Price is only half the story. Below: the lowest cost per million tokens from our catalog of 4,880 priced models, and, as the community grows, the real cost per successful task. The cheapest model is not always the best value.
Lowest cost per million tokens
Blended price at a fixed 3:1 input-to-output ratio, text models, from the live catalog.
| # | Model | Provider | Input | Output | Blended |
|---|---|---|---|---|---|
| 1 | perplexity/pplx-decider-flash-v1.2 | perplexity | $0.01 | $0.00 | $0.008 |
| 2 | perplexity/pplx-decider-flash-latest | perplexity | $0.01 | $0.00 | $0.008 |
| 3 | baseten/decision-models/baseten-joey-2b-latest | baseten | $0.01 | $0.00 | $0.008 |
| 4 | nscale/Qwen/Qwen2.5-Coder-3B-Instruct | nscale | $0.01 | $0.03 | $0.015 |
| 5 | nscale/Qwen/Qwen2.5-Coder-7B-Instruct | nscale | $0.01 | $0.03 | $0.015 |
| 6 | nebius/Qwen/Qwen2.5-Coder-7B | nebius | $0.01 | $0.03 | $0.015 |
| 7 | perplexity/pplx-decider-v1-27b | perplexity | $0.02 | $0.00 | $0.015 |
| 8 | perplexity/pplx-decider-v1.1-27b | perplexity | $0.02 | $0.00 | $0.015 |
| 9 | perplexity/pplx-decider-v1.2 | perplexity | $0.02 | $0.00 | $0.015 |
| 10 | perplexity/pplx-decider-latest | perplexity | $0.02 | $0.00 | $0.015 |
| 11 | empiriolabs/aplomb-1 | empiriolabs | $0.02 | $0.00 | $0.015 |
| 12 | lambda_ai/llama3.2-11b-vision-instruct | lambda_ai | $0.02 | $0.03 | $0.018 |
| 13 | lambda_ai/llama3.2-3b-instruct | lambda_ai | $0.02 | $0.03 | $0.018 |
| 14 | deepinfra/meta-llama/Llama-3.2-3B-Instruct | deepinfra | $0.02 | $0.02 | $0.020 |
| 15 | novita/paddlepaddle/paddleocr-vl | novita | $0.02 | $0.02 | $0.020 |
| 16 | novita/meta-llama/llama-3.2-1b-instruct | novita | $0.02 | $0.02 | $0.020 |
| 17 | together_ai/Qwen/Qwen2-1.5B-Instruct | together_ai | $0.02 | $0.02 | $0.020 |
| 18 | nace/drex-v1.0 | nace | $0.03 | $0.00 | $0.023 |
| 19 | nace/drex-v1.5 | nace | $0.03 | $0.00 | $0.023 |
| 20 | nace/drex-v2.0 | nace | $0.03 | $0.00 | $0.023 |
Lowest price is not the same as best value. A cheaper model that fails more often can cost more per finished task. That is what the next section measures.
From the community
Real-world value for money
Cost per successful task, success rate, average quality, and latency, aggregated across everyone who opts in. Anonymized, and only shown when enough people contribute. Last 30 days.
This fills in as the community grows
Send the optional success,
quality_score, and
latency_ms fields with your events
and we can show which models are actually worth it, not just which are cheapest. The more people who do, the sharper this gets.
Cost per success = total spend divided by tasks reported successful. We never show a model unless enough separate contributors reported it. See the community dashboard for usage totals.