Plan your spend
Monthly cost calculator
Set your token mix and see what each model would cost per month at its cheapest listed provider.
| # | Model | Est. monthly | Relative | In / Out per M |
|---|---|---|---|---|
| 1 | KB Whisperevroc | $0.05 | $0.0023 / $0.0023 | |
| 2 | Voxtral Small 24Bevroc | $0.05 | $0.0023 / $0.0023 | |
| 3 | Whisper 3 Largeopenai | $0.05 | $0.0023 / $0.0023 | |
| 4 | Whisper Large v3 Turboopenai | $0.05 | $0.0023 / $0.0023 | |
| 5 | Whisper Large v3scaleway | $0.06 | $0.0030 / $0 | |
| 6 | Green Sgreenpt | $0.09 | $0.0044 / $0 | |
| 7 | Green S Progreenpt | $0.09 | $0.0044 / $0 | |
| 8 | Voxtral Mini 3Bprivatemode-ai | $0.09 | $0.0046 / $0 | |
| 9 | All-MiniLM-L6-v2digitalocean | $0.18 | $0.0090 / $0 | |
| 10 | Multi-QA-mpnet-base-dot-v1digitalocean | $0.18 | $0.0090 / $0 | |
| 11 | Ling-2.6-flashopenrouter | $0.19 | $0.01 / $0.03 | |
| 12 | BGE Reranker v2 M3digitalocean | $0.20 | $0.01 / $0 | |
| 13 | Qwen 3 Embedding 4Bhuggingface | $0.20 | $0.01 / $0 | |
| 14 | Qwen 3 Embedding 8Bhuggingface | $0.20 | $0.01 / $0 | |
| 15 | Qwen 3 Embedding 4Binference | $0.20 | $0.01 / $0 | |
| 16 | Qwen3 Embedding 0.6Bnearai | $0.20 | $0.01 / $0 | |
| 17 | Qwen3-Embedding-8Bnebius | $0.20 | $0.01 / $0 | |
| 18 | Meta Llama Prompt Guard 2 22Mhelicone | $0.23 | $0.01 / $0.01 | |
| 19 | Meta Llama Prompt Guard 2 86Mhelicone | $0.23 | $0.01 / $0.01 | |
| 20 | Llama 3.2 1B Instructinference | $0.23 | $0.01 / $0.01 | |
| 21 | Qwen3 Reranker 0.6Bnearai | $0.23 | $0.01 / $0.01 | |
| 22 | Google Gemma 2helicone | $0.29 | $0.01 / $0.03 | |
| 23 | Whisper large-v3privatemode-ai | $0.32 | $0.016 / $0 | |
| 24 | Llama 3.1 8B (decentralized)nano-gpt | $0.37 | $0.02 / $0.03 | |
| 25 | text-embedding-3-smallazure-cognitive-services | $0.40 | $0.02 / $0 | |
| 26 | text-embedding-3-smallazure | $0.40 | $0.02 / $0 | |
| 27 | BGE M3digitalocean | $0.40 | $0.02 / $0 | |
| 28 | E5 Large v2digitalocean | $0.40 | $0.02 / $0 | |
| 29 | Mistral Nemo Instruct 2407io-net | $0.40 | $0.02 / $0.04 | |
| 30 | text-embedding-3-smallopenai | $0.40 | $0.02 / $0 |
Estimate uses each model's cheapest listed provider. Cache-hit spend is billed at the provider's cache-read rate when published, otherwise at the input rate.