Inteligência em modelos de IA

Preços · 2026-11-12

As APIs de LLM mais baratas

Todas as APIs de LLM texto-entrada / texto-saída ordenadas da mais barata à mais cara.

Sobre esta lista

  • Ordenação por preço total por token (input + output).
  • Modelos com preço $0 fictício (tiers promocionais, espelhos do Github Copilot) são excluídos — «Desconhecido» não é o mesmo que grátis.
  • Use esta lista para encontrar o provedor mais barato que atenda seus requisitos de contexto e recursos.
#ModeloFornecedorEntrada / 1MSaída / 1MTotalContexto
1Qwen3.8 27BAlibaba (Qwen)$0.001$0.001$0.0021.05M
2Ambient Smallambient$0.001$0.001$0.002101K
3Multi-QA-mpnet-base-dot-v1digitalocean$0.009Unknown$0.009512
4All-MiniLM-L6-v2digitalocean$0.009Unknown$0.009256
5Qwen3 Embedding 8BAlibaba (Qwen)$0.010Unknown$0.01033K
6Qwen3 Embedding 4BAlibaba (Qwen)$0.010Unknown$0.01033K
7BGE Reranker V2 M3novita-ai$0.010Unknown$0.0108K
8BGE M3novita-ai$0.010Unknown$0.0108K
9BGE Reranker v2 M3digitalocean$0.010Unknown$0.0108K
10Nomic Embed Text v1.5tinfoil$0.016Unknown$0.0168K
11Llama 3.2 1B InstructMeta$0.010$0.010$0.02060K
12Qwen3 Embedding 0.6BAlibaba (Qwen)$0.010$0.010$0.02033K
13Prompt Guard 2 86MMeta$0.010$0.010$0.020512
14Llama Prompt Guard 2 22MMeta$0.010$0.010$0.020512
15text-embedding-3-smallOpenAI$0.020Unknown$0.0208K
16text-embedding-3-smallazure-cognitive-services$0.020Unknown$0.0208K
17E5 Large v2digitalocean$0.020Unknown$0.020512
18BGE M3digitalocean$0.020Unknown$0.0208K
19text-embedding-3-smallazure$0.020Unknown$0.0208K
20amazon--titan-embed-textsap-ai-core$0.020Unknown$0.0208K
21text-embedding-3-smallsap-ai-core$0.020Unknown$0.0208K
22GLiNER 2.5 Basepioneer$0.030Unknown$0.0304K
23GLiNER2 Multi Largepioneer$0.030Unknown$0.0308K
24GLiNER-2.5-Decidepioneer$0.030Unknown$0.0308K
25GLiNER2 Basepioneer$0.030Unknown$0.0302K
26GLiNER2 Privacy Filter PII (Multi)pioneer$0.030Unknown$0.0308K
27GLiNER2 Largepioneer$0.030Unknown$0.0308K
28GLiNER2 Multipioneer$0.030Unknown$0.0308K
29GLiNER 2.5 Multipioneer$0.030Unknown$0.0304K
30Llama 3.2 3B InstructMeta$0.020$0.020$0.040131K
31PaddleOCR VLnovita-ai$0.020$0.020$0.04016K
32Extractopenrouter$0.040Unknown$0.0401M
33Summarizeopenrouter$0.040Unknown$0.0401M
34Gemma 4 26B A4B ITGoogle$0.010$0.031$0.041262K
35Llama-3.1-8B-InstructMeta$0.020$0.030$0.050131K
36ScaleDown: Extractkilo$0.050Unknown$0.0501M
37ScaleDown: Summarizekilo$0.050Unknown$0.0501M
38Extract-1vercel$0.050Unknown$0.0501M
39Summarize-1vercel$0.050Unknown$0.0501M
40Meta Llama 3.1 8B Instruct TurboMeta$0.020$0.030$0.050128K
41Mistral NemoMistral$0.029$0.030$0.059131K
42DeepSeek OCR 2DeepSeek$0.030$0.030$0.0608K
43Mistral NemoMistral$0.020$0.040$0.06016K
44inclusionAI: Ling 3.0 Tinykilo$0.015$0.045$0.060262K
45Ling 3.0 Tinynano-gpt$0.015$0.045$0.060262K
46Ling 3.0 Tiny Thinkingnano-gpt$0.015$0.045$0.060262K
47Ling 3.0 Tinyopenrouter$0.015$0.045$0.060262K
48Ministral 3Bazure-cognitive-services$0.040$0.040$0.080128K
49Ministral 3Bazure$0.040$0.040$0.080128K
50Ling 3.0 Flashvercel$0.021$0.063$0.084256K
51Ling 3.0 Flashopenrouter$0.021$0.063$0.084262K
52Gemma 3 4B ITGoogle$0.040$0.050$0.090131K
53Llama 3 8B LunarisMeta$0.040$0.050$0.0908K
54GTE Large (v1.5)digitalocean$0.090Unknown$0.0908K
55Qwen3.5 9BAlibaba (Qwen)$0.040$0.060$0.100262K
56Mistral EmbedMistral$0.100Unknown$0.1008K
57Qwen2.5 7B Instruct (Deep Infra)Alibaba (Qwen)$0.050$0.050$0.10033K
58text-embedding-ada-002OpenAI$0.100Unknown$0.1008K
59text-embedding-ada-002azure-cognitive-services$0.100Unknown$0.1008K
60text-embedding-ada-002azure$0.100Unknown$0.1008K
61gpt-oss-20bOpenAI$0.018$0.090$0.108131K
62Llama-3.2-11B-Vision-Instruct (Deep Infra)Meta$0.055$0.055$0.110131K
63Llama-Guard-3-8B (Cloudflare)Meta$0.055$0.055$0.110131K
64Qwen3.5 4BAlibaba (Qwen)$0.040$0.070$0.110262K
65GLM Flash LatestZ.AI / Zhipu$0.040$0.078$0.1181.05M
66Nex AGI: Nex-N2.5-Minikilo$0.025$0.100$0.125262K
67Nex N2.5 Mininano-gpt$0.025$0.100$0.125262K
68Nex-N2.5-Miniopenrouter$0.025$0.100$0.125262K
69Granite 4.0 H Microcloudflare-workers-ai$0.017$0.112$0.129131K
70Mistral Small 3Mistral$0.050$0.080$0.13033K
71text-embedding-3-largeOpenAI$0.130Unknown$0.1308K
72Llama 3.1 8BMeta$0.050$0.080$0.130131K
73text-embedding-3-largeazure-cognitive-services$0.130Unknown$0.1308K
74Synth 2.5 Flash Previewnano-gpt$0.030$0.100$0.13030K
75text-embedding-3-largeazure$0.130Unknown$0.1308K
76text-embedding-3-largesap-ai-core$0.130Unknown$0.1308K
77DeepSeek V4 Flash 0731DeepSeek$0.045$0.090$0.1351.05M
78Model Routerazure-cognitive-services$0.140Unknown$0.140200K
79Baichuan M2 32Bnovita-ai$0.070$0.070$0.140131K
80Model Routerazure$0.140Unknown$0.140200K

Mostrando os 80 primeiros de 1576. Ver o resto no diretório completo.

Frequently asked questions

What is the cheapest LLM API right now?

Qwen3.8 27B is the lowest-priced AI APIs on this list, at $0.001 per 1M input tokens and $0.001 per 1M output tokens. The total column above sums input + output per 1M tokens for direct comparison.

Why are prices shown per 1M tokens?

Almost every commercial LLM provider publishes rates per million tokens. Per-1K-tokens or per-token rates are easy to misread (off by 1000×). Standardising on $/1M lets you compare vendors directly.

Are these prices including or excluding tax?

All prices are the provider's headline list rate in USD, before any volume discounts, prepaid credits, batch-API discounts, prompt-caching discounts or jurisdictional sales tax. Always verify with the provider before committing to a budget.

How often do these prices change?

Vendor list-price moves are typically picked up within hours of an announcement, and our pipeline re-syncs daily. Each change is also written to /changelog so you can audit historical pricing over time.

Why are some models showing 'Unknown' instead of a price?

We deliberately do not coerce missing data to $0. 'Unknown' means the provider does not publish a public rate (often models behind enterprise sales or invite-only access). Treating Unknown as free would push paid-but-unpriced models to the top of every cheap list — broken UX and broken SEO.

Última atualização:

Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.

Pricing and capabilities are refreshed daily and reconciled against each provider's official documentation. Always verify critical production decisions with the provider directly.