Inteligencia de modelos de IA

Precios · 2026-06-29

Las APIs de LLM más baratas

Todas las APIs de LLM texto-entrada / texto-salida ordenadas de más barata a más cara.

Acerca de esta lista

  • Ordenación por precio total por token (input + output).
  • Se excluyen modelos con precio $0 ficticio (tiers promocionales, espejos de Github Copilot) — «Desconocido» no es lo mismo que gratis.
  • Usa esta lista para encontrar el proveedor más barato que cumpla tus requisitos de contexto y capacidades.
#ModeloEditorEntrada / 1MSalida / 1MTotalContexto
1BGE Reranker Basecloudflare-ai-gateway$0.003Unknown$0.003128K
2Voxtral Small 24B 2507Mistral$0.002$0.002$0.00532K
3All-MiniLM-L6-v2digitalocean$0.009Unknown$0.009256
4Multi-QA-mpnet-base-dot-v1digitalocean$0.009Unknown$0.009512
5Qwen3 Embedding 8BAlibaba (Qwen)$0.010Unknown$0.01033K
6Qwen3 Embedding 0.6BAlibaba (Qwen)$0.010Unknown$0.01033K
7Qwen3 Embedding 4BAlibaba (Qwen)$0.010Unknown$0.01033K
8BGE Reranker v2 M3digitalocean$0.010Unknown$0.0108K
9BGE M3cloudflare-ai-gateway$0.012Unknown$0.012128K
10PLaMo Embedding 1Bcloudflare-ai-gateway$0.019Unknown$0.019128K
11Llama 3.2 1B InstructMeta$0.010$0.010$0.02060K
12text-embedding-3-smallOpenAI$0.020Unknown$0.0208K
13llama-3.1-nemotron-safety-guard-8b-v3NVIDIA$0.010$0.010$0.020128K
14Prompt Guard 2 86MMeta$0.010$0.010$0.020512
15Llama Prompt Guard 2 22MMeta$0.010$0.010$0.020512
16E5 Large v2digitalocean$0.020Unknown$0.020512
17BGE M3digitalocean$0.020Unknown$0.0208K
18BGE Small EN v1.5cloudflare-ai-gateway$0.020Unknown$0.020128K
19text-embedding-3-smallazure$0.020Unknown$0.0208K
20text-embedding-3-smallazure-cognitive-services$0.020Unknown$0.0208K
21DistilBERT SST-2 INT8cloudflare-ai-gateway$0.026Unknown$0.026128K
22Llama 3.2 3B InstructMeta$0.020$0.020$0.04080K
23PaddleOCR-VLnovita-ai$0.020$0.020$0.04016K
24Ling-2.6-flashopenrouter$0.010$0.030$0.040262K
25Meta-Llama-3.1-8B-InstructMeta$0.020$0.030$0.050128K
26Nomic Embed Text v1.5tinfoil$0.050Unknown$0.0508K
27Meta Llama 3.1 8B Instruct TurboMeta$0.020$0.030$0.050128K
28Mistral NemoMistral$0.020$0.040$0.060128K
29Gemma 3n 4BGoogle$0.020$0.040$0.06033K
30BGE Base EN v1.5cloudflare-ai-gateway$0.067Unknown$0.067128K
31Meta-Llama-3-8B-InstructMeta$0.030$0.040$0.0708K
32Llama Guard 3 8BMeta$0.020$0.060$0.080131K
33Ministral 3B (latest)Mistral$0.040$0.040$0.080128K
34Ministral 3Bazure$0.040$0.040$0.080128K
35Ministral 3Bazure-cognitive-services$0.040$0.040$0.080128K
36Llama 3 8B LunarisMeta$0.040$0.050$0.0908K
37GTE Large (v1.5)digitalocean$0.090Unknown$0.0908K
38Llama-3.2-11B-Vision-InstructMeta$0.049$0.049$0.098128K
39Mistral EmbedMistral$0.100Unknown$0.1008K
40text-embedding-ada-002OpenAI$0.100Unknown$0.1008K
41L3 8B Stheno V3.2novita-ai$0.050$0.050$0.1008K
42Sao10k L3 8B Lunaris novita-ai$0.050$0.050$0.1008K
43text-embedding-ada-002azure$0.100Unknown$0.1008K
44text-embedding-ada-002azure-cognitive-services$0.100Unknown$0.1008K
45Gemma 3 4B ITGoogle$0.040$0.080$0.120128K
46MythoMax 13Bkilo$0.060$0.060$0.1204K
47MythoMax 13Bopenrouter$0.060$0.060$0.1204K
48Sarvam 30Bfastrouter$0.020$0.100$0.120128K
49IBM Granite 4.0 H Microcloudflare-ai-gateway$0.017$0.110$0.127128K
50IBM: Granite 4.0 Microkilo$0.017$0.110$0.127131K
51Granite 4.0 H Microcloudflare-workers-ai$0.017$0.112$0.129131K
52Granite 4.0 Microopenrouter$0.017$0.112$0.129131K
53text-embedding-3-largeOpenAI$0.130Unknown$0.1308K
54Llama 3.1 8BMeta$0.050$0.080$0.130131K
55text-embedding-3-largeazure$0.130Unknown$0.1308K
56text-embedding-3-largeazure-cognitive-services$0.130Unknown$0.1308K
57Sarvam 30Bnano-gpt$0.028$0.111$0.13966K
58Google Gemma 3 27B InstructGoogle$0.030$0.110$0.140203K
59baichuan-m2-32bnovita-ai$0.070$0.070$0.140131K
60Model Routerazure$0.140Unknown$0.140128K
61Model Routerazure-cognitive-services$0.140Unknown$0.140128K
62Google Gemma 3 12BGoogle$0.050$0.100$0.150131K
63Gemini Embedding 001Google$0.150Unknown$0.1502K
64LiquidAI: LFM2-24B-A2Bkilo$0.030$0.120$0.15033K
65LFM2-24B-A2Btogetherai$0.030$0.120$0.15033K
66LFM2-24B-A2Bopenrouter$0.030$0.120$0.15033K
67LFM2 24B A2Bnano-gpt$0.030$0.120$0.15033K
68IBM: Granite 4.1 8Bkilo$0.050$0.100$0.150131K
69Granite 4.1 8Bopenrouter$0.050$0.100$0.150131K
70Granite 4.1 8Bnano-gpt$0.050$0.100$0.150131K
71DeepSeek R1 Distill Llama 70BMeta$0.030$0.130$0.16033K
72gpt-oss-20bOpenAI$0.029$0.140$0.169128K
73R1 Distill Llama 70BDeepSeek$0.030$0.140$0.1708K
74Qwen3 235B A22B 2507Alibaba (Qwen)$0.071$0.100$0.171262K
75Nova Microvercel$0.035$0.140$0.175128K
76Amazon: Nova Micro 1.0kilo$0.035$0.140$0.175128K
77Nova Microamazon-bedrock$0.035$0.140$0.175128K
78Nova Micro 1.0openrouter$0.035$0.140$0.175128K
79Amazon Nova Micro 1.0nano-gpt$0.036$0.139$0.175128K
80gpt-oss-120bOpenAI$0.030$0.150$0.180128K

Mostrando los 80 primeros de 977. Ver el resto en el directorio completo.

Frequently asked questions

What is the cheapest LLM API right now?

BGE Reranker Base is the lowest-priced AI APIs on this list, at $0.003 per 1M input tokens and Unknown 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 actualización:

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.