Intelligence des modèles d'IA

Tarifs · 2026-09-28

Les APIs LLM les moins chères

Toutes les APIs LLM texte-entrée / texte-sortie classées de la moins chère à la plus chère.

À propos de cette liste

  • Classement par prix total par token (input + output).
  • Les modèles à prix $0 fictif (tiers promotionnels, miroirs Github Copilot) sont exclus — « Inconnu » ne signifie pas gratuit.
  • Utilisez cette liste pour trouver le fournisseur le moins cher répondant à vos besoins de contexte et de fonctionnalités.
#ModèleÉditeurEntrée / 1MSortie / 1MTotalContexte
1Voxtral Small 24B 2507Mistral$0.002$0.002$0.00533K
2All-MiniLM-L6-v2digitalocean$0.009Unknown$0.009256
3Multi-QA-mpnet-base-dot-v1digitalocean$0.009Unknown$0.009512
4Qwen3 Embedding 8BAlibaba (Qwen)$0.010Unknown$0.01033K
5Qwen3 Embedding 4BAlibaba (Qwen)$0.010Unknown$0.01033K
6BGE Reranker v2 M3digitalocean$0.010Unknown$0.0108K
7Llama 3.2 1B InstructMeta$0.010$0.010$0.02060K
8Qwen3 Embedding 0.6BAlibaba (Qwen)$0.010$0.010$0.02033K
9Prompt Guard 2 86MMeta$0.010$0.010$0.020512
10Llama Prompt Guard 2 22MMeta$0.010$0.010$0.020512
11text-embedding-3-smallOpenAI$0.020Unknown$0.0208K
12text-embedding-3-smallazure$0.020Unknown$0.0208K
13text-embedding-3-smallazure-cognitive-services$0.020Unknown$0.0208K
14text-embedding-3-smallsap-ai-core$0.020Unknown$0.0208K
15BGE M3digitalocean$0.020Unknown$0.0208K
16E5 Large v2digitalocean$0.020Unknown$0.020512
17Llama 3.2 3B InstructMeta$0.020$0.020$0.040131K
18PaddleOCR-VLnovita-ai$0.020$0.020$0.04016K
19Llama-3.1-8B-InstructMeta$0.020$0.030$0.050131K
20Mistral NemoMistral$0.020$0.030$0.05016K
21Nomic Embed Text v1.5tinfoil$0.050Unknown$0.0508K
22Meta Llama 3.1 8B Instruct TurboMeta$0.020$0.030$0.050128K
23DeepSeek OCR 2DeepSeek$0.030$0.030$0.0608K
24nvidia--llama-3.2-nv-embedqa-1bMeta$0.070Unknown$0.0708K
25Llama 3.2 3B Instruct (NovitaAI)novita$0.030$0.050$0.08033K
26Llama 3 8B InstructMeta$0.040$0.040$0.0808K
27Ministral 3Bazure$0.040$0.040$0.080128K
28Ministral 3Bazure-cognitive-services$0.040$0.040$0.080128K
29Ministral 3B (latest)Mistral$0.040$0.040$0.080128K
30Ling 3.0 Flash VLopenrouter$0.021$0.062$0.083262K
31Ling 3.0 Flashopenrouter$0.021$0.063$0.084262K
32Ling 3.0 Flashvercel$0.021$0.063$0.084256K
33Llama 3 8B LunarisMeta$0.040$0.050$0.0908K
34text-embedding-3-largesap-ai-core$0.090Unknown$0.0908K
35GTE Large (v1.5)digitalocean$0.090Unknown$0.0908K
36Mistral EmbedMistral$0.100Unknown$0.1008K
37text-embedding-ada-002OpenAI$0.100Unknown$0.1008K
38L3 8B Stheno V3.2novita-ai$0.050$0.050$0.1008K
39Sao10k L3 8B Lunaris novita-ai$0.050$0.050$0.1008K
40text-embedding-ada-002azure$0.100Unknown$0.1008K
41text-embedding-ada-002azure-cognitive-services$0.100Unknown$0.1008K
42DeepSeek V4 Flash 0731DeepSeek$0.035$0.070$0.1051.31M
43gpt-oss-20bOpenAI$0.018$0.090$0.108131K
44Llama 3.2 11B Vision InstructMeta$0.055$0.055$0.110128K
45Llama Guard 3 8BMeta$0.055$0.055$0.110131K
46Qwen3.5 4BAlibaba (Qwen)$0.040$0.070$0.110262K
47Gemma 3 4B ITGoogle$0.040$0.080$0.120131K
48GPT OSS 20B (FlexAI)edenai$0.020$0.100$0.120131K
49Sarvam 30Bfastrouter$0.020$0.100$0.120128K
50Granite 4.0 H Microcloudflare-workers-ai$0.017$0.112$0.129131K
51IBM: Granite 4.0 Microkilo$0.017$0.112$0.129131K
52Granite 4.0 Microopenrouter$0.017$0.112$0.129131K
53Mistral Small 3Mistral$0.050$0.080$0.13033K
54Llama 3.1 8BMeta$0.050$0.080$0.130131K
55text-embedding-3-largeOpenAI$0.130Unknown$0.1308K
56text-embedding-3-largeazure$0.130Unknown$0.1308K
57text-embedding-3-largeazure-cognitive-services$0.130Unknown$0.1308K
58amazon--nova-microsap-ai-core$0.030$0.100$0.130128K
59baichuan-m2-32bnovita-ai$0.070$0.070$0.140131K
60Model Routerazure$0.140Unknown$0.140200K
61Model Routerazure-cognitive-services$0.140Unknown$0.140200K
62amazon--titan-embed-textsap-ai-core$0.140Unknown$0.1408K
63Gemma 3 12B ITGoogle$0.050$0.100$0.150131K
64Gemini Embedding 001Google$0.150Unknown$0.1502K
65LFM2 24B A2Bpioneer$0.030$0.120$0.15033K
66LFM2-24B-A2Btogetherai$0.030$0.120$0.15033K
67Mellum2 12B A2.5Bwandb$0.050$0.100$0.150131K
68Granite 4.1 8Bwandb$0.050$0.100$0.150131K
69Qwen3.7 FlashAlibaba (Qwen)$0.030$0.130$0.1601M
70DeepSeek R1 Distill Llama 70BMeta$0.030$0.130$0.160128K
71R1 Distill Llama 70BDeepSeek$0.030$0.140$0.1708K
72GPT OSS 120Bllmgateway$0.032$0.140$0.172131K
73Amazon: Nova Micro 1.0kilo$0.035$0.140$0.175128K
74Nova Micro 1.0openrouter$0.035$0.140$0.175128K
75Nova Microvercel$0.035$0.140$0.175128K
76Nova Microedenai$0.035$0.140$0.175128K
77Nova Micro (US)edenai$0.035$0.140$0.175128K
78Nova Microamazon-bedrock$0.035$0.140$0.175128K
79Nova Micro (US)amazon-bedrock$0.035$0.140$0.175128K
80Phi 4 Multimodalnano-gpt$0.070$0.110$0.180128K

Top 80 sur 1458 affichés. Voir le reste dans le répertoire complet.

Frequently asked questions

What is the cheapest LLM API right now?

Voxtral Small 24B 2507 is the lowest-priced AI APIs on this list, at $0.002 per 1M input tokens and $0.002 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.

Dernière mise à jour :

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.