Fournisseur · 2026-05-12
vercel
| Modèle | Entrée / 1M | Sortie / 1M | Contexte | Fournisseurs | Tags |
|---|---|---|---|---|---|
| Titan Text Embeddings V2 | $0.020 | Unknown | 8K | 1 | — |
| Nova Micro | $0.035 | $0.140 | 128K | 1 | tools |
| Trinity Mini | $0.050 | $0.150 | 131K | 1 | — |
| Nova Lite | $0.060 | $0.240 | 300K | 1 | tools · vision |
| Trinity Large Thinking | $0.250 | $0.900 | 262K | 1 | tools · reasoning · open-weights |
| Trinity Large Preview | $0.250 | $1.00 | 131K | 1 | tools |
| INTELLECT 3 | $0.200 | $1.10 | 131K | 1 | tools · reasoning |
| Nova 2 Lite | $0.300 | $2.50 | 1M | 1 | reasoning · vision |
| Nova Pro | $0.800 | $3.20 | 300K | 1 | tools · vision |
| Interfaze Beta | $1.50 | $3.50 | 1M | 1 | reasoning |
| v0-1.5-md | $3.00 | $15.00 | 128K | 1 | tools · reasoning · vision |
| v0-1.0-md | $3.00 | $15.00 | 128K | 1 | tools · reasoning · vision |
| Text Embedding 005dérivé | $0.030 | Unknown | 8K | 1 | — |
| Text Multilingual Embedding 002dérivé | $0.030 | Unknown | 8K | 1 | — |
| Ministral 3B (latest)dérivé | $0.040 | $0.040 | 128K | 1 | tools · open-weights |
| Embed v4.0dérivé | $0.120 | Unknown | 8K | 1 | — |
| Codestral Embeddérivé | $0.150 | Unknown | 8K | 1 | — |
| Ministral 8B (latest)dérivé | $0.100 | $0.100 | 128K | 1 | tools · open-weights |
| Qwen3-14Bdérivé | $0.060 | $0.240 | 41K | 1 | tools · reasoning |
| Qwen3-30B-A3Bdérivé | $0.080 | $0.290 | 41K | 1 | tools · reasoning |
| Qwen 3.32Bdérivé | $0.100 | $0.300 | 41K | 1 | tools · reasoning |
| Ministral 14Bdérivé | $0.200 | $0.200 | 256K | 1 | vision |
| Devstral Small 1.1dérivé | $0.100 | $0.300 | 128K | 1 | tools |
| Qwen3 235B A22B Instruct 2507dérivé | $0.130 | $0.600 | 41K | 1 | tools |
| Mistral Small (latest)dérivé | $0.150 | $0.600 | 256K | 1 | tools · reasoning · vision · open-weights |
| Nvidia Nemotron Nano 12B V2 VLdérivé | $0.200 | $0.600 | 131K | 1 | tools · reasoning · vision |
| Codestral (latest)dérivé | $0.300 | $0.900 | 256K | 1 | tools · open-weights |
| Mistral Large 3dérivé | $0.500 | $1.50 | 256K | 1 | vision |
| Seed 1.6dérivé | $0.250 | $2.00 | 256K | 1 | tools · reasoning |
| Seed 1.8dérivé | $0.250 | $2.00 | 256K | 1 | tools · reasoning · vision |
| Mistral Medium 3.1dérivé | $0.400 | $2.00 | 128K | 1 | tools · vision |
| MiniMax M2.1 Lightningdérivé | $0.300 | $2.40 | 205K | 1 | tools · reasoning |
| Qwen3 235B A22B Thinking 2507dérivé | $0.300 | $2.90 | 262K | 1 | tools · reasoning · vision |
| Qwen3 VL Instructdérivé | $0.700 | $2.80 | 131K | 1 | tools · vision · open-weights |
| Sonar Reasoningdérivé | $1.00 | $5.00 | 127K | 1 | reasoning |
| Magistral Medium (latest)dérivé | $2.00 | $5.00 | 128K | 1 | tools · reasoning · open-weights |
| Qwen 3 Max Thinkingdérivé | $1.20 | $6.00 | 256K | 1 | tools · reasoning · open-weights |
| Codex Minidérivé | $1.50 | $6.00 | 200K | 1 | tools · reasoning · vision |
| Grok 4.20 Non-Reasoningdérivé | $2.00 | $6.00 | 2M | 1 | tools · vision |
| Grok 4.20 Beta Non-Reasoningdérivé | $2.00 | $6.00 | 2M | 1 | tools · vision |
| Grok 4.20 Reasoningdérivé | $2.00 | $6.00 | 2M | 1 | tools · reasoning · vision |
| Grok 4.20 Multi Agent Betadérivé | $2.00 | $6.00 | 2M | 1 | tools · reasoning |
| Grok 4.20 Beta Reasoningdérivé | $2.00 | $6.00 | 2M | 1 | tools · reasoning · vision |
| Pixtral Large (latest)dérivé | $2.00 | $6.00 | 128K | 1 | tools · vision · open-weights |
| Qwen 3.6 Max Previewdérivé | $1.30 | $7.80 | 240K | 1 | tools · reasoning · vision · open-weights |
| Qwen3 VL Thinkingdérivé | $0.700 | $8.40 | 131K | 1 | tools · reasoning · vision · open-weights |
| GPT 5.1 Thinkingdérivé | $1.25 | $10.00 | 400K | 1 | tools · reasoning · vision |
| GPT-5.1 Instantdérivé | $1.25 | $10.00 | 128K | 1 | tools · reasoning · vision |
| Kimi K2 Turbodérivé | $2.40 | $10.00 | 256K | 1 | tools |
| Nano Banana Pro (Gemini 3 Pro Image)dérivé | $2.00 | $120.00 | 66K | 1 | — |
| Devstral 2dérivé | Inconnu | Inconnu | 256K | 1 | tools |
| Devstral Small 2dérivé | Inconnu | Inconnu | 256K | 1 | tools |
| Gemini Embedding 2dérivé | Inconnu | Inconnu | Unknown | 1 | — |
| Grok Imagine Imagedérivé | Inconnu | Inconnu | Unknown | 1 | — |
| Grok Imagine Image Prodérivé | Inconnu | Inconnu | Unknown | 1 | — |
| Imagen 4dérivé | Inconnu | Inconnu | 480 | 1 | — |
| Imagen 4 Fastdérivé | Inconnu | Inconnu | 480 | 1 | — |
| Imagen 4 Ultradérivé | Inconnu | Inconnu | 480 | 1 | — |
Frequently asked questions
How many AI models does vercel offer?
We track 12 canonical vercel models plus 46 community fine-tunes / derivatives (excluded from the main table). The list is recomputed daily from models.dev.
Which vercel model is the cheapest?
Titan Text Embeddings V2 is currently the lowest-priced vercel model, at $0.020 per 1M input tokens and Unknown per 1M output tokens. For the full apples-to-apples list, see /pricing/cheapest-llm-api.
Which vercel model has the largest context window?
Nova 2 Lite leads at 1M tokens. This is the total of prompt + completion.
Which vercel models support tool calling?
Multiple vercel models support tool calling, with Nova Micro being a popular pick. The capability column in the table above marks every model with vercel tool-calling support.
Which vercel models accept image input?
Nova Lite accepts image input. Other vision-capable vercel models are tagged 'vision' in the table above. See /capabilities/vision for a cross-vendor comparison.
What are the best alternatives to vercel?
Depends on the use case. For raw cost savings, look at /pricing/cheapest-llm-api. For agent-oriented workloads, /best/best-ai-model-for-agents. For long-document workflows, /best/best-long-context-llm.
How fresh is this vercel pricing data?
Daily. Our pipeline pulls models.dev each morning and rebuilds these pages on data change, so list-price moves and new model releases land within roughly 24 hours.
Explore more
Top vercel models
- Titan Text Embeddings V2$0.02 in / $0.00 out
- Nova Micro$0.04 in / $0.14 out
- Trinity Mini$0.05 in / $0.15 out
- Nova Lite$0.06 in / $0.24 out
- Trinity Large Thinking$0.25 in / $0.90 out
Browse by use case
Browse by capability
Dernière mise à jour :
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
Data is sourced from models.dev and normalized for comparison. Prices and capabilities may change. Always verify critical production decisions with the provider's official documentation.