Vercel AI Gateway models and pricing

We track 263 models on Vercel AI Gateway (298 listings) from 33 labs. The cheapest paid model is Mistral Nemo, at $0.03 per million input tokens and $0.03 per million output tokens. Input prices range from $0.02 to $30 and output prices from $0.03 to $180 per million tokens. 2 models are listed free. The largest context window is 2M tokens (Grok 4.20 (Reasoning) and Grok 4.20 (Non-Reasoning)). Prices last verified 18 Nov 2026.

Prices in USD per million tokens. Official site

Cheapest models on Vercel AI Gateway

Input / output per million tokens, paid models, by combined price.

Newest models on Vercel AI Gateway

By the lab's release date.

All Vercel AI Gateway models and prices

ModelLabInputOutputContextSource
GPT-6.2 Sol
openai/gpt-6.2-sol-fast
OpenAI$4$201.1Mmodels.dev
GPT-6.2 Astra
openai/gpt-6.2-astra
OpenAI$8$401.1Mmodels.dev
GPT-6.2 Astra
openai/gpt-6.2-astra-fast
OpenAI$16$801.1Mmodels.dev
GPT-6.2 Sol
openai/gpt-6.2-sol
OpenAI$2$101.1Mmodels.dev
Qwen 4 Max
alibaba/qwen4-max
Alibaba (Qwen)$1.50$4.501Mmodels.dev
Tencent Hy4 Flash
tencent/hy4-flash
Tencent (Hunyuan)$0.04$0.141Mmodels.dev
Gemini 4 Hydrogen
google/gemini-4-hydrogen
Google DeepMind$1.50$7.501Mmodels.dev
Gemini 4 Carbon
google/gemini-4-carbon
Google DeepMind$2$101Mmodels.dev
Claude Fable 5.2
anthropic/claude-fable-5.2-fast
Anthropic$16$801Mmodels.dev
Claude Fable 5.2
anthropic/claude-fable-5.2
Anthropic$8$401Mmodels.dev
Gemini Omni 1.2 Flash
google/gemini-omni-1.2-flash
Google DeepMind$1.50$9131Kmodels.dev
Inkling 2 Small
thinkingmachines/inkling-2-small
Thinkingmachines$0.30$11Mmodels.dev
Tencent Hy4
tencent/hy4
Tencent (Hunyuan)$0.42$1.251Mmodels.dev
LongCat 2.5
meituan/longcat-2.5
Meituan$0.30$1.201Mmodels.dev
Particle-1
particle/particle-1
Particle AI$0.13$0.501Mmodels.dev
GPT-6.1 Terra
openai/gpt-6.1-terra-fast
OpenAI$2$101.1Mmodels.dev
GPT-6.1 Terra
openai/gpt-6.1-terra
OpenAI$1$51.1Mmodels.dev
Kimi K3.1 Pro Highspeed
moonshotai/kimi-k3.1-pro
Moonshot AI$2$101Mmodels.dev
MiniMax-M3.1-Flash
minimax/minimax-m3.1-flash
MiniMax$0.15$0.601Mmodels.dev
DeepSeek V4.1 Flash 1017
deepseek/deepseek-v4.1-flash-1017
DeepSeek$0.30$1.201Mmodels.dev
DeepSeek V4.1 Flash 1017
deepseek/deepseek-v4.1-flash-1017-fast
DeepSeek$0.60$2.401Mmodels.dev
Mercury 3
inception/mercury-3
Inception Labs$0.10$0.351Mmodels.dev
NVIDIA Nemotron 3.5 Super VL
nvidia/nemotron-3.5-super-vl
NVIDIA$0.20$0.501Mmodels.dev
Muse Spark Open
meta/muse-spark-open
Meta$1.25$4.251Mmodels.dev
Gemini 4 Argon
google/gemini-4-argon
Google DeepMind$2$101Mmodels.dev
Muse Wonder
meta/muse-wonder-1.0
Meta$4$201Mmodels.dev
Claude Haiku 5.5
anthropic/claude-haiku-5.5
Anthropic$0.10$0.501Mmodels.dev
Gemini Nano Banana 2.1
google/gemini-nano-banana-2.1
Google DeepMind$1.50$7.50131Kmodels.dev
Mistral Large 4
mistral/mistral-large-4
Mistral AI$0.70$2.101Mmodels.dev
Beam 1.0
reflection/beam
ReflectionFreeFree1Mmodels.dev
Beam 1.0
reflection/beam-free
ReflectionFreeFree1Mmodels.dev
Grok Imagine Video 1.5 Lite
spacexai/grok-imagine-video-1.5-lite
xAI––1Kmodels.dev
Embed 5 Fast
cohere/embed-v5.0-fast
Cohere––128Kmodels.dev
Voyage Rerank 3 Lite
voyage/rerank-3-lite
Voyageai––32Kmodels.dev
Embed 5 Pro
cohere/embed-v5.0-pro
Cohere––128Kmodels.dev
Voyage Rerank 3
voyage/rerank-3
Voyageai––32Kmodels.dev
GPT-6.1 Sol
openai/gpt-6.1-sol-fast
OpenAI$4$201.1Mmodels.dev
GPT-6.1 Sol
openai/gpt-6.1-sol
OpenAI$2$101.1Mmodels.dev
Ling 3.1 Flash
inclusionai/ling-3.1-flash
Inclusionai$0.30$0.90262Kmodels.dev
Claude Sonnet 5.5
anthropic/claude-sonnet-5.5
Anthropic$2$101Mmodels.dev
Qwen 3.8 Max Prime
alibaba/qwen3.8-max-prime
Alibaba (Qwen)$4$121Mmodels.dev
GPT-6 Luna
openai/gpt-6-luna-fast
OpenAI$0.20$11.1Mmodels.dev
Claude Opus 5.5
anthropic/claude-opus-5.5-fast
Anthropic$8$401Mmodels.dev
GPT-6 Sol
openai/gpt-6-sol
OpenAI$2$101.1Mmodels.dev
GPT-6 Sol
openai/gpt-6-sol-fast
OpenAI$4$201.1Mmodels.dev
GPT-6 Luna
openai/gpt-6-luna
OpenAI$0.10$0.501.1Mmodels.dev
Gemini 3.8 Flash-Lite TTS
google/gemini-3.8-flash-lite-tts
Google DeepMind$0.50$68Kmodels.dev
Ember-1
fireworks/ember-1
Fireworks$3$151Mmodels.dev
Gemini 3.8 Flash TTS
google/gemini-3.8-flash-tts
Google DeepMind$0.50$98Kmodels.dev
Claude Opus 5.5
anthropic/claude-opus-5.5
Anthropic$4$201Mmodels.dev
MiMo-V2.6-Flash
xiaomi/mimo-v2.6-flash
Xiaomi (MiMo)$0.14$0.281Mmodels.dev
MiMo-V2.6-Pro
xiaomi/mimo-v2.6-pro
Xiaomi (MiMo)$0.43$0.871Mmodels.dev
Grok 4.7
spacexai/grok-4.7
xAI$2$6500Kmodels.dev
MiMo-V2.6-Pro-UltraSpeed
xiaomi/mimo-v2.6-pro-ultraspeed
Xiaomi (MiMo)$4.35$8.701Mmodels.dev
Qwen3.8 Omni Flash
alibaba/qwen3.8-omni-flash
Alibaba (Qwen)$0.15$0.471Mmodels.dev
Arrow 2
quiverai/arrow-2
Quiverai$4$20131Kmodels.dev
Arrow 2 Telos
quiverai/arrow-2-telos
Quiverai$6$30131Kmodels.dev
Step 5 Preview
stepfun/step-5-preview
StepFun$1$2.701Mmodels.dev
Gemini 3.8 Live Extended Thinking
google/gemini-3.8-live-extended-thinking
Google DeepMind$0.75$4.50131Kmodels.dev
Gemini 3.8 Live
google/gemini-3.8-live
Google DeepMind$0.75$4.50131Kmodels.dev
Fugu Ultra v2
sakana/fugu-ultra-v2
Sakana$5$301Mmodels.dev
Fugu Max
sakana/fugu-max
Sakana$2$61Mmodels.dev
DeepSeek V4.1 Flash
deepseek/deepseek-v4.1-flash
DeepSeek$0.30$1.201Mmodels.dev
DeepSeek V4.1 Flash
deepseek/deepseek-v4.1-flash-fast
DeepSeek$0.60$2.401Mmodels.dev
Ling 3.0 Flash VL
inclusionai/ling-3.0-flash-vl
Inclusionai$0.07$0.22256Kmodels.dev
GPT-Live 1
openai/gpt-live-1
OpenAI–––models.dev
GPT Image 2.5 Sunburst
openai/gpt-image-2.5-sunburst
OpenAI–––models.dev
GPT Image 2.5 Flare
openai/gpt-image-2.5-flare
OpenAI–––models.dev
GPT-6 Astra (Fast)
openai/gpt-6-astra-fast
OpenAI$20$1001.1Mmodels.dev
GPT-6 Astra
openai/gpt-6-astra
OpenAI$10$501.1Mmodels.dev
Ling 3.0 Flash Sante
inclusionai/ling-3.0-flash-sante
Inclusionai$0.07$0.22256Kmodels.dev
Gemini 3.8 Flash
google/gemini-3.8-flash
Google DeepMind$0.75$3.751Mmodels.dev
Qwen3.8 Max 0902
alibaba/qwen3.8-max-0902
Alibaba (Qwen)$2$6991Kmodels.dev
Muse Spark 1.3 Contributor
meta/muse-spark-1.3
Meta$1.25$4.251Mmodels.dev
Claude Fable 5.1
anthropic/claude-fable-5.1
Anthropic$10$501Mmodels.dev
Tencent Hy4 Preview
tencent/hy4-preview
Tencent (Hunyuan)$0.83$2.501Mmodels.dev
Ling 3.0 Flash Fin
inclusionai/ling-3.0-flash-fin
Inclusionai$0.07$0.22256Kmodels.dev
Gemini 3.5 Transcribe Live
google/gemini-3.5-transcribe-live
Google DeepMind–––models.dev
Gemini 3.5 Transcribe
google/gemini-3.5-transcribe
Google DeepMind$2$1298Kmodels.dev
GLM-5.3-Flash
zai/glm-5.3-flashx
Zhipu AI (Z.ai)$0.37$1.251Mmodels.dev
GLM-5.3-Flash
zai/glm-5.3-flash
Zhipu AI (Z.ai)$0.15$0.501Mmodels.dev
MiniMax H3 Max
minimax/minimax-h3-max
MiniMax–––models.dev
Qwen3.8 Flash
alibaba/qwen3.8-flash
Alibaba (Qwen)$0.15$0.47991Kmodels.dev
DeepSeek V4 Flash Vision Exp
deepseek/deepseek-v4-flash-vision-exp
DeepSeek$0.22$0.651Mmodels.dev
GLM-5.3
zai/glm-5.3
Zhipu AI (Z.ai)$1.40$4.401Mmodels.dev
Qwen3.8 27B
alibaba/qwen3.8-27b
Alibaba (Qwen)$0.06$2.20262Kmodels.dev
GLM-5.3
zai/glm-5.3-fast
Zhipu AI (Z.ai)$2.10$6.601Mmodels.dev
DeepSeek V4 Pro
deepseek/deepseek-v4-pro-0813
DeepSeek$0.66$1.981Mmodels.dev
Gemini 3.7 Flash
google/gemini-3.7-flash
Google DeepMind$0.75$3.751Mmodels.dev
DeepSeek V4 Pro
deepseek/deepseek-v4-pro
DeepSeek$1.32$3.961Mmodels.dev
Toast 1
mixedbread/toast-1
Mixedbread$0.30$0.72131Kmodels.dev
Qwen3.8 2.4T A95B
alibaba/qwen3.8-2.4t-a95b
Alibaba (Qwen)$2$6262Kmodels.dev
Grok 4.6
spacexai/grok-4.6
xAI$2$6500Kmodels.dev
Nemotron 3.5 Lightning 30B
nvidia/nemotron-3.5-lightning-free
NVIDIAFreeFree1Mmodels.dev
Nemotron 3.5 Lightning 30B
nvidia/nemotron-3.5-lightning
NVIDIA$0.06$0.16262Kmodels.dev
Muse Glimmer 30B
meta/muse-glimmer-30b
Meta$0.35$1.50131Kmodels.dev
Grok Imagine Image 2.0
spacexai/grok-imagine-image-2.0
xAI––64Kmodels.dev
Muse Spark 1.2 Contributor
meta/muse-spark-1.2
Meta$1.25$4.251Mmodels.dev
Sakana Namazu
sakana/namazu
Sakana$0.95$4256Kmodels.dev
MiniMax H3
minimax/minimax-h3
MiniMax–––models.dev
DeepSeek V4 Flash 0731
deepseek/deepseek-v4-flash-0731
DeepSeek$0.13$0.261Mmodels.dev
Seedance 2.5
bytedance/seedance-2.5
ByteDance Seed–––models.dev
Inkling Small
thinkingmachines/inkling-small
Thinkingmachines$0.45$1.201Mmodels.dev
Claude Opus 5
anthropic/claude-opus-5-fast
Anthropic$10$501Mmodels.dev
Claude Opus 5
anthropic/claude-opus-5
Anthropic$5$251Mmodels.dev
Ling 3.0 Flash
inclusionai/ling-3.0-flash
Inclusionai$0.02$0.06256Kmodels.dev
Gemini 3.5 Flash Lite
google/gemini-3.5-flash-lite
Google DeepMind$0.30$2.501Mmodels.dev
Gemini 3.6 Flash
google/gemini-3.6-flash
Google DeepMind$0.75$3.751Mmodels.dev
Qwen 3.8 Max
alibaba/qwen3.8-max
Alibaba (Qwen)$2$61Mmodels.dev
Kimi K3
moonshotai/kimi-k3-fast
Moonshot AI$6$22.501Mmodels.dev
Kimi K3
moonshotai/kimi-k3
Moonshot AI$3$151Mmodels.dev
Inkling
thinkingmachines/inkling
Thinkingmachines$1$4.05256Kmodels.dev
Qwen3.7 Flash
alibaba/qwen3.7-flash
Alibaba (Qwen)$0.03$0.13991Kmodels.dev
GPT-5.6 Luna
openai/gpt-5.6-luna
OpenAI$0.20$1.201.1Mmodels.dev
GPT-5.6 Luna
openai/gpt-5.6-luna-fast
OpenAI$0.40$2.401.1Mmodels.dev
GPT-5.6 Terra
openai/gpt-5.6-terra
OpenAI$2$121.1Mmodels.dev
GPT-5.6 Sol
openai/gpt-5.6-sol-fast
OpenAI$8$401.1Mmodels.dev
GPT-5.6 Sol
openai/gpt-5.6-sol
OpenAI$4$201.1Mmodels.dev
GPT-5.6 Terra
openai/gpt-5.6-terra-fast
OpenAI$4$241.1Mmodels.dev
Grok 4.5
spacexai/grok-4.5
xAI$2$6500Kmodels.dev
Muse Image 1.0
meta/muse-image-1.0
Meta–––models.dev
GPT-Realtime-2.1
openai/gpt-realtime-2.1
OpenAI$4$24128Kmodels.dev
Hy3
tencent/hy3
Tencent (Hunyuan)$0.14$0.58262Kmodels.dev
Gemini Omni Flash Preview
google/gemini-omni-flash-preview
Google DeepMind$1.50$91Mmodels.dev
Nano Banana 2 Lite
google/gemini-3.1-flash-lite-image
Google DeepMind$0.25$1.5066Kmodels.dev
Claude Sonnet 5
anthropic/claude-sonnet-5
Anthropic$2$101Mmodels.dev
Seed 2.1 Turbo
bytedance/seed-2.1-turbo
ByteDance Seed$0.50$2.50262Kmodels.dev
Fugu Ultra
sakana/fugu-ultra
Sakana$5$301Mmodels.dev
GLM-5.2
zai/glm-5.2
Zhipu AI (Z.ai)$1.40$4.401Mmodels.dev
GLM-5.2
zai/glm-5.2-fast
Zhipu AI (Z.ai)$2.80$8.801Mmodels.dev
Kimi K2.7 Code High Speed
moonshotai/kimi-k2.7-code-highspeed
Moonshot AI$1.90$8262Kmodels.dev
Kimi K2.7 Code
moonshotai/kimi-k2.7-code
Moonshot AI$0.95$4256Kmodels.dev
Claude Fable 5
anthropic/claude-fable-5
Anthropic$10$501Mmodels.dev
Nemotron 3 Ultra
nvidia/nemotron-3-ultra-550b-a55b
NVIDIA$0.60$2.401Mmodels.dev
Qwen3.7 Plus
alibaba/qwen3.7-plus
Alibaba (Qwen)$0.40$1.601Mmodels.dev
MiniMax-M3
minimax/minimax-m3
MiniMax$0.30$1.201Mmodels.dev
Grok Imagine Video 1.5
spacexai/grok-imagine-video-1.5
xAI––1Kmodels.dev
Step 3.7 Flash
stepfun/step-3.7-flash
StepFun$0.20$1.15256Kmodels.dev
Nano Banana Pro
google/gemini-3-pro-image
Google DeepMind$2$1266Kmodels.dev
Claude Opus 4.8
anthropic/claude-opus-4.8-fast
Anthropic$10$501Mmodels.dev
Nano Banana 2
google/gemini-3.1-flash-image
Google DeepMind$0.50$3131Kmodels.dev
Claude Opus 4.8
anthropic/claude-opus-4.8
Anthropic$5$251Mmodels.dev
Qwen3.7 Max
alibaba/qwen3.7-max
Alibaba (Qwen)$2.50$7.50991Kmodels.dev
Gemini 3.5 Flash
google/gemini-3.5-flash
Google DeepMind$1.50$91Mmodels.dev
gpt-realtime-2
openai/gpt-realtime-2
OpenAI$4$24128Kmodels.dev
gpt-realtime-whisper
openai/gpt-realtime-whisper
OpenAI––16Kmodels.dev
Gemini 3.1 Flash Lite
google/gemini-3.1-flash-lite
Google DeepMind$0.25$1.501Mmodels.dev
Mistral Medium Latest
mistral/mistral-medium-3.5
Mistral AI$1.50$7.50262Kmodels.dev
DeepSeek V4 Flash
deepseek/deepseek-v4-flash
DeepSeek$0.13$0.261Mmodels.dev
GPT-5.5 Pro
openai/gpt-5.5-pro
OpenAI$30$1801Mmodels.dev
GPT-5.5
openai/gpt-5.5
OpenAI$5$301Mmodels.dev
GPT-5.5
openai/gpt-5.5-fast
OpenAI$12.50$751Mmodels.dev
Qwen3.6 27B
alibaba/qwen3.6-27b
Alibaba (Qwen)$0.60$3.60256Kmodels.dev
Gemini Embedding 2
google/gemini-embedding-2
Google DeepMind––8Kmodels.dev
gpt-image-2
openai/gpt-image-2
OpenAI–––models.dev
Kimi K2.6
moonshotai/kimi-k2.6
Moonshot AI$0.95$4262Kmodels.dev
Qwen3.6 35B-A3B
alibaba/qwen3.6-35b-a3b
Alibaba (Qwen)$0.38$2.25262Kmodels.dev
Grok 4.3
spacexai/grok-4.3
xAI$1.25$2.501Mmodels.dev
Schematron V2 Turbo
inference-net/schematron-v2-turbo
Inference NET$0.03$0.15128Kmodels.dev
Schematron V2 Small
inference-net/schematron-v2-small
Inference NET$0.05$0.23128Kmodels.dev
Grok Build 0.1
spacexai/grok-build-0.1
xAI$1$2256Kmodels.dev
Claude Opus 4.7
anthropic/claude-opus-4.7
Anthropic$5$251Mmodels.dev
Muse Spark 1.1
meta/muse-spark-1.1
Meta$1.25$4.251Mmodels.dev
GLM-5.1
zai/glm-5.1
Zhipu AI (Z.ai)$1.40$4.40203Kmodels.dev
Veo 3.1 Lite Generate
google/veo-3.1-lite-generate-001
Google DeepMind––1Kmodels.dev
Gemma 4 26B A4B IT
google/gemma-4-26b-a4b-it
Google DeepMind$0.15$0.60262Kmodels.dev
Qwen3.6 Plus
alibaba/qwen3.6-plus
Alibaba (Qwen)$0.50$31Mmodels.dev
Gemma 4 31B IT
google/gemma-4-31b-it
Google DeepMind$0.14$0.40262Kmodels.dev
GLM-5V-Turbo
zai/glm-5v-turbo
Zhipu AI (Z.ai)$1.20$4200Kmodels.dev
MiniMax-M2.7
minimax/minimax-m2.7
MiniMax$0.30$1.20197Kmodels.dev
GPT-5.4 mini
openai/gpt-5.4-mini-fast
OpenAI$1.50$9400Kmodels.dev
GPT-5.4 mini
openai/gpt-5.4-mini
OpenAI$0.75$4.50400Kmodels.dev
GPT-5.4 nano
openai/gpt-5.4-nano
OpenAI$0.20$1.25400Kmodels.dev
GLM-5-Turbo
zai/glm-5-turbo
Zhipu AI (Z.ai)$1.20$4203Kmodels.dev
Grok TTS
spacexai/grok-tts
xAI––15Kmodels.dev
NVIDIA Nemotron 3 Super 120B A12B
nvidia/nemotron-3-super-120b-a12b
NVIDIA$0.15$0.65256Kmodels.dev
Grok 4.20 (Reasoning)
spacexai/grok-4.20-reasoning
xAI$1.25$2.502Mmodels.dev
Grok 4.20 (Non-Reasoning)
spacexai/grok-4.20-non-reasoning
xAI$1.25$2.502Mmodels.dev
GPT-5.4
openai/gpt-5.4
OpenAI$2.50$151.1Mmodels.dev
GPT-5.4 Pro
openai/gpt-5.4-pro
OpenAI$30$1801.1Mmodels.dev
GPT-5.4
openai/gpt-5.4-fast
OpenAI$5$301.1Mmodels.dev
GPT-Realtime-1.5
openai/gpt-realtime-1.5
OpenAI$4$1632Kmodels.dev
Qwen3.5 Flash
alibaba/qwen3.5-flash
Alibaba (Qwen)$0.10$0.401Mmodels.dev
Gemini Pro Latest
google/gemini-3.1-pro-preview
Google DeepMind$2$121Mmodels.dev
Claude Sonnet 4.6
anthropic/claude-sonnet-4.6
Anthropic$3$151Mmodels.dev
Qwen3.5 Plus
alibaba/qwen3.5-plus
Alibaba (Qwen)$0.40$2.401Mmodels.dev
MiniMax-M2.5
minimax/minimax-m2.5
MiniMax$0.30$1.201Mmodels.dev
GLM-5
zai/glm-5
Zhipu AI (Z.ai)$1$3.20203Kmodels.dev
Seedance 2.0
bytedance/seedance-2.0
ByteDance Seed–––models.dev
GPT-5.3 Codex
openai/gpt-5.3-codex
OpenAI$1.75$14400Kmodels.dev
GPT-5.3 Codex
openai/gpt-5.3-codex-fast
OpenAI$3.50$28400Kmodels.dev
Claude Opus 4.6
anthropic/claude-opus-4.6
Anthropic$5$251Mmodels.dev
Qwen3 Coder Next
alibaba/qwen3-coder-next
Alibaba (Qwen)$0.50$1.20256Kmodels.dev
Grok Imagine Video
spacexai/grok-imagine-video
xAI–––models.dev
Grok Imagine Image
spacexai/grok-imagine-image
xAI––16Kmodels.dev
Kimi K2.5
moonshotai/kimi-k2.5
Moonshot AI$0.60$3256Kmodels.dev
GLM-4.7-FlashX
zai/glm-4.7-flashx
Zhipu AI (Z.ai)$0.06$0.40200Kmodels.dev
GLM-4.7-Flash
zai/glm-4.7-flash
Zhipu AI (Z.ai)$0.07$0.40200Kmodels.dev
voyage-4-large
voyage/voyage-4-large
Voyageai––32Kmodels.dev
FLUX.2 Klein 4B
bfl/flux-2-klein-4b
Black Forest Labs–––models.dev
voyage-4-lite
voyage/voyage-4-lite
Voyageai––32Kmodels.dev
voyage-4
voyage/voyage-4
Voyageai––32Kmodels.dev
MiniMax-M2.1
minimax/minimax-m2.1
MiniMax$0.30$1.20205Kmodels.dev
GLM-4.7
zai/glm-4.7
Zhipu AI (Z.ai)$0.60$2.20200Kmodels.dev
Cohere Rerank 4 Pro
cohere/rerank-v4-pro
Cohere––32Kmodels.dev
GPT-5.2-Codex
openai/gpt-5.2-codex
OpenAI$1.75$14400Kmodels.dev
GPT-5.2 Pro
openai/gpt-5.2-pro
OpenAI$21$168400Kmodels.dev
Cohere Rerank 4 Fast
cohere/rerank-v4-fast
Cohere––32Kmodels.dev
GPT-5.2
openai/gpt-5.2
OpenAI$1.75$14400Kmodels.dev
GPT-5.2
openai/gpt-5.2-fast
OpenAI$3.50$28400Kmodels.dev
Nova 2 Lite
amazon/nova-2-lite
Amazon$0.33$2.751Mmodels.dev
Ministral 14B
mistral/ministral-14b
Mistral AI$0.20$0.20262Kmodels.dev
DeepSeek V3.2
deepseek/deepseek-v3.2-thinking
DeepSeek$0.62$1.85128Kmodels.dev
DeepSeek V3.2
deepseek/deepseek-v3.2
DeepSeek$0.62$1.85128Kmodels.dev
gpt-image-1.5
openai/gpt-image-1.5
OpenAI–––models.dev
Claude Opus 4.5
anthropic/claude-opus-4.5
Anthropic$5$25200Kmodels.dev
Veo 3.1
google/veo-3.1-generate-001
Google DeepMind––1Kmodels.dev
Veo 3.1 Fast Generate
google/veo-3.1-fast-generate-001
Google DeepMind––1Kmodels.dev
GPT-5.1 Codex mini
openai/gpt-5.1-codex-mini
OpenAI$0.25$2400Kmodels.dev
GPT 5.1 Codex Max
openai/gpt-5.1-codex-max
OpenAI$1.25$10400Kmodels.dev
GPT-5.1-Codex
openai/gpt-5.1-codex
OpenAI$1.25$10400Kmodels.dev
GPT OSS Safeguard 120B
openai/gpt-oss-safeguard-120b
OpenAI$0.15$0.60128Kmodels.dev
GPT OSS Safeguard 20B
openai/gpt-oss-safeguard-20b
OpenAI$0.07$0.20128Kmodels.dev
Nvidia Nemotron Nano 12B V2 VL
nvidia/nemotron-nano-12b-v2-vl
NVIDIA$0.20$0.60131Kmodels.dev
Claude Haiku 4.5
anthropic/claude-haiku-4.5
Anthropic$1$5200Kmodels.dev
GPT-Realtime mini
openai/gpt-realtime-mini
OpenAI$0.60$2.4032Kmodels.dev
GPT-5 Pro
openai/gpt-5-pro
OpenAI$15$120400Kmodels.dev
GLM-4.6
zai/glm-4.6
Zhipu AI (Z.ai)$0.60$2.20200Kmodels.dev
Claude Sonnet 4.5
anthropic/claude-sonnet-4.5
Anthropic$3$151Mmodels.dev
gpt-image-1-mini
openai/gpt-image-1-mini
OpenAI–––models.dev
GPT-5-Codex
openai/gpt-5-codex
OpenAI$1.25$10400Kmodels.dev
Qwen3-Next 80B-A3B Instruct
alibaba/qwen3-next-80b-a3b-instruct
Alibaba (Qwen)$0.15$1.20262Kmodels.dev
Nano Banana
google/gemini-2.5-flash-image
Google DeepMind$0.30$2.5033Kmodels.dev
DeepSeek-V3.1
deepseek/deepseek-v3.1
DeepSeek$0.25$0.95164Kmodels.dev
Nvidia Nemotron Nano 9B V2
nvidia/nemotron-nano-9b-v2
NVIDIA$0.06$0.23131Kmodels.dev
Voyage Rerank 2.5 Lite
voyage/rerank-2.5-lite
Voyageai––32Kmodels.dev
Voyage Rerank 2.5
voyage/rerank-2.5
Voyageai––32Kmodels.dev
GLM-4.5V
zai/glm-4.5v
Zhipu AI (Z.ai)$0.60$1.8066Kmodels.dev
GPT-5
openai/gpt-5-fast
OpenAI$2.50$20400Kmodels.dev
GPT-5 Mini
openai/gpt-5-mini
OpenAI$0.25$2400Kmodels.dev
GPT-5 Nano
openai/gpt-5-nano
OpenAI$0.05$0.40400Kmodels.dev
GPT-5
openai/gpt-5
OpenAI$1.25$10400Kmodels.dev
GPT-5 Mini
openai/gpt-5-mini-fast
OpenAI$0.45$3.60400Kmodels.dev
gpt-oss-120b
openai/gpt-oss-120b
OpenAI$0.10$0.50131Kmodels.dev
gpt-oss-20b
openai/gpt-oss-20b
OpenAI$0.03$0.14131Kmodels.dev
GLM-4.5-Air
zai/glm-4.5-air
Zhipu AI (Z.ai)$0.20$1.10128Kmodels.dev
GLM-4.5
zai/glm-4.5
Zhipu AI (Z.ai)$0.60$2.20128Kmodels.dev
Kimi K2 Instruct
moonshotai/kimi-k2
Moonshot AI$0.57$2.30131Kmodels.dev
Morph V3 Large
morph/morph-v3-large
Morph$0.90$1.90262Kmodels.dev
Morph V3 Fast
morph/morph-v3-fast
Morph$0.80$1.20262Kmodels.dev
Gemini 2.5 Flash-Lite
google/gemini-2.5-flash-lite
Google DeepMind$0.10$0.401Mmodels.dev
Gemini 2.5 Pro
google/gemini-2.5-pro
Google DeepMind$1.25$101Mmodels.dev
Gemini 2.5 Flash
google/gemini-2.5-flash
Google DeepMind$0.30$2.501Mmodels.dev
o3-pro
openai/o3-pro
OpenAI$20$80200Kmodels.dev
Qwen 3 Embedding 4B
alibaba/qwen3-embedding-4b
Alibaba (Qwen)––33Kmodels.dev
Qwen 3 Embedding 8B
alibaba/qwen3-embedding-8b
Alibaba (Qwen)––33Kmodels.dev
Qwen3 Embedding 0.6B
alibaba/qwen3-embedding-0.6b
Alibaba (Qwen)––33Kmodels.dev
Codestral Embed
mistral/codestral-embed
Mistral AI––8Kmodels.dev
Gemini Embedding 001
google/gemini-embedding-001
Google DeepMind––2Kmodels.dev
Qwen3-30B-A3B
alibaba/qwen-3-30b
Alibaba (Qwen)$0.12$0.5041Kmodels.dev
o3
openai/o3-fast
OpenAI$3.50$14200Kmodels.dev
o3
openai/o3
OpenAI$2$8200Kmodels.dev
Embed v4.0
cohere/embed-v4.0
Cohere––128Kmodels.dev
GPT-4.1
openai/gpt-4.1
OpenAI$2$81Mmodels.dev
GPT-4.1 mini
openai/gpt-4.1-mini
OpenAI$0.40$1.601Mmodels.dev
GPT-4.1 mini
openai/gpt-4.1-mini-fast
OpenAI$0.70$2.801Mmodels.dev
GPT-4.1
openai/gpt-4.1-fast
OpenAI$3.50$141Mmodels.dev
Llama-4-Maverick-17B-128E-Instruct-FP8
meta/llama-4-maverick
Meta$0.24$0.97128Kmodels.dev
Llama-4-Scout-17B-16E-Instruct-FP8
meta/llama-4-scout
Meta$0.17$0.66128Kmodels.dev
Qwen3 32B
alibaba/qwen-3-32b
Alibaba (Qwen)$0.15$0.60128Kmodels.dev
Qwen3-Coder 30B-A3B Instruct
alibaba/qwen3-coder-30b-a3b
Alibaba (Qwen)$0.15$0.60262Kmodels.dev
GPT-4o Transcribe
openai/gpt-4o-transcribe
OpenAI$2.50$1016Kmodels.dev
GPT-4o mini Transcribe
openai/gpt-4o-mini-transcribe
OpenAI$1.25$516Kmodels.dev
Command A
cohere/command-a
Cohere$2.50$10256Kmodels.dev
Llama-3.3-70B-Instruct
meta/llama-3.3-70b
Meta$0.72$0.72128Kmodels.dev
Nova Lite
amazon/nova-lite
Amazon$0.06$0.24300Kmodels.dev
Nova Pro
amazon/nova-pro
Amazon$0.80$3.20300Kmodels.dev
Nova Micro
amazon/nova-micro
Amazon$0.04$0.14128Kmodels.dev
Cohere Rerank 3.5
cohere/rerank-v3.5
Cohere––4Kmodels.dev
Text Embedding 005
google/text-embedding-005
Google DeepMind––2Kmodels.dev
Mistral Large 3
mistral/mistral-large-3
Mistral AI$0.50$1.50262Kmodels.dev
Ministral 3B
mistral/ministral-3b
Mistral AI$0.10$0.10131Kmodels.dev
GPT-4o (2024-08-06)
openai/gpt-4o
OpenAI$2.50$10128Kmodels.dev
GPT-4o (2024-08-06)
openai/gpt-4o-fast
OpenAI$4.25$17128Kmodels.dev
Llama 3.1 8B Instruct
meta/llama-3.1-8b
Meta$0.22$0.22128Kmodels.dev
Llama 3.1 70B Instruct
meta/llama-3.1-70b
Meta$0.72$0.72128Kmodels.dev
Mistral Nemo
mistral/mistral-nemo
Mistral AI$0.03$0.03131Kmodels.dev
GPT-4o mini
openai/gpt-4o-mini
OpenAI$0.15$0.60128Kmodels.dev
GPT-4o mini
openai/gpt-4o-mini-fast
OpenAI$0.25$1128Kmodels.dev
Text Multilingual Embedding 002
google/text-multilingual-embedding-002
Google DeepMind––2Kmodels.dev
text-embedding-3-small
openai/text-embedding-3-small
OpenAI––8Kmodels.dev
text-embedding-3-large
openai/text-embedding-3-large
OpenAI––8Kmodels.dev
Sonar
perplexity/sonar
Perplexity$0.25$2.50127Kmodels.dev
Mistral Embed
mistral/mistral-embed
Mistral AI––8Kmodels.dev
TTS-1
openai/tts-1
OpenAI–––models.dev
TTS-1 HD
openai/tts-1-hd
OpenAI–––models.dev
Whisper
openai/whisper-1
OpenAI–––models.dev
text-embedding-ada-002
openai/text-embedding-ada-002
OpenAI––8Kmodels.dev

Frequently asked questions

How much does Vercel AI Gateway cost per million tokens?

Prices on Vercel AI Gateway depend on the model. Across the 263 models we track, input costs $0.02 to $30 per million tokens and output costs $0.03 to $180 per million tokens. 2 models are listed free. Prices last verified 18 Nov 2026.

What is the cheapest model on Vercel AI Gateway?

Mistral Nemo from Mistral AI is the cheapest paid model we track on Vercel AI Gateway, at $0.03 per million input tokens and $0.03 per million output tokens. Next are Ling 3.0 Flash ($0.02 / $0.06) and Qwen3.7 Flash ($0.03 / $0.13). Prices last verified 18 Nov 2026.

How many models does Vercel AI Gateway offer?

We currently track 263 active models on Vercel AI Gateway from 33 labs, led by OpenAI (58), Google DeepMind (35), Alibaba (Qwen) (24) and Anthropic (15).

Which model on Vercel AI Gateway has the largest context window?

Grok 4.20 (Reasoning) and Grok 4.20 (Non-Reasoning) share the largest context window we track on Vercel AI Gateway: 2,000,000 tokens (2M).