Vercel AI Gateway

About Vercel AI Gateway

Use 400+ AI models without managing rate limits and API keys through Vercel AI Gateway.

Invoicing is available with no payment processing fees. See the AI Gateway pricing docs .

If a provider degrades, the Gateway fails over to the same model on another provider. Identical output, no downtime.

Everyday requests route to a cost-efficient open model. Complex jobs escalate to a frontier model only when needed.

Website ↗Documentation ↗GitHub ↗

Source ↗ · 2026-11-12T03:22:34.201741970Z

Service status

operational

AI Gateway

Official status page ↗

505 indexed models

505 matching models

DeepSeek: R1

deepseek/deepseek-r1

DeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass....

Context window
64,000
Input modalities
text
Output modalities
text
Capabilities
reasoning, structuredOutputs, toolCalling

Benchmarks

  • Artificial Analysis: 11.4
  • LLM Stats · GitHub archive: 0.959

Inference prices

Qwen: Qwen3 Next 80B A3B Thinking

qwen/qwen3-next-80b-a3b-thinking-2509

Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic...

Context window
262,144
Input modalities
text
Output modalities
text
Capabilities
reasoning, structuredOutputs, toolCalling

Benchmarks

  • Artificial Analysis: 11.2
  • HELM Capabilities: 46.683%
  • OpenCompass LLM: 89%

Inference prices

Google: Gemma 4 31B

google/gemma-4-31b-it-20260402

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function calling, and multilingual support across 140+ languages. Strong on

Context window
262,144
Input modalities
image, text, video
Output modalities
text
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput

Benchmarks

  • Artificial Analysis: 4.4
  • OpenRouter Benchmarks: 76.44%

Inference prices

OpenAI: gpt-oss-120b

openai/gpt-oss-120b

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized to run on a single H100 GPU with nativ

Context window
131,072
Input modalities
text
Output modalities
text
Capabilities
promptCaching, reasoning, structuredOutputs, toolCalling

Benchmarks

  • Artificial Analysis: 3.8
  • HELM Capabilities: 68.833%
  • Kaggle Benchmarks: 100%
  • LLM Stats · GitHub archive: 0.19
  • OpenCompass LLM: 93.4%
  • OpenRouter Benchmarks: 76.305%

Inference prices

OpenAI: GPT-5.4

openai/gpt-5.4-20260305

GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling high-context reasoning, coding, and multimodal analysis within the s

Context window
1,050,000
Input modalities
text, image, file
Output modalities
text
Capabilities
fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch

Benchmarks

  • Artificial Analysis: 39
  • LMArena: 1,469.112
  • OpenRouter Benchmarks: 72.667%

Inference prices

Anthropic: Claude Fable 5

anthropic/claude-5-fable-20260609

Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for long-running, complex, and asynchronous tasks t

Context window
1,000,000
Input modalities
text, image, file
Output modalities
text
Capabilities
batch, computerUse, fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch

Benchmarks

  • Artificial Analysis: 49.6
  • LMArena: 1,491.587
  • OpenRouter Benchmarks: 80.2%

Inference prices

OpenAI: GPT-5.6 Sol

openai/gpt-5.6-sol-20260709

GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.

Context window
1,050,000
Input modalities
file, image, text
Output modalities
text
Capabilities
fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch

Benchmarks

  • Artificial Analysis: 47
  • LMArena: 1,457.12
  • OpenRouter Benchmarks: 73.111%

Inference prices

Qwen: Qwen3.8 2.4T A95B

qwen/qwen3.8-2.4t-a95b-20260812

Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is suited for coding, research, complex reasoning, and agentic workflows.

Context window
1,048,576
Input modalities
text
Output modalities
text
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput

Benchmarks

  • Artificial Analysis: 39.9
  • OpenRouter Benchmarks: 91.771%

Inference prices

Anthropic: Claude Opus 4.8

anthropic/claude-4.8-opus-20260528

Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for highly autonomous agents, long-horizon agentic work, knowled

Context window
1,000,000
Input modalities
text, image, file
Output modalities
text
Capabilities
batch, computerUse, fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch

Benchmarks

  • Artificial Analysis: 41.8
  • OpenRouter Benchmarks: 89.96%

Inference prices

Meta: Muse Spark 1.2

meta/muse-spark-1.2-20260805

Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, and PDF documents, returns text, and offers a 1M-token context window. The model is built to support multi-agent workflows, whether as either a main agent that plan

Context window
1,048,576
Input modalities
text, image, video, file
Output modalities
text
Capabilities
audioInput, fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, videoInput, visionInput, webSearch

Benchmarks

  • Artificial Analysis: 39.6

Inference prices

Anthropic: Claude Sonnet 5

anthropic/claude-sonnet-5-20260630

Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max, and x-high), a 1M-token context window, and text, image,

Context window
1,000,000
Input modalities
text, image, file
Output modalities
text
Capabilities
batch, computerUse, fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch

Benchmarks

  • Artificial Analysis: 38.2
  • LMArena: 1,441.891
  • OpenRouter Benchmarks: 75.08%

Inference prices

DeepSeek: DeepSeek V4 Flash Vision Exp

deepseek/deepseek-v4-flash-vision-exp-20260821

DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding while matching the base model on text capabilities including agents, reasoning, and

Context window
1,048,576
Input modalities
text, image
Output modalities
text
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput

Benchmarks

  • Artificial Analysis: 34.8
  • OpenRouter Benchmarks: 90.909%

Inference prices

Anthropic: Claude Opus 4.7

anthropic/claude-4.7-opus-20260416

Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on complex, multi-step tasks and more reliable agentic execution across extended wor

Context window
1,000,000
Input modalities
text, image, file
Output modalities
text
Capabilities
batch, computerUse, fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch

Benchmarks

  • Artificial Analysis: 40.7
  • OpenRouter Benchmarks: 89.777%

Inference prices

OpenAI: GPT-5.5

openai/gpt-5.5-20260423

GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and

Context window
1,050,000
Input modalities
file, image, text
Output modalities
text
Capabilities
fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch

Benchmarks

  • Artificial Analysis: 38.4
  • LMArena: 1,471.184
  • OpenRouter Benchmarks: 92.845%

Inference prices

Google: Gemini 3.7 Flash

google/gemini-3.7-flash-20260813

Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.

Context window
1,048,576
Input modalities
text, image, video, file, audio
Output modalities
text
Capabilities
audioInput, batch, computerUse, fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, videoInput, visionInput, webSearch

Benchmarks

  • Artificial Analysis: 39.6
  • LMArena: 1,488.817
  • OpenRouter Benchmarks: 94.108%

Inference prices

DeepSeek: DeepSeek V4 Flash 0731

deepseek/deepseek-v4-flash-20260731

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows. This is the GA release of DeepSeek V4 Flash.

Context window
1,048,576
Input modalities
text
Output modalities
text
Capabilities
promptCaching, reasoning, structuredOutputs, toolCalling

Benchmarks

  • Artificial Analysis: 34.3
  • Kaggle Benchmarks: 1,472.3
  • OpenRouter Benchmarks: 88.72%
  • Vercel AI Gateway: 10.855%

Inference prices

Z.ai: GLM 5.2

z-ai/glm-5.2-20260616

GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering, and complex multi-step automation. Reasoning efforts `high` and `xhigh` are s

Context window
1,048,576
Input modalities
text
Output modalities
text
Capabilities
promptCaching, reasoning, structuredOutputs, toolCalling

Benchmarks

  • Artificial Analysis: 33.7
  • OpenRouter Benchmarks: 76.933%

Inference prices

Google: Gemini 3.6 Flash

google/gemini-3.6-flash-20260721

Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and less hedging, while reducing token use and the number of model calls needed to complete

Context window
1,048,576
Input modalities
text, image, video, file, audio
Output modalities
text
Capabilities
audioInput, batch, computerUse, fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, videoInput, visionInput, webSearch

Benchmarks

  • Artificial Analysis: 34
  • LMArena: 1,479.263
  • OpenRouter Benchmarks: 93.013%

Inference prices

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace