Skip to main content
Docs
Providers

Providers

The AI providers available in Alvin and what each is good at.

Alvin brings eleven providers behind one account. You don't need to choose between them — Alvin routes across all of them — but it helps to know what each is for when you want to pick manually.

At a glance

OpenAI

GPT-5.5, GPT-5 mini/nano, GPT-4.1, GPT-4o, image, speech

Anthropic

Claude Opus 4.8, Sonnet 4.6, Haiku 4.5

Google

Gemini 3.5 Flash, 3.1 Pro, 2.5 Pro/Flash, Imagen, Veo

xAI

Grok 4.3, Grok 4

Meta

Llama 4 Scout & Maverick, Llama 3.3

Mistral AI

Mistral Large 3, Small 4, Codestral

DeepSeek

DeepSeek V4 Pro, V4 Flash, V3.2

Cohere

Command A+, Command A

Perplexity

Sonar Deep Research, Sonar Reasoning Pro, Sonar

Fireworks AI

Qwen 3.5, Kimi K2.6, DeepSeek V4, Llama 4

ElevenLabs

eleven-v3 speech, Scribe v2 transcription

OpenAI

Strengths — strong instruction following, wide capability coverage, fast.

ModelBest forContext
gpt-5.5Current flagship, hardest reasoning128K
gpt-5.5-proMaximum reasoning depth128K
gpt-5-miniBalanced, cost-effective128K
gpt-5-nanoFast and cheap128K
gpt-4.1Long context with vision1M
gpt-4o-miniCheapest general chat128K

Also: gpt-image-2 and gpt-image-1.5 for images, tts-1-hd for speech, whisper-1 and gpt-4o-transcribe for transcription, text-embedding-3-small/-large for embeddings.

Anthropic

Strengths — best-in-class for software development, long context, careful and detailed answers, extended thinking.

ModelBest forContext
claude-opus-4.8Current flagship, agentic coding200K
claude-sonnet-4.6Coding and agents, everyday driver200K
claude-haiku-4.5Fast and affordable200K

Google

Strengths — the largest context windows available, native multimodality, strong price-performance.

ModelBest forContext
gemini-3.5-flashFast, beats the previous Pro tier on coding1M
gemini-3.1-pro-previewMost capable, deep reasoning1M
gemini-2.5-proBalanced with long context1M
gemini-2.5-flash-liteUltra-fast, lowest cost1M

Also: imagen-4 and the nano-banana family for images, veo-3.1 and veo-3 for video.

xAI

Strengths — cost-efficient reasoning at long context.

ModelBest forContext
grok-4.3Current flagship, cost-efficient1M
grok-4High-capability reasoning100K

Meta

Strengths — open weights, permissive licensing, good value.

ModelBest forContext
llama4-maverickComplex tasks, vision1M
llama4-scoutEfficient, vision320K
llama-3.3-70bHigh quality, well understood128K

Mistral AI

Strengths — European hosting, strong code models, efficient at size.

ModelBest forContext
mistral-large-3Most capable256K
mistral-small-4Multimodal, agentic coding256K
codestral-22bCode generation256K

DeepSeek

Strengths — reasoning and code at a fraction of frontier pricing.

ModelBest forContext
deepseek-v4-proFlagship reasoning and coding128K
deepseek-v4-flashFast, cost-effective128K

Cohere

Strengths — enterprise RAG, retrieval, and embeddings.

ModelBest forContext
command-a-plusLatest flagship, vision256K
command-aEnterprise RAG256K

Perplexity

Strengths — the web, with citations. Use these when the answer depends on current information.

ModelBest forContext
sonar-deep-researchMulti-step research with citations128K
sonar-reasoning-proReasoning grounded in live sources128K
perplexity-sonarFast web-grounded answers128K

Fireworks AI

Strengths — fast, cheap serving of open-weight models.

Hosts Qwen 3.5, Kimi K2.6, DeepSeek V4 and Llama 4 among others. Useful when you want an open model with better latency than self-hosting gives you.

ElevenLabs

Strengths — the most natural speech synthesis available.

ModelBest for
eleven-v3Natural text-to-speech
scribe-v2Speech-to-text

Picking a provider

Most users don't need to. Alvin routing selects across every provider listed here on a per-request basis.

If you want to choose manually, the Model Hub lets you filter by capability, context size and cost, and compare candidates side by side before committing.

Providers | Alvin