Skip to Content
ConceptsSupported ModelsOverview

Supported Models

Convoy supports a wide range of models. Use the Convoy Model ID in your requests — Convoy handles routing to the underlying provider automatically.

Browse by Provider

  • Anthropic — Claude 3, 3.5, 3.7, Sonnet 4, Opus 4, and more
  • Amazon Nova — Nova Micro, Lite, Pro, Premier, Nova 2 Lite
  • Meta Llama — Llama 3.1, 3.2, 3.3, Llama 4
  • Mistral AI — Mistral Small, Large, Ministral, Devstral, Voxtral
  • DeepSeek — DeepSeek V3.1, V3.2
  • Google — Gemma 3 (4B, 12B, 27B)
  • MiniMax — MiniMax M2, M2.1
  • NVIDIA — Nemotron Nano
  • Moonshot AI — Kimi K2, K2.5
  • OpenAI — GPT OSS 20B, 120B
  • Qwen — Qwen3 32B, 235B, Coder, VL
  • Z.AI — GLM 4.7, GLM 4.7 Flash

Model IDs

Each model has a Convoy Model ID — a stable, provider-agnostic identifier you use in all API requests. Convoy translates this to the correct provider-specific ID (e.g. a Bedrock ARN) at routing time.

convoy-model-id  →  provider-specific-id
claude-3-haiku   →  anthropic.claude-3-haiku-20240307-v1:0
amazon-nova-pro  →  amazon.nova-pro-v1:0
llama-3.3-70b-instruct  →  meta.llama3-3-70b-instruct-v1:0

This means if Convoy adds support for a new provider in the future, your code doesn’t change — the same model ID continues to work.

Example Request

curl -X POST https://api.cnvy.ai/cargo/load \
  -H "Content-Type: application/json" \
  -H "X-API-Key: convoy_sk_your_key_here" \
  -d '{
    "params": {
      "model": "claude-3-haiku"
    },
    "records": [
      {
        "recordId": "rec_001",
        "modelInput": {
          "anthropic_version": "bedrock-2023-05-31",
          "max_tokens": 1024,
          "messages": [
            {
              "role": "user",
              "content": "Summarize this document."
            }
          ]
        }
      }
    ]
  }'
Last updated on
OverviewAnthropic