anthropic/claude-3-5-sonnet-20241022

$3.00

Input / 1M

$15.00

Output / 1M

200K

Context

80 t/s

Speed

Public benchmark scores

Sourced from each provider's published numbers. Verify before quoting.

Quality index

MMLU

88.7

GPQA

HumanEval

MATH

78.3

SWE-bench

—

Arena Elo

—

Sources: anthropic-system-card

Capabilities

toolsvisionstreamingprompt_cache

Input modalities: text, image

Use claude-3-5-sonnet-20241022 via Relay

Configure the model alias in YAML, then call it from Python.

YAML

# models.yaml
version: 1
models:
  claude:
    target: anthropic/claude-3-5-sonnet-20241022
    credential: $env.ANTHROPIC_API_KEY

Python

from relay import Hub

async with Hub.from_yaml("models.yaml") as hub:
    resp = await hub.chat(
        "claude",
        messages=[{"role": "user", "content": "Hello"}],
    )
    print(resp.text, resp.cost_usd)

pip install ai5labs-relay · full docs on GitHub

Compare with

vs google/gemini-2.5-flash vs openai/gpt-4o vs deepseek/deepseek-chat vs xai/grok-3