Models

claude-sonnet-5 — API, Pricing & Context Window | Vivgrid

claude-sonnet-5 on Vivgrid: Anthropic's Sonnet 5 model with a 1M-token context window, Messages API, and geo-distributed acceleration.

claude-sonnet-5 is Anthropic's Sonnet 5 model, delivering near-Opus coding and reasoning quality at a fraction of the price and higher speed. With a 1M-token context window and lower rates than claude-sonnet-4-6, it's a proven workhorse for production agents. For new projects, claude-sonnet-5-5 is the latest Sonnet release at the same price.

On Vivgrid, claude-sonnet-5 is geo-distributed across AMER, EMEA, and APAC and reachable on the Messages API through the same unified key as the rest of the catalog.

Specifications

ProviderAnthropic
Model IDclaude-sonnet-5
Best forCoding
Available onChat Completions, Vibe coding
Context window1,000,000 tokens
Max output128,000 tokens
ModalitiesText, Image
Tool / function callingYes
Knowledge cutoff2026-01
Acceleration⚡ Geo-Distributed — AMER, EMEA, APAC

Pricing

Pricing in USD per 1M tokens, matching the provider's rates.

InputCached inputOutput
$2.00$0.20$10.00

What one request costs

The rates above applied to a 20K-token prompt with a 2K-token reply — a typical single agent turn, small enough that every request is billed at the base rate.

RequestCost
Cold prompt, nothing cached$0.0600
Warm prompt, 90% of the input served from cache$0.0276

API surfaces

The Vivgrid Console catalogs claude-sonnet-5 on 2 surfaces, all behind the same API key. The endpoint shown is the one the Console previews for that surface.

SurfacePrimary endpointUse it for
Chat Completions/messagesAgent projects, where Vivgrid injects the model, system prompt and tools server-side, and Model API calls that name the model per request.
Vibe coding/messagesCoding CLIs and IDE agents that drive the model themselves — point the tool at Vivgrid and keep your own loop.

Quick start

Get an API key from the Vivgrid Console, then call claude-sonnet-5 directly.

curl https://api.vivgrid.com/v1/messages \
  -H "Authorization: Bearer $VIVGRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-5",
    "max_tokens": 1024,
    "messages": [
      { "role": "user", "content": "Say hello in English, Chinese and Spanish." }
    ],
    "stream": true
  }'

Choosing within the Claude 5 family

Prices are USD per 1M tokens at the base rate. Rows marked this page are the model described here.

ModelContextMax outputInputOutput
claude-fable-5-11,000,000128,000$10.00$50.00
claude-fable-51,000,000128,000$10.00$50.00
claude-opus-5-51,000,000128,000$4.00$20.00
claude-opus-51,000,000128,000$5.00$25.00
claude-sonnet-5-51,000,000128,000$2.00$10.00
claude-sonnet-5 — this page1,000,000128,000$2.00$10.00
claude-haiku-5-51,000,000128,000$0.10$0.50

Ideal use cases

  • Everyday coding agents balancing quality, speed, and cost
  • High-volume reasoning and content workflows
  • Long-context analysis within a 1M-token budget
  • Production assistants needing reliable tool use

On this page