LLM Pricing
PricingLeaderboardsToolsProvidersReleasesGuides

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Claude Sonnet 4

anthropic·anthropic/claude-sonnet-4-20250514·Deprecated·Closed·claude-sonnet series
Balanced Claude model for coding, analysis, agent workflows, and cost control

Claude Sonnet 4 by anthropic is offered by 15 providers on this page. Its reference price is $3.00 per 1M input tokens and $15.00 per 1M output tokens. The lowest paid channel is Poe at $2.60 / $13.00 per 1M, about 1.2× below the reference price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.

The context window is 200,000 tokens at the reference host, but hosts report different limits, from 200,000 to 1,000,000, so the usable window depends on the provider you pick. It supports reasoning and tool use. Accepted input modalities are Text, Image, and PDF. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2025-03-31.

Specs & pricing

Input / output per 1M tokens
Reference price·NanoGPT
$3.00 / $15.00
Blended $6.00 · Cache read $0.30
Lowest paid·PoeGateway
$2.60 / $13.00
Blended $5.20 · 1.2× spread
Context
200,000
Output limit
64,000
Knowledge cutoff
2025-03-31
Released / updated
2025-05-22 / 2025-05-22
Capabilities
✓ Reasoning✓ Tool useStructured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImagePDF

Available at 15 providers15 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Poe
anthropic/claude-sonnet-4
Gateway$2.60$13.00$0.26$3.20983,040 ⚠64,000
Jiekou.AIGateway$2.70$13.50——200,00064,000
AbacusGateway$3.00$15.00——200,00064,000
OpenRouter
anthropic/claude-sonnet-4
Gateway$3.00
tiered >200K: $6.00
$15.00$0.30$3.75200,00064,000
ZenMux
anthropic/claude-sonnet-4
Gateway$3.00$15.00$0.30$3.751,000,000 ⚠64,000
Vercel AI Gateway
anthropic/claude-sonnet-4
Cloud$3.00
tiered >200K: $6.00
$15.00$0.30$3.751,000,000 ⚠64,000
FastRouter
anthropic/claude-sonnet-4
Gateway$3.00$15.00$0.30$3.75200,00064,000
Vertex (Anthropic)
claude-sonnet-4@20250514
Cloud$3.00$15.00$0.30$3.75200,00064,000deprecated
Merge GatewayGateway$3.00$15.00$0.30$3.75200,00064,000
OpenCode Zen
claude-sonnet-4
Gateway$3.00
tiered >200K: $6.00
$15.00$0.30$3.751,000,000 ⚠64,000

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Reasoning control

Toggle (on / off)effort = loweffort = mediumeffort = highbudget_tokens ≥ 1,024 ≤ 63,999effort = none

2 / 15 providers expose no reasoning control (reasoning_options: []).

Your usage cost

1Poe$889.20
2OpenRouter$1,026.00
3ZenMux$1,026.00
4Vercel AI Gateway$1,026.00
5FastRouter$1,026.00
6Vertex (Anthropic)$1,026.00
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$16.54$02026-08-052026-09-032026-08-05 · Input list $3.312026-08-06 · Input list $3.312026-08-07 · Input list $3.312026-08-08 · Input list $3.312026-08-09 · Input list $3.002026-08-10 · Input list $3.002026-08-11 · Input list $3.002026-08-12 · Input list $3.002026-08-13 · Input list $3.002026-09-03 · Input list $3.002026-08-05 · Output list $16.542026-08-06 · Output list $16.542026-08-07 · Output list $16.542026-08-08 · Output list $16.542026-08-09 · Output list $15.002026-08-10 · Output list $15.002026-08-11 · Output list $15.002026-08-12 · Output list $15.002026-08-13 · Output list $15.002026-09-03 · Output list $15.002026-08-05 · Min blended $5.202026-08-06 · Min blended $5.202026-08-07 · Min blended $5.202026-08-08 · Min blended $5.202026-08-09 · Min blended $5.202026-08-10 · Min blended $5.202026-08-11 · Min blended $5.202026-08-12 · Min blended $5.202026-08-13 · Min blended $6.002026-09-03 · Min blended $5.20

Benchmark1 items

NameConditionsScoreMetricSource
Aider Polyglot—61.3percent correctSource ↗

The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.

Related models

Claude Sonnet 5.5same series$2.00 / $10.00Claude Sonnet 5.5 (EU)same series$2.20 / $11.00Claude Sonnet Latestsame series$2.00 / $10.00GLM-5.2cheaper alternative$1.40 / $4.40GPT OSS 120Bcheaper alternative$2.92 / $2.92GLM-5.3cheaper alternative$1.40 / $4.40GLM-5.3-Flashcheaper alternative$0.15 / $0.50
Data partly from models.dev (MIT) · NanoGPT official docs ↗