LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Claude Sonnet 4.5 (latest)

anthropic·anthropic/claude-sonnet-4-5·Deprecated·Closed·claude-sonnet series
Balanced Claude model for coding, analysis, agent workflows, and cost control

Specs & pricing

Input / output per 1M tokens
Official price·Anthropic
$3.00 / $15.00
Blended $6.00 · Cache read $0.30
Lowest paid·PoeGateway
$2.58 / $12.88
Blended $5.15 · 1.8× spread
Context
200,000
Output limit
64,000
Knowledge cutoff
2025-07-31
Released / updated
2025-09-29 / 2025-09-29
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
Modalities
TextImagePDF

Claude Sonnet 4.5 (latest) by anthropic is offered by 35 providers on this page. Public prices are shown for 33 of them. Its official list price is $3.00 per 1M input tokens and $15.00 per 1M output tokens. Prices vary about 1.8× across the providers that host it.

Median output speed is 49 tokens per second, with 13.63s to the first token.

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, tool use, and structured output. Accepted input modalities are Text, Image, and PDF. Its training knowledge cuts off at 2025-07-31.

Quality & performanceArtificial Analysis · Intelligence Index v5 · rep. tier Reasoning

Intelligence—
Value—
Output speed49 tok/s
TTFT13.63 s

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 35 providers33 with public prices

  • ProviderInput / Output
  • PoeGateway
    anthropic/claude-sonnet-4.5
    $2.58 / $12.88
    Cache read $0.26Context 983,040 ⚠Output limit 32,768
  • AnthropicOfficialFirst-party
    $3.00 / $15.00
    Cache read $0.30Context 200,000Output limit 64,000deprecated
  • Perplexity AgentGateway
    $3.00 / $15.00
    Cache read $0.30Context 200,000Output limit 64,000
  • LLM GatewayGateway
    $3.00 / $15.00
    Cache read $0.30Context 200,000Output limit 64,000
  • LLM GatewayGateway
    $3.00 / $15.00
    Cache read $0.30Context 200,000Output limit 64,000
  • LLM GatewayGateway
    $3.00 / $15.00
    Cache read $0.30Context 200,000Output limit 8,192
  • RequestyGateway
    $3.00 / $15.00
    tiered >200K: $6.00
    Cache read $0.30Context 1,000,000 ⚠Output limit 64,000
  • DigitalOceanCloud
    anthropic-claude-4.5-sonnet
    $3.00 / $15.00
    tiered >200K: $6.00
    Cache read $0.30Context 200,000Output limit 64,000
  • NanoGPTGateway
    anthropic/claude-sonnet-4.5
    $3.00 / $15.00
    Cache read $0.30Context 200,000Output limit 64,000
  • NanoGPTGateway
    anthropic/claude-sonnet-4.5:thinking
    $3.00 / $15.00
    Cache read $0.30Context 200,000Output limit 64,000
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Poe
anthropic/claude-sonnet-4.5
Gateway$2.58$12.88$0.26$3.22983,040 ⚠32,768
AnthropicOfficialFirst-party$3.00$15.00$0.30$3.75200,00064,000deprecated
Perplexity AgentGateway$3.00$15.00$0.30$3.75200,00064,000
LLM GatewayGateway$3.00$15.00$0.30$3.75200,00064,000
LLM GatewayGateway$3.00$15.00$0.30$3.75200,00064,000
LLM GatewayGateway$3.00$15.00$0.30$3.75200,0008,192
RequestyGateway$3.00
tiered >200K: $6.00
$15.00$0.30$3.751,000,000 ⚠64,000
DigitalOcean
anthropic-claude-4.5-sonnet
Cloud$3.00
tiered >200K: $6.00
$15.00$0.30$3.75200,00064,000
NanoGPT
anthropic/claude-sonnet-4.5
Gateway$3.00$15.00$0.30$3.75200,00064,000
NanoGPT
anthropic/claude-sonnet-4.5:thinking
Gateway$3.00$15.00$0.30$3.75200,00064,000

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

budget_tokens ≥ 1,024 ≤ 63,999effort = loweffort = mediumeffort = higheffort = xhigheffort = maxeffort = noneToggle (on / off)

Interleaved thinking (reasoning between tool calls) is declared by 4 of 35 providers.

3 / 35 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1Poe$880.92
2Anthropic · Official$1,026.00
3Perplexity Agent$1,026.00
4LLM Gateway$1,026.00
5LLM Gateway$1,026.00
6LLM Gateway$1,026.00
Switch to Poe to save $145.08/mo (14%). The gap is small, so staying on the official channel is fine.
Note: this is a gateway; verify availability and rate limits yourself.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$15.00$02026-08-052026-10-22
2026-10-22Input list $3.00Output list $15.00Min blended $5.15

Benchmark1 items

NameConditionsScoreMetricSource
SWE-Bench Prodataset: public43.6resolve rateSource ↗

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 5same series$2.00 / $10.00Claude Sonnet Latestsame series—GLM-5.3cheaper alternative$1.40 / $4.40GLM-5.3-Flashcheaper alternative$0.15 / $0.50DeepSeek V4.1 Flash 1017cheaper alternative$0.15 / $0.60GLM-5.2cheaper alternative$1.40 / $4.40Claude Sonnet 4same lab—Claude Sonnet 4.5same lab$3.00 / $15.00
Data partly from models.dev (MIT) · Anthropic official docs ↗