LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Claude Sonnet 4.6

anthropic·anthropic/claude-sonnet-4-6·GA·Closed·claude-sonnet series
Claude workhorse for coding agents, careful analysis, and production 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·XpersonaGateway
$0.90 / $5.55
Blended $2.06 · 5.1× spread
1 more $0 channels
Context
1,000,000
Output limit
128,000
Knowledge cutoff
2025-08-31
Released / updated
2026-02-17 / 2026-03-13
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
Modalities
TextImagePDF

Claude Sonnet 4.6 by anthropic is offered by 69 providers on this page. Public prices are shown for 67 of them. Its official list price is $3.00 per 1M input tokens and $15.00 per 1M output tokens. The lowest paid channel is Xpersona at $0.90 / $5.55 per 1M, about 2.9× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. It also has 1 free ($0) channel; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.

Median output speed is 45 tokens per second, with 1.11s to the first token.

The context window is 1,000,000 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 2025-08-31.

Quality & performanceArtificial Analysis · Intelligence Index v5 · rep. tier Non-reasoning, High

Intelligence—
Value—
Output speed45 tok/s
TTFT1.11 s

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

Available at 69 providers67 with public prices · 1 free

  • ProviderInput / Output
  • GitLab DuoCloud
    duo-chat-sonnet-4-6
    Free
    Cache read $0Context 1,000,000Output limit 64,000
  • XpersonaGateway
    $0.90 / $5.55
    Cache read $0.09Context 200,000 ⚠Output limit 128,000
  • Outer LabsGateway
    $1.80 / $9.00
    Cache read $0.18Context 1,000,000Output limit 64,000
  • KunavoGateway
    $2.10 / $10.50
    Cache read $0.21Context 1,000,000Output limit 64,000
  • PoeGateway
    anthropic/claude-sonnet-4.6
    $2.58 / $12.88
    Cache read $0.26Context 983,040 ⚠Output limit 128,000
  • AnthropicOfficialFirst-party
    $3.00 / $15.00
    Cache read $0.30Context 1,000,000Output limit 128,000
  • Perplexity AgentGateway
    $3.00 / $15.00
    Cache read $0.30Context 200,000 ⚠Output limit 64,000
  • CrossModelGateway
    $3.00 / $15.00
    Cache read $0.30Context 1,000,000Output limit 128,000
  • LLM GatewayGateway
    $3.00 / $15.00
    Cache read $0.30Context 1,000,000Output limit 64,000
  • LLM GatewayGateway
    $3.00 / $15.00
    Cache read $0.30Context 1,000,000Output limit 64,000
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
GitLab Duo
duo-chat-sonnet-4-6
CloudFree$0$01,000,00064,000
XpersonaGateway$0.90$5.55$0.09—200,000 ⚠128,000
Outer LabsGateway$1.80$9.00$0.18$2.251,000,00064,000
KunavoGateway$2.10$10.50$0.21$2.631,000,00064,000
Poe
anthropic/claude-sonnet-4.6
Gateway$2.58$12.88$0.26$3.22983,040 ⚠128,000
AnthropicOfficialFirst-party$3.00$15.00$0.30$3.751,000,000128,000
Perplexity AgentGateway$3.00$15.00$0.30$3.75200,000 ⚠64,000
CrossModelGateway$3.00$15.00$0.30$3.751,000,000128,000
LLM GatewayGateway$3.00$15.00$0.30$3.751,000,00064,000
LLM GatewayGateway$3.00$15.00$0.30$3.751,000,00064,000

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

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

Interleaved thinking (reasoning between tool calls) is declared by 8 of 69 providers.

6 / 69 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1Xpersona$360.30
2Outer Labs$615.60
3Kunavo$718.20
4Poe$880.92
5Anthropic · Official$1,026.00
6Perplexity Agent$1,026.00

1 more channels offer $0 (GitLab Duo); free tiers usually have rate limits and no SLA, excluded from ranking.

Switch to Xpersona to save $665.70/mo (65%)
Note: this is a gateway; verify availability and rate limits yourself.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$15.00$02026-08-052026-08-13
2026-08-13Input list $3.00Output list $15.00Min blended $2.06

Benchmark11 items

NameConditionsScoreMetricSource
SWE-Atlas Codebase QnAharness: Claude Code31.2scoreSource ↗
SWE-Atlas Refactoringharness: Claude Code32.21scoreSource ↗
SWE-Atlas Test Writingharness: Claude Code31.76scoreSource ↗
Artificial Analysis Coding Agent Indexharness: Claude Code · variant: medium49.4average pass@1Source ↗
SWE-Atlas Codebase QnAharness: Claude Code · variant: medium70.3pass@1Source ↗
SWE-Bench Proharness: Claude Code · variant: medium · dataset: hard-aa14.9pass@1Source ↗
Terminal-Benchharness: Claude Code · variant: medium · v2.163.1pass@1Source ↗
Terminal-Benchharness: Terminus-2 · v2.167success rateSource ↗
Humanity's Last Examvariant: no tools34.6accuracySource ↗
Humanity's Last Examvariant: with tools46.8accuracySource ↗
OSWorld-Verified—78.5success 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 4.5same lab$3.00 / $15.00
Data partly from models.dev (MIT) · Anthropic official docs ↗