LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Claude Sonnet 5

anthropic·anthropic/claude-sonnet-5·GA·Closed·claude-sonnet series
Everyday Claude agent model for coding, planning, browsing, and general work

Specs & pricing

Input / output per 1M tokens
Official price·Anthropic
$2.00 / $10.00
Blended $4.00 · Cache read $0.20
Lowest paid·Teapot RouterGateway
$0.70 / $3.50
Blended $1.40 · 4.4× spread
1 more $0 channels
Context
1,000,000
Output limit
128,000
Knowledge cutoff
2026-01-31
Released / updated
2026-06-30 / 2026-06-30
Capabilities
✓ Reasoning✓ Tool use✓ Structured outputTemperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImagePDF

Claude Sonnet 5 by anthropic is offered by 67 providers on this page. Public prices are shown for 65 of them. Its official list price is $2.00 per 1M input tokens and $10.00 per 1M output tokens. The lowest paid channel is Teapot Router at $0.70 / $3.50 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 65 tokens per second, with 1.39s to the first token.

The context window is 1,000,000 tokens, with an output limit of 128,000 tokens. It supports reasoning, tool use, and structured output. 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 2026-01-31.

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

Intelligence—
Value—
Output speed65 tok/s
TTFT1.39 s

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

Available at 67 providers65 with public prices · 1 free

  • ProviderInput / Output
  • GitLab DuoCloud
    duo-chat-sonnet-5
    Free
    Cache read $0Context 1,000,000Output limit 64,000
  • Teapot RouterGateway
    $0.70 / $3.50
    Context 1,000,000Output limit 128,000
  • xxapiGateway
    $0.77 / $3.85
    Cache read $0.077Context 1,000,000Output limit 128,000
  • JZSTOKENGateway
    $0.78 / $3.89
    Cache read $0.078Context 1,000,000Output limit 128,000
  • Outer LabsGateway
    $1.20 / $6.00
    Cache read $0.12Context 1,000,000Output limit 128,000
  • KoRouterGateway
    $1.30 / $6.50
    Cache read $0.13Context 1,000,000Output limit 128,000
  • KunavoGateway
    $1.40 / $7.00
    Cache read $0.14Context 1,000,000Output limit 128,000
  • KenariGateway
    $1.43 / $7.14
    Cache read $0.57Context 1,000,000Output limit 128,000
  • UnoRouterGateway
    $1.44 / $7.20
    Context 1,000,000Output limit 128,000
  • AnthropicOfficialFirst-party
    $2.00 / $10.00
    Cache read $0.20Context 1,000,000Output limit 128,000
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
GitLab Duo
duo-chat-sonnet-5
CloudFree$0$01,000,00064,000
Teapot RouterGateway$0.70$3.50——1,000,000128,000
xxapiGateway$0.77$3.85$0.077$0.961,000,000128,000
JZSTOKENGateway$0.78$3.89$0.078$0.971,000,000128,000
Outer LabsGateway$1.20$6.00$0.12$1.501,000,000128,000
KoRouterGateway$1.30$6.50$0.13$1.631,000,000128,000
KunavoGateway$1.40$7.00$0.14$1.751,000,000128,000
KenariGateway$1.43$7.14$0.57$1.711,000,000128,000
UnoRouterGateway$1.44$7.20——1,000,000128,000
AnthropicOfficialFirst-party$2.00$10.00$0.20$2.501,000,000128,000

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 = higheffort = xhigheffort = maxeffort = none

Interleaved thinking (reasoning between tool calls) is declared by 6 of 67 providers.

6 / 67 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1xxapi$263.07
2JZSTOKEN$266.11
3Teapot Router$315.00
4Outer Labs$410.40
5KoRouter$444.60
6Kunavo$478.80
9Anthropic · Official$684.00

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

Switch to xxapi to save $420.93/mo (62%)
Note: this is a gateway; verify availability and rate limits yourself.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$10.00$02026-08-052026-11-15
2026-11-15Input list $2.00Output list $10.00Min blended $1.40

Benchmark7 items

NameConditionsScoreMetricSource
SWE-Bench Verified—85.2resolvedSource ↗
SWE-Bench Pro—63.2resolve rateSource ↗
SWE-Bench Multilingual—78.3resolve rateSource ↗
Terminal-Benchharness: Terminus-2 · v2.180.4success rateSource ↗
OSWorld-Verified—81.2success rateSource ↗
BrowseCompvariant: single agent84.7accuracySource ↗
FrontierCodevv138.8pass 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 Latestsame series—Claude Sonnet 4.6same series$3.00 / $15.00GLM-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 / $4.40
Data partly from models.dev (MIT) · Anthropic official docs ↗