LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Claude Haiku 4.5 (latest)

anthropic·anthropic/claude-haiku-4-5·GA·Closed·claude-haiku series
Fast Claude lane for lightweight agents, office tasks, and responsive chat

Specs & pricing

Input / output per 1M tokens
Official price·Anthropic
$1.00 / $5.00
Blended $2.00 · Cache read $0.10
Lowest paid·Teapot RouterGateway
$0.35 / $1.75
Blended $0.70 · 4.4× spread
Context
200,000
Output limit
64,000
Knowledge cutoff
2025-02-28
Released / updated
2025-10-15 / 2025-10-15
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImagePDF

Claude Haiku 4.5 (latest) by anthropic is offered by 49 providers on this page. Public prices are shown for 46 of them. Its official list price is $1.00 per 1M input tokens and $5.00 per 1M output tokens. The lowest paid channel is Teapot Router at $0.35 / $1.75 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.

Artificial Analysis rates it 7.4 on the Intelligence Index, with 19.4 for Finance & Accounting, its strongest domain. Against its lowest blended price of $0.70 per 1M, that is roughly 11 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 101 tokens per second, with 21.58s to the first token. Running one task of the Artificial Analysis suite costs about $0.5318, which reflects how many tokens its reasoning consumes rather than the unit price alone.

The context window is 200,000 tokens at the reference host, but hosts report different limits, from 192,000 to 200,000, 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. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2025-02-28.

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

Intelligence7.4
Value11
Engineering17
Finance & Accounting19.4
Legal18
Healthcare & Medical12.1
Strategy & Ops11.2
Economics19.1
Output speed101 tok/s
TTFT21.58 s
Cost per task$0.53
Value formulaIQ 7.4 ÷ min blended $0.700 = 11

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

Available at 49 providers46 with public prices

  • ProviderInput / Output
  • Teapot RouterGateway
    $0.35 / $1.75
    Context 200,000Output limit 64,000
  • xxapiGateway
    $0.38 / $1.92
    Cache read $0.038Context 200,000Output limit 64,000
  • Outer LabsGateway
    $0.60 / $3.00
    Cache read $0.06Context 200,000Output limit 64,000
  • KoRouterGateway
    $0.65 / $3.25
    Cache read $0.065Context 200,000Output limit 64,000
  • XpersonaGateway
    $0.60 / $3.70
    Cache read $0.06Context 200,000Output limit 128,000
  • KunavoGateway
    $0.70 / $3.50
    Cache read $0.07Context 200,000Output limit 64,000
  • PoeGateway
    anthropic/claude-haiku-4.5
    $0.86 / $4.29
    Cache read $0.086Context 192,000 ⚠Output limit 64,000
  • AnthropicOfficialFirst-party
    $1.00 / $5.00
    Cache read $0.10Context 200,000Output limit 64,000
  • Perplexity AgentGateway
    $1.00 / $5.00
    Cache read $0.10Context 200,000Output limit 64,000
  • CrossModelGateway
    $1.00 / $5.00
    Cache read $0.10Context 200,000Output limit 64,000
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Teapot RouterGateway$0.35$1.75——200,00064,000
xxapiGateway$0.38$1.92$0.038$0.48200,00064,000
Outer LabsGateway$0.60$3.00$0.06$0.75200,00064,000
KoRouterGateway$0.65$3.25$0.065$0.81200,00064,000
XpersonaGateway$0.60$3.70$0.06—200,000128,000
KunavoGateway$0.70$3.50$0.07$0.88200,00064,000
Poe
anthropic/claude-haiku-4.5
Gateway$0.86$4.29$0.086$1.07192,000 ⚠64,000
AnthropicOfficialFirst-party$1.00$5.00$0.10$1.25200,00064,000
Perplexity AgentGateway$1.00$5.00$0.10$1.25200,00064,000
CrossModelGateway$1.00$5.00$0.10$1.25200,00064,000

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

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

Interleaved thinking (reasoning between tool calls) is declared by 6 of 49 providers.

6 / 49 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1xxapi$131.53
2Teapot Router$157.50
3Outer Labs$205.20
4KoRouter$222.30
5Kunavo$239.40
6Xpersona$240.20
8Anthropic · Official$342.00
Switch to xxapi to save $210.47/mo (62%)
Note: this is a gateway; verify availability and rate limits yourself.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$5.00$02026-08-052026-11-15
2026-11-15Input list $1.00Output list $5.00Min blended $0.70

Benchmark1 items

NameConditionsScoreMetricSource
SWE-Bench Prodataset: public39.45resolve rateSource ↗

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

Related models

Claude Haiku 5.5same series$0.10 / $0.50Claude Haiku Latestsame series—Claude Haiku 4.5same series$1.00 / $5.00GLM-5.3-Flashcheaper alternative$0.15 / $0.50DeepSeek V4.1 Flash 1017cheaper alternative$0.15 / $0.60GPT-5.6 Lunacheaper alternative$0.20 / $1.20MiniMax-M3cheaper alternative$0.30 / $1.20Claude Fable Latestsame lab—
Data partly from models.dev (MIT) · Anthropic official docs ↗