TokenRate
Anthropic

Claude Haiku 3.5

Claude Haiku 3.5 by Anthropic. Official list price: $0.8 per 1M input and $4 per 1M output tokens.

Official price benchmark

USD per 1M tokens

input
$0.800
output
$4.00
cache read
$0.080
Official pricing page ↗

Your budget

$100Budget

Input:output ratio · Similar amounts of input and output

Purchasing power ranking

$100 · Claude Haiku 3.5 · Balanced

Best price

Tokemart

−94%

providers

9

max −94%

Purchasing power ranking

The provider's published prices next to the vendor's official list.

#ProviderInputOutputCacheUptimeLatencyScoreTokens for budgetSave
—
Official price
$0.800$4.00$0.080———41.7M0%
1
Tokemartdemooperational
Minimum top-up: $2· Nov 06, 2026
$0.046$0.228$0.004998.7%930 ms92731M−94%
2
SwiftRoutedemooperational
Minimum top-up: $5· Nov 05, 2026
$0.071$0.355$0.0065100.0%616 ms96470M−91%
3
PromptPortdemooperational
Minimum top-up: ¥10· Nov 05, 2026
$0.095$0.474$0.0095100.0%458 ms98352M−88%
4
ModelMilldemooperational
Minimum top-up: $1· Nov 06, 2026
$0.127$0.636$0.013100.0%751 ms95262M−84%
5
NovaRelaydemooperational
Minimum top-up: $5· Nov 05, 2026
$0.174$0.869$0.018100.0%518 ms97192M−78%
6
FluxAPIdemooperational
Minimum top-up: $10· Nov 05, 2026
$0.370$1.85$0.039100.0%391 ms9990.0M−54%
7
RelayOnedemooperational
Minimum top-up: $50· Nov 09, 2026
$0.449$2.24$0.048100.0%350 ms9974.3M−44%
8
ByteGatedemooperational
Minimum top-up: $25· Nov 10, 2026
$0.494$2.47$0.05198.7%656 ms9567.4M−38%

Some links on this site are partner links. They do not affect prices or ranking. Uptime and latency come from our own GET /models probes every 30 minutes, not a guarantee that the model is available.

Cost estimate

What one request and a month of traffic cost at the selected provider.

per request

$0

per month

$1.03

Tokemart · −94% · 1.20K / 500

Other models

Frequently asked questions

Answers are generated from the live quotes.

We collect Claude Haiku 3.5 prices two ways: the official Anthropic list and quotes from providers our crawler checks daily. Providers in our catalogue sell Claude Haiku 3.5 at $0.046 in / $0.228 out (94% below the official list). Everything is normalised to a blended cost at a chosen input:output ratio, so “Claude Haiku 3.5 price per 1M tokens” means the same thing on every page.

What does the Claude Haiku 3.5 API cost?

The official Anthropic list price is $0.800 per 1M input tokens and $4.00 per 1M output tokens. Cached input is $0.080 per 1M tokens, 10× cheaper than the regular input.

How much does 1 million tokens of Claude Haiku 3.5 cost?

1M input tokens cost $0.800, 1M output tokens — $4.00. With a 1:1 input/output load a million tokens works out to about $2.40. Chatbots with long context push the blended price down; code generation pushes it up.

Where is the Claude Haiku 3.5 API cheapest?

Our measurements show Tokemart as the cheapest: 94% below the official price (sample listing). Quotes from 9 providers refresh daily — see the table above.

What is the Claude Haiku 3.5 context window?

The context window is 200K tokens. Some vendors raise the price above a context threshold — check the plan notes.

How do I check that a provider key works?

The free checker sends a GET request to your endpoint's model list and reports status and latency. The key is not stored server-side.