Start free trial

Anthropic: Claude Haiku 4.5

anthropic/claude-haiku-4-5
CompareAPITry this model

Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models.

Modalities
In / out per 1M$1.00 / $5.00
Context195K
ReleasedOct 15, 2025

Providers

8 providers serve this model upstream.

Providers serving this model
ProviderInput /MOutput /MCache read /MLatency P50Throughput P50Uptime
Azureglobal$1.00$5.00$0.100.38s69 tps100%
Amazon Bedrock$1.00$5.00$0.100.71s97 tps100%
Anthropic$1.00$5.00$0.100.40s71 tps100%
Amazon Bedrockus-east-1$1.10$5.50$0.110.85s132 tps100%
Google Vertexus-east5$1.10$5.50$0.112.54s192 tps100%
Amazon Bedrockeu-west-1$1.10$5.50$0.110.47s172 tps100%
Google Vertexeurope-west1$1.10$5.50$0.110.23s81 tps100%
Google Vertexglobal$1.00$5.00$0.100.67s87 tps99.93%

Market-wide measurements, refreshed every 15 minutes. They describe who serves Claude Haiku 4.5 in general, not how ProjectCOZY routes your requests.

Pricing

List rates per 1M tokens — what Claude Haiku 4.5 costs pay-as-you-go elsewhere, not what you pay here.

Input
$1.00
per 1M tokens
Output
$5.00
per 1M tokens
Cache read
$0.10
per 1M cached tokens
Included in every pass
Claude Haiku 4.5 is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.

Performance

Time to first token and output speed across every provider, over the last 3 days.

0.0s2.0s4.0s6.0s8.0s
Oct 29, 12 AMOct 29, 8 AMOct 29, 4 PMOct 30, 12 AMOct 30, 8 AMOct 30, 4 PMOct 31, 12 AMOct 31, 8 AMOct 31, 4 PMNov 1, 12 AMNov 1, 8 AMNov 1, 4 PM
Google Vertex (global) Amazon Bedrock (eu-west-1) Azure (global) Amazon Bedrock Google Vertex (europe-west1) Anthropic Google Vertex (us-east5) Amazon Bedrock (us-east-1)
0 tok/s500 tok/s1000 tok/s1500 tok/s2000 tok/s
Oct 29, 12 AMOct 29, 8 AMOct 29, 4 PMOct 30, 12 AMOct 30, 8 AMOct 30, 4 PMOct 31, 12 AMOct 31, 8 AMOct 31, 4 PMNov 1, 12 AMNov 1, 8 AMNov 1, 4 PM
Google Vertex (global) Amazon Bedrock (eu-west-1) Azure (global) Amazon Bedrock Google Vertex (europe-west1) Anthropic Google Vertex (us-east5) Amazon Bedrock (us-east-1)

Uptime

100% of requests were served successfully over the last 3 days, across all providers.

Last 3 daysAvailability 99.86%
Oct 29, 5:00 PMNow
Availability over the last 24 hoursAvailability 99.88%
100% 98% 97% 95%
Oct 31, 5:20 PMNow

Apps

Tools that most often run Claude Haiku 4.5, by tokens this week.

Claude CodeCli Agent · 41.2% of tokens49.5BHermes AgentPersonal Agent · 21.3% of tokens25.6BDescriptVideo Gen · 14.1% of tokens17.0BOpenClawPersonal Agent · 12.1% of tokens14.5BRevRing Max11.2% of tokens13.5B

Activity

779.0B tokens processed market-wide in the last month.

020.0B40.0B60.0B80.0B
Oct 2Oct 7Oct 12Oct 17Oct 22Oct 27Nov 1
Tokens

FAQ

Which model id do I use for Claude Haiku 4.5?
anthropic/claude-haiku-4.5. Send it as the model field from any OpenAI-compatible client, against https://minuykh.app/v1.
How much context does Claude Haiku 4.5 hold?
200,000 tokens per request, of which up to 64,000 can be the response.
What can it accept and return?
Input: text, image, file. Output: text.
What does Claude Haiku 4.5 cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $1.00 per 1M input tokens and $5.00 per 1M output tokens.
Who built Claude Haiku 4.5?
Anthropic, in the Claude family.

Explore

Other models your pass can call.

Aion 3.5aion-labs/aion-3.5256KAionAion 3.5 Miniaion-labs/aion-3.5-mini256KAionAion-2.0aion-labs/aion-2.0128KAionAion-3.0aion-labs/aion-3.0128KAionAion-3.0-Miniaion-labs/aion-3.0-mini128KAionAion-RP 1.0 (8B)aion-labs/aion-rp-llama-3.1-8b32KAion