Does claude-haiku-4-5 have a free tier?

Claude Haiku 4.5 is billed per use and the record publishes no free-tier allowance. The current published rates are input $1.0000 per 1M tokens and output $5.0000 per 1M tokens. Trial credit or promotional quota is tied to your account rather than to the model, so check the console before planning around a free tier.

What should you evaluate before moving production traffic to Claude Haiku 4.5?

Test your real-time and high-volume applications. Verify extended thinking, tool-assisted workflows, and coding performance meet your requirements.

What is the max output length for claude-haiku-4-5?

claude-haiku-4-5 supports up to 64000 output tokens per request. Plan your prompts to stay within this limit, and use the max_tokens or max_completion_tokens parameter to control output length.

How does claude-haiku-4-5 compare with other models, and what should you compare?

Compare claude-haiku-4-5 against models of similar capability and pricing on your actual workload. Evaluate latency, output quality, instruction following, and cost per task. Run side-by-side tests with your own prompts — the best model depends on your specific use case, not just benchmark scores.

What is the rate limit for claude-haiku-4-5?

claude-haiku-4-5 rate limits vary by your MixRoute subscription plan. Check your plan details in the console for requests per minute (RPM) and tokens per minute (TPM) limits. Run a small load test before production to confirm your effective quota.

How do you get a cache hit on claude-haiku-4-5?

To get a cache hit on claude-haiku-4-5, send requests with identical prompt prefixes. The cache is keyed by the beginning of your prompt; as long as the prefix matches a previous request, subsequent calls benefit from the lower cached rate. Keep system messages and initial context consistent across calls for best results.

Model detail

Claude Haiku 4.5

Provided by Anthropic

Pay-as-you-go

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. Matching Claude Sonnet 4’s performance across reasoning, coding, and computer-use tasks, Haiku 4.5 brings frontier-level capability to real-time and high-volume applications. It introduces extended thinking to the Haiku line; enabling controllable reasoning depth, summarized or interleaved thought output, and tool-assisted workflows with full support for coding, bash, web search, and computer-use tools. Scoring >73% on SWE-bench Verified, Haiku 4.5 ranks among the world’s best coding models while maintaining exceptional responsiveness for sub-agents, parallelized execution, and scaled deployment.

Model specs

Model ID: claude-haiku-4-5

Context length: 200K
Max output: 64K
I/O modalities
Released: 2025-10

API endpoints

One MixRoute gateway, OpenAI-compatible

Anthropic Messages /v1/messages POST
OpenAI-compatible /v1/chat/completions POST

Pricing

Flat rate, unit: /1M Tokens

Input

$1.0000 /1M Tokens

Completion

$5.0000 /1M Tokens

Cache read

$0.1000 /1M Tokens

Cache creation

$1.2500 /1M Tokens

Selection summary

Quickly judge whether it fits your workload

What is this model good for?

Coding

Claude Haiku 4.5 is built for writing and reviewing code, and it reads images alongside text. It accepts text and image input and returns text. Its capabilities are broken down in the section just below. Run it on one file from your own repository and check the patch before you commit.

What should you check before using it?

200,000 context, 64,000 output tokens

Claude Haiku 4.5 accepts up to 200,000 tokens of context and returns up to 64,000 output tokens per request. Check that your longest prompt and its expected answer fit inside both limits before you size production traffic.

Why use it through MixRoute?

Swap the base URL, keep the Claude Haiku 4.5 client

Keep your existing OpenAI client and swap only the base URL. MixRoute supports calling Claude Haiku 4.5 through its OpenAI-compatible endpoint; point your client at https://api.mixroute.ai/v1 with the model ID claude-haiku-4-5 and re-run your integration tests.

Capabilities & compatibility

Unconfirmed capabilities stay "Unknown," no guesses

Tool calling

Claude Haiku 4.5 supports function and tool calls.

EX Send a tools definition; the response returns tool_calls to execute and feed results back.

Structured output

Claude Haiku 4.5 can produce JSON-formatted output on demand.

EX response_format: { type: "json_schema" } forces valid JSON output.

Streaming

Claude Haiku 4.5 supports streamed responses.

EX stream: true streams tokens incrementally, so chat UIs render as they arrive.

Prompt caching

Claude Haiku 4.5 supports prompt caching under supported routing conditions.

EX Keep the system prompt and tool definitions at the start of the request; repeated prefixes are automatically billed at the cache-read rate.

Vision input

Claude Haiku 4.5 can process image inputs alongside text.

EX Pass a base64-encoded image in a image_url content part alongside text messages.

OpenAI SDK

Call Claude Haiku 4.5 through MixRoute's OpenAI-compatible endpoint.

EX Change base_url to https://api.mixroute.ai/v1; everything else follows the OpenAI style.

Token cost estimator

Live estimate from this page's pricing, not an actual bill

Input tokens Max per request 200K

Output tokens Max per request 64K

Requests / month

Cache hit rate 0%

Share of the same prefix read repeatedly, up to 100%

FAQ

Use the model ID claude-haiku-4-5 through the compatible chat completions endpoint. It supports extended thinking with controllable reasoning depth.

Get started

01

Create an API key

Generate a key in the Console; one key calls every model.
02

Set the base URL

Fully OpenAI SDK-compatible; just swap the URL to connect.

https://api.mixroute.ai/v1
03

Specify the model ID

In the request's model field, enter:

claude-haiku-4-5

Create an API key

New users get $5 in free credits

More from Anthropic

All Anthropic models

Claude Haiku 5.5 Anthropic In $0.10 · Out $0.50 · Cached $0.01 Tiered /1M View model Claude Sonnet 5.5 Anthropic In $2.00 · Out $10.00 · Cached $0.20 /1M View model Claude Opus 5.5 Anthropic In $4.00 · Out $20.00 · Cached $0.20 /1M View model Claude Fable 5.1 Anthropic In $10.00 · Out $50.00 · Cached $0.25 /1M View model

One endpoint, a testable decision

Test this model and alternate routes with the same request format

Start from a real workload, then let quality, total cost, and failure conditions decide whether to send production traffic.

Create an API key View integration docs