BroadRouter

Claude Haiku 4.5 vs GPT-5.4 Mini API pricing

Updated

Claude Haiku 4.5: USD 1 input, USD 5 output per 1M tokens (Anthropic and 3 others). GPT-5.4 Mini: USD 0.75 input, USD 4.50 output per 1M tokens (OpenAI and 2 others). At 3 input tokens per output token, Claude Haiku 4.5 costs 19% more than GPT-5.4 Mini (USD 2 vs USD 1.688 per 1M).

Picked by the same-tier rule: both are in the fourth quarter of the indexed models by price (above USD 1.40 per 1M tokens at 3:1) and in the same size class, small (a tier word such as Flash, Mini or Haiku, or 40B parameters or fewer). GPT-5.4 Mini is the 1st-closest-priced model from another maker to Claude Haiku 4.5 in that bucket. Price only: every number is computed from prices read from each provider's own pricing page (linked per cell, newest check 2026-11-14), with no claim about quality, speed or accuracy.

How do Claude Haiku 4.5 and GPT-5.4 Mini differ on price?

Claude Haiku 4.5 and GPT-5.4 Mini prices side by side

USD per 1M tokens, standard tier. "Cheapest" is the lowest price at 3 input tokens to 1 output token; each line can come from a different provider.

Claude Haiku 4.5 and GPT-5.4 Mini API prices compared
PriceClaude Haiku 4.5GPT-5.4 Mini
Model pageClaude Haiku 4.5
Anthropic · 5 providers
GPT-5.4 Mini
OpenAI · 3 providers
Cheapest standard price, blended 3:1USD 2
USD 1 in / USD 5 out at Anthropic and 3 others
Anthropic page checked 2026-11-14
USD 1.688 lower
USD 0.75 in / USD 4.50 out at OpenAI and 2 others
OpenAI page checked 2026-11-14
Cheapest inputUSD 1
Anthropic source
USD 0.75 lower
OpenAI source
Cheapest cached inputUSD 0.10
Anthropic source
USD 0.075 lower
OpenAI source
Cheapest outputUSD 5
Anthropic source
USD 4.50 lower
OpenAI source
Maker's own APIUSD 1 / USD 5
Anthropic source
USD 0.75 / USD 4.50
OpenAI source
Median standard priceUSD 1 / USD 5
input / output, 5 prices
USD 0.75 / USD 4.50
input / output, 3 prices
Context window200,000 tokens, largest statedNo provider states one on its pricing page.
Providers with a standard price53

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

What do Claude Haiku 4.5 and GPT-5.4 Mini cost for a real workload?

30 days at each model's cheapest standard price for the workload (presets of the cost calculator; cached input at the cached price where listed).

Monthly cost of three workloads on Claude Haiku 4.5 and GPT-5.4 Mini
WorkloadClaude Haiku 4.5GPT-5.4 MiniDifference
Support chatbot
2,000 requests a day, 1,500 input tokens (60% cached), 300 output
USD 131.40
Anthropic
USD 112.05
OpenAI
USD 19.35
GPT-5.4 Mini lower
RAG over documents
1,000 requests a day, 8,000 input tokens (30% cached), 500 output
USD 250.20
Anthropic
USD 198.90
OpenAI
USD 51.30
GPT-5.4 Mini lower
Coding agent (one developer)
1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning
USD 873.00
Anthropic
USD 722.25
OpenAI
USD 150.75
GPT-5.4 Mini lower

GPT-5.4 Mini is cheaper on all three workloads. The widest gap is on RAG over documents: the dearer model costs 26% more than the cheaper one.

Does the cheaper model change with your input:output ratio?

GPT-5.4 Mini is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below Claude Haiku 4.5's, so the input:output ratio never changes the answer.

Price per 1M tokens of Claude Haiku 4.5 and GPT-5.4 Mini at different input:output mixes
Input : output tokensClaude Haiku 4.5GPT-5.4 Mini
1 : 3 (long answers)USD 4
Anthropic
USD 3.563 lower
OpenAI
1 : 1USD 3
Anthropic
USD 2.625 lower
OpenAI
3 : 1 (the site’s blend)USD 2
Anthropic
USD 1.688 lower
OpenAI
10 : 1 (retrieval, long prompts)USD 1.364
Anthropic
USD 1.091 lower
OpenAI
30 : 1 (agents, big contexts)USD 1.129
Anthropic
USD 0.871 lower
OpenAI

USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.

What do Claude Haiku 4.5 and GPT-5.4 Mini cost per character in other languages?

Not measured: the real cost by language dataset covers only tokenizers we could measure from published files, and Claude Haiku 4.5 and GPT-5.4 Mini are not among them. Count tokens on your own text with the counters below.

Check it on your own traffic

More comparisons: Claude Haiku 5.5 vs Claude Haiku 4.5 · GPT-5.4 Mini vs GPT-5 Mini · GPT-5.4 Mini vs GPT-5.4 Nano · GPT-5.4 Pro vs GPT-5.4 Mini · every Claude Haiku 4.5 comparison · every GPT-5.4 Mini comparison · all 662 price comparisons

Questions

Is Claude Haiku 4.5 cheaper than GPT-5.4 Mini?

No. On a blend of 3 input tokens to 1 output token, GPT-5.4 Mini costs USD 1.688 per 1M tokens and Claude Haiku 4.5 USD 2, at each model's cheapest standard price. For input alone, GPT-5.4 Mini is cheaper (USD 0.75 against USD 1 per 1M); for output alone, GPT-5.4 Mini is (USD 4.50 against USD 5). This compares price only, not quality.

What do Claude Haiku 4.5 and GPT-5.4 Mini cost per 1M tokens?

Claude Haiku 4.5: from USD 1 input and USD 5 output at Anthropic and 3 others; Anthropic's own API charges USD 1 / USD 5; median of 5 standard prices USD 1 / USD 5. GPT-5.4 Mini: from USD 0.75 input and USD 4.50 output at OpenAI and 2 others; OpenAI's own API charges USD 0.75 / USD 4.50; median of 3 standard prices USD 0.75 / USD 4.50. Each price is read from the provider's own pricing page; the source is linked in the table.

Which providers sell both Claude Haiku 4.5 and GPT-5.4 Mini?

1 provider has a standard price for both: DigitalOcean (USD 2 and USD 1.688 at 3:1). Buying each model from its own cheapest provider costs USD 2 and USD 1.688.

Which is cheaper for a coding agent or a chatbot, Claude Haiku 4.5 or GPT-5.4 Mini?

For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 873.00 a month on Claude Haiku 4.5 (Anthropic) against USD 722.25 on GPT-5.4 Mini (OpenAI), a difference of USD 150.75. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 131.40 a month on Claude Haiku 4.5 (Anthropic) against USD 112.05 on GPT-5.4 Mini (OpenAI), a difference of USD 19.35. Each uses the cheapest standard price for that workload, cached input included. Try your own numbers.

At what input:output ratio does the cheaper of Claude Haiku 4.5 and GPT-5.4 Mini change?

GPT-5.4 Mini is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below Claude Haiku 4.5's, so the input:output ratio never changes the answer.

Do Claude Haiku 4.5 and GPT-5.4 Mini have cached input pricing?

Claude Haiku 4.5 from USD 0.10 per 1M cached input tokens (Anthropic; 4 of 5 standard prices list a discount). GPT-5.4 Mini from USD 0.075 per 1M cached input tokens (OpenAI; 3 of 3 standard prices list a discount). Cached tokens are billed at the input price where no cache price is published.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity