Verified November 2026

Home › Compare › Claude Haiku 4.5 vs Gemini 4 Hydrogen

Claude Haiku 4.5 vs Gemini 4 Hydrogen

A straight cost comparison of Claude Haiku 4.5 (Anthropic) and Gemini 4 Hydrogen (Google Gemini), per 1,000,000 tokens, verified November 2026.

$1Claude Haiku 4.5 input / 1M
$1.50Gemini 4 Hydrogen input / 1M
33%Blended price gap
Claude Haiku 4.5Cheaper blended

Rate-by-rate comparison

USD per 1M tokens · November 2026
MetricClaude Haiku 4.5Gemini 4 HydrogenWinner
Input / 1M$1$1.50Claude Haiku 4.5
Cached input / 1M$0.10$0.075Gemini 4 Hydrogen
Cache write / 1M$1.25—Gemini 4 Hydrogen
Output / 1M$5$7.50Claude Haiku 4.5
Context window200,0001,000,000Gemini 4 Hydrogen
Batch APIYesYesTie
Long-context tierNoneNone—

For per-token metrics, the lower number wins. For context window and batch support, the higher or broader option wins. A dash means the provider does not publish that rate: a missing cache-write fee means writes are not billed per token, while a missing cached-input rate means cache hits bill at the full input rate.

Blended cost: 1M input + 250K output

ModelBlended costDifference
Claude Haiku 4.5$2.25Cheaper
Gemini 4 Hydrogen$3.38+$1.13

Ten workloads, two bills

The same two models, priced across ten workloads that differ only in their input:output ratio. Nothing else changes — no retries, no system prompt, no middleware.

WorkloadClaude Haiku 4.5Gemini 4 HydrogenWinner
Classification
100K reqs · 500 in / 10 out
$55$82.50Claude Haiku 4.5
Data extraction
10K reqs · 2K in / 200 out
$30$45Claude Haiku 4.5
Support chat
1K reqs · 4K in / 600 out
$7$10.50Claude Haiku 4.5
Code review
2K reqs · 8K in / 1.5K out
$31$46.50Claude Haiku 4.5
Summarisation
1K reqs · 20K in / 1K out
$25$37.50Claude Haiku 4.5
Agent loop
5K reqs · 12K in / 2K out
$110$165Claude Haiku 4.5
Translation
500 reqs · 15K in / 15K out
$45$67.50Claude Haiku 4.5
Long-document QA
200 reqs · 120K in / 800 out
$24.80$37.20Claude Haiku 4.5
Cached RAG
1K reqs · 50K in (45K cached) / 1K out
$14.55$18.44Claude Haiku 4.5
Nightly batch
10K reqs · 10K in / 2K out
$100$150Claude Haiku 4.5

Claude Haiku 4.5 wins 10 of 10, Gemini 4 Hydrogen wins 0 of 10. The winner is set by the token mix, not by the headline rate.

Where the two bills cross over

Claude Haiku 4.5 is cheaper on both sides of the mix: $1 vs $1.50 per million input tokens, and $5 vs $7.50 per million output. No input:output ratio reverses that, so on price alone the other model never becomes the better choice — it has to win on context, latency or output quality.

Cost at four scales

The same support-chat workload (4K input, 600 output per request) at four monthly volumes.

Requests / monthClaude Haiku 4.5Gemini 4 HydrogenDifference
100$0.70$1.05Claude Haiku 4.5 cheaper by $0.35
1,000$7$10.50Claude Haiku 4.5 cheaper by $3.50
10,000$70$105Claude Haiku 4.5 cheaper by $35
100,000$700$1,050Claude Haiku 4.5 cheaper by $350

What caching does to each bill

Caching only helps the part of the prompt that repeats. This is the support-chat workload (1,000 requests, 4,000 input tokens each) with an increasing share of that prompt served from a warm cache, written once on the first request.

Cached share of the promptClaude Haiku 4.5Gemini 4 HydrogenWinner
0%$7$10.50Claude Haiku 4.5
50%$5.20$7.65Claude Haiku 4.5
80%$4.12$5.94Claude Haiku 4.5
95%$3.58$5.09Claude Haiku 4.5

Both models publish a cached-read rate, so the discount is comparable: Claude Haiku 4.5 reads cache at $0.10 per million, Gemini 4 Hydrogen at $0.075.

Which one should you pick?

Claude Haiku 4.5 wins on classification, data extraction, support chat, code review, summarisation, agent loop, translation, long-document qa, cached rag, nightly batch, while Gemini 4 Hydrogen wins on none of the ten workloads above.

Beyond price, the two differ on input rate ($1 vs $1.50); output rate ($5 vs $7.50); cached-input rate ($0.10 vs $0.075); cache-write rate ($1.25 vs —); context window (200,000 vs 1,000,000).

Batch mode is available on Claude Haiku 4.5 and Gemini 4 Hydrogen, which halves the nightly job. Both publish cached-input discounts, so a stable system prompt is worth caching on either.

FAQ

Is Claude Haiku 4.5 cheaper than Gemini 4 Hydrogen?

On a blended 1M-input-plus-250K-output workload, Claude Haiku 4.5 is cheaper by 33% ($2.25 vs $3.38). The gap changes for cache-heavy prompts and for batch jobs, as the workload table shows.

Which handles longer prompts, Claude Haiku 4.5 or Gemini 4 Hydrogen?

Claude Haiku 4.5 has the larger context window (1,000,000 vs 200,000 tokens). Neither model publishes a long-context surcharge.

Do both models support prompt caching?

Claude Haiku 4.5 bills cached reads at $0.10 per 1M; Gemini 4 Hydrogen at $0.075.

Related comparisons

Run your own token volumes