Home › Compare › Claude Haiku 5.5 vs Gemini 3.1 Flash-Lite
Claude Haiku 5.5 vs Gemini 3.1 Flash-Lite
A straight cost comparison of Claude Haiku 5.5 (Anthropic) and Gemini 3.1 Flash-Lite (Google Gemini), per 1,000,000 tokens, verified November 2026.
Rate-by-rate comparison
| Metric | Claude Haiku 5.5 | Gemini 3.1 Flash-Lite | Winner |
|---|---|---|---|
| Input / 1M | $0.10 | $0.25 | Claude Haiku 5.5 |
| Cached input / 1M | $0.01 | $0.025 | Claude Haiku 5.5 |
| Cache write / 1M | $0.125 | — | Gemini 3.1 Flash-Lite |
| Output / 1M | $0.50 | $1.50 | Claude Haiku 5.5 |
| Context window | 200,000 | 1,000,000 | Gemini 3.1 Flash-Lite |
| Batch API | Yes | Yes | Tie |
| Long-context tier | > 100,000 | None | — |
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
| Model | Blended cost | Difference |
|---|---|---|
| Claude Haiku 5.5 | $0.225 | Cheaper |
| Gemini 3.1 Flash-Lite | $0.625 | +$0.40 |
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.
| Workload | Claude Haiku 5.5 | Gemini 3.1 Flash-Lite | Winner |
|---|---|---|---|
| Classification 100K reqs · 500 in / 10 out | $5.50 | $14 | Claude Haiku 5.5 |
| Data extraction 10K reqs · 2K in / 200 out | $3 | $8 | Claude Haiku 5.5 |
| Support chat 1K reqs · 4K in / 600 out | $0.70 | $1.90 | Claude Haiku 5.5 |
| Code review 2K reqs · 8K in / 1.5K out | $3.10 | $8.50 | Claude Haiku 5.5 |
| Summarisation 1K reqs · 20K in / 1K out | $2.50 | $6.50 | Claude Haiku 5.5 |
| Agent loop 5K reqs · 12K in / 2K out | $11 | $30 | Claude Haiku 5.5 |
| Translation 500 reqs · 15K in / 15K out | $4.50 | $13.13 | Claude Haiku 5.5 |
| Long-document QA 200 reqs · 120K in / 800 out | $12.08 | $6.24 | Gemini 3.1 Flash-Lite |
| Cached RAG 1K reqs · 50K in (45K cached) / 1K out | $1.46 | $3.89 | Claude Haiku 5.5 |
| Nightly batch 10K reqs · 10K in / 2K out | $10 | $27.50 | Claude Haiku 5.5 |
Claude Haiku 5.5 wins 9 of 10, Gemini 3.1 Flash-Lite wins 1 of 10. The winner is set by the token mix, not by the headline rate.
Where the two bills cross over
Claude Haiku 5.5 is cheaper on both sides of the mix: $0.10 vs $0.25 per million input tokens, and $0.50 vs $1.50 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 / month | Claude Haiku 5.5 | Gemini 3.1 Flash-Lite | Difference |
|---|---|---|---|
| 100 | $0.07 | $0.19 | Claude Haiku 5.5 cheaper by $0.12 |
| 1,000 | $0.70 | $1.90 | Claude Haiku 5.5 cheaper by $1.20 |
| 10,000 | $7 | $19 | Claude Haiku 5.5 cheaper by $12 |
| 100,000 | $70 | $190 | Claude Haiku 5.5 cheaper by $120 |
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 prompt | Claude Haiku 5.5 | Gemini 3.1 Flash-Lite | Winner |
|---|---|---|---|
| 0% | $0.70 | $1.90 | Claude Haiku 5.5 |
| 50% | $0.52 | $1.45 | Claude Haiku 5.5 |
| 80% | $0.412 | $1.18 | Claude Haiku 5.5 |
| 95% | $0.358 | $1.05 | Claude Haiku 5.5 |
Both models publish a cached-read rate, so the discount is comparable: Claude Haiku 5.5 reads cache at $0.01 per million, Gemini 3.1 Flash-Lite at $0.025.
Which one should you pick?
Claude Haiku 5.5 wins on classification, data extraction, support chat, code review, summarisation, agent loop, translation, cached rag, nightly batch, while Gemini 3.1 Flash-Lite wins on long-document qa.
Beyond price, the two differ on input rate ($0.10 vs $0.25); output rate ($0.50 vs $1.50); cached-input rate ($0.01 vs $0.025); cache-write rate ($0.125 vs —); context window (200,000 vs 1,000,000); long-context tier (yes, above 100,000 vs none).
Batch mode is available on Claude Haiku 5.5 and Gemini 3.1 Flash-Lite, which halves the nightly job. Both publish cached-input discounts, so a stable system prompt is worth caching on either.
FAQ
Is Claude Haiku 5.5 cheaper than Gemini 3.1 Flash-Lite?
On a blended 1M-input-plus-250K-output workload, Claude Haiku 5.5 is cheaper by 64% ($0.225 vs $0.625). The gap changes for cache-heavy prompts and for batch jobs, as the workload table shows.
Which handles longer prompts, Claude Haiku 5.5 or Gemini 3.1 Flash-Lite?
Claude Haiku 5.5 has the larger context window (1,000,000 vs 200,000 tokens). Watch the long-context threshold on Claude Haiku 5.5: rates rise once input passes it.
Do both models support prompt caching?
Claude Haiku 5.5 bills cached reads at $0.01 per 1M; Gemini 3.1 Flash-Lite at $0.025.
Related comparisons
- Claude Haiku 4.5 vs Claude Haiku 5.5
- Gemini 3.5 Flash-Lite vs Gemini 3.1 Flash-Lite
- GPT-6 Luna vs Claude Haiku 5.5
- All Anthropic pricing
- All Google Gemini pricing