Model comparison
Claude Haiku 5.5 vs Gemini 3.8 Flash: pricing, context and features compared
Claude Haiku 5.5 costs $0.10 per million input tokens and $0.50 per million output tokens; Gemini 3.8 Flash costs $0.75 and $3.75. Here is how they compare on specs, on what real workloads cost, and on which to pick for what, from prices updated daily.
Both are the go-to cheaper models of their providers for high-volume work. Their price structures differ (long-prompt surcharges, batch rules), so the cheaper one depends on what you send.
- Input / 1M
- $0.10
- Output / 1M
- $0.50
- Context
- 1,000,000
- Max output
- 128,000
- Input / 1M
- $0.75
- Output / 1M
- $3.75
- Context
- 1,048,576
- Max output
- 65,536
Verdict
Claude Haiku 5.5 or Gemini 3.8 Flash: which to pick
Claude Haiku 5.5 has the lower list prices: 7.5× cheaper per input token and 7.5× per output token. On our data, Claude Haiku 5.5 has the edge for the lowest bill, very long prompts, long replies, repeated prompts and batch jobs, and Gemini 3.8 Flash for non-text inputs. For scale, a support chatbot handling 1,000 requests a day costs about $8.59 a month on Claude Haiku 5.5 and $64.45 on Gemini 3.8 Flash.
- Lowest bill for typical workloadsPick Claude Haiku 5.5
- Claude Haiku 5.5 costs less on all 4 workloads below, 7.5× cheaper than Gemini 3.8 Flash at list prices.
- Very long prompts (whole codebases, long documents)Pick Claude Haiku 5.5
- Both read about 1,000,000 tokens per request. One 800,000-token prompt with a 2,000-token reply costs $0.41 on Claude Haiku 5.5 and $0.61 on Gemini 3.8 Flash. Claude Haiku 5.5 charges $0.50 / $2.50 per 1M once a prompt passes 100,000 tokens.
- Long replies (reports, large code files)Pick Claude Haiku 5.5
- Claude Haiku 5.5 can write up to 128,000 tokens in one reply, against 65,536 for Gemini 3.8 Flash.
- Images, audio, video or files in the promptPick Gemini 3.8 Flash
- Gemini 3.8 Flash also accepts audio and video, which Claude Haiku 5.5 doesn’t.
- Repeated long prompts (prompt caching)Pick Claude Haiku 5.5
- Claude Haiku 5.5 bills cached input at $0.01 per 1M (10% of its input price), against $0.075 per 1M (10% of its input price) for Gemini 3.8 Flash.
- Overnight batch jobsPick Claude Haiku 5.5
- Both offer batch prices; on the document summariser workload Claude Haiku 5.5 costs $5.02 a month against $37.64.
- Self-hosting or choosing your own hostEither
- Neither has downloadable weights: both are only available through their provider’s API and cloud partners.
Criteria use only list prices, published limits and the features each provider declares. We don’t rank answer quality; test both models on your own prompts before you commit.
Specs
Claude Haiku 5.5 vs Gemini 3.8 Flash side by side
| Spec | Claude Haiku 5.5 | Gemini 3.8 Flash |
|---|---|---|
| Provider | Anthropic | |
| Input / 1M tokens | $0.10 (better) | $0.75 |
| Output / 1M tokens | $0.50 (better) | $3.75 |
| Cached input / 1M | $0.01 (better) | $0.075 |
| Cache write / 1M | $0.125 | No write charge listed |
| Batch in / out | $0.05 / $0.25 (better) | $0.375 / $1.875 |
| Long-prompt price | $0.50 / $2.50 over 100,000 | None |
| Context window | 1,000,000 | 1,048,576 |
| Max output | 128,000 (better) | 65,536 |
| Accepts | text, images, files | text, images, files, audio, video |
| Image input | Yes | Yes |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | Yes |
| Prompt caching | Yes | Yes |
| Structured output | Yes | Yes |
| Open weights | No | No |
| Knowledge cutoff | Not published | Not published |
| First listed | 2026-10-07 | 2026-09-02 |
Prices in US dollars per million tokens. Highlighted: the lower price or larger limit where the difference is over 5%. Features are as declared by each provider’s API; “First listed” is when our data source first listed the model. Long-prompt prices apply to the whole request once the prompt passes the threshold.
Costs
What Claude Haiku 5.5 and Gemini 3.8 Flash cost for real workloads
| Workload | Tokens in / out | Requests/day | Claude Haiku 5.5 / month | Gemini 3.8 Flash / month | Cheaper |
|---|---|---|---|---|---|
| Support chatbotCalculator: Claude Haiku 5.5 · Gemini 3.8 Flash | 1,500 / 400 | 1,000 | $8.5950% cached | $64.4550% cached | Claude Haiku 5.5 (7.5×) |
| RAG appCalculator: Claude Haiku 5.5 · Gemini 3.8 Flash | 6,000 / 500 | 500 | $11.2820% cached | $84.6320% cached | Claude Haiku 5.5 (7.5×) |
| Coding agentCalculator: Claude Haiku 5.5 · Gemini 3.8 Flash | 40,000 / 2,000 | 200 | $12.9080% cached | $96.7380% cached | Claude Haiku 5.5 (7.5×) |
| Document summariserCalculator: Claude Haiku 5.5 · Gemini 3.8 Flash | 8,000 / 600 | 300 | $5.02batch | $37.64batch | Claude Haiku 5.5 (7.5×) |
Each row uses the same token counts for both models and list prices, with caching and batch discounts only where the provider publishes them. A month is 365 ÷ 12 days. The support chatbot reads 50% of its prompt from the cache. The RAG app reads 20% of its prompt from the cache. The coding agent reads 80% of its prompt from the cache. The document summariser runs as a batch job where a batch price exists. Open either model in the LLM cost calculator to change any number.
Tokenizers
Are their per-token prices comparable?
Not exactly. Each model splits text into tokens its own way, so the same prompt can be a different number of tokens on Claude Haiku 5.5 and Gemini 3.8 Flash, and the cheaper per-token price isn’t always the cheaper bill. The last column converts each output price into a price per million English words, which is the fairer comparison for prose.
| Model | Tokenizer | Tokens per 1,000 words | Output per 1M words |
|---|---|---|---|
| Claude Haiku 5.5 | Claude (Opus 4.7 and later)Provider’s published figure | 1,802 | $0.90 |
| Gemini 3.8 Flash | GeminiOur measurement | 1,186 | $4.45 |
English prose, measured on the Universal Declaration of Human Rights (2026-10-11) or taken from the provider’s published words-per-token figure. Code, JSON and other languages use more tokens per word. Count your own text in the token counter or convert with tokens to words.
FAQ
Claude Haiku 5.5 vs Gemini 3.8 Flash questions
Is Claude Haiku 5.5 cheaper than Gemini 3.8 Flash?
Claude Haiku 5.5 costs $0.10 per million input tokens and $0.50 per million output tokens; Gemini 3.8 Flash costs $0.75 and $3.75. For a support chatbot handling 1,000 requests a day, that is about $8.59 a month on Claude Haiku 5.5 against $64.45 on Gemini 3.8 Flash, so Claude Haiku 5.5 is 7.5× cheaper there. Try your own numbers in the LLM cost calculator.
Which has the bigger context window, Claude Haiku 5.5 or Gemini 3.8 Flash?
Their context windows are about the same size. Claude Haiku 5.5 reads up to 1,000,000 tokens (roughly 750,000 English words) and writes up to 128,000 tokens per reply. Gemini 3.8 Flash reads up to 1,048,576 tokens (roughly 786,432 English words) and writes up to 65,536 tokens per reply. The window is shared between your prompt and the reply. Word counts use a rough 0.75 words per token; real ratios depend on the tokenizer.
Is Claude Haiku 5.5 or Gemini 3.8 Flash better for coding?
We don’t publish benchmark scores, so this page can’t say which writes better code. What we can show is cost: a coding agent re-sending 40,000 tokens of context (80% cached) and writing 2,000 tokens, 200 times a day, costs about $12.90 a month on Claude Haiku 5.5 and $96.73 on Gemini 3.8 Flash. Both support tool calling. Test both on tasks from your own repository.
Can Claude Haiku 5.5 and Gemini 3.8 Flash read images?
Claude Haiku 5.5 accepts images and files as well as text. Gemini 3.8 Flash accepts images, files, audio and video as well as text. So both can read screenshots, photos and scanned pages. This is what each provider declares for its API, not a measure of how well it works.
Are Claude Haiku 5.5 and Gemini 3.8 Flash open source?
No. Neither Claude Haiku 5.5 nor Gemini 3.8 Flash has published weights: you can only use them through Anthropic’s and Google’s APIs and their cloud partners. If you need a model you can host yourself, compare open-weight options in the model comparison table.
Do Claude Haiku 5.5 and Gemini 3.8 Flash count tokens the same way?
Not necessarily. Each model splits text into tokens with its own tokenizer, so the same prompt can be a different number of tokens on each, and per-token prices aren’t directly comparable. Claude Haiku 5.5 uses about 1,802 tokens per 1,000 English words (the provider’s published figure). Gemini 3.8 Flash uses about 1,186 tokens per 1,000 English words (our measurement). Count your own text with the token counter or convert with tokens to words.