claude-haiku-5-5 vs gemini-3.8-flash: pricing and capabilities compared
In each model's cheapest group on this site, claude-haiku-5-5 costs ¥0.4 input and ¥2 output (Claude Plus group) and gemini-3.8-flash costs ¥1.5 input and ¥7.5 output (Standard group), per 1M tokens.
claude-haiku-5-5 is cheaper on input, output and cache reads, by 73%, 73% and 73% respectively.
claude-haiku-5-5 is offered in 4 groups and gemini-3.8-flash in 4 groups. Groups offering both: Official · Enterprise; a key in any of them can call either model.
Prices updated Nov 13, 2026, 5:58 PM
At a glance
| Item | claude-haiku-5-5 | gemini-3.8-flash |
|---|---|---|
| Vendor | Anthropic | |
| Billing | Per token | Per token |
| Cheapest group | Claude Plus | Standard |
| Input ¥ per 1M tokens | ¥0.473% lower | ¥1.5 |
| Output ¥ per 1M tokens | ¥273% lower | ¥7.5 |
| Cache read ¥ per 1M tokens | ¥0.0473% lower | ¥0.15 |
| Groups | 4 groups | 4 groups |
| Input types | text and images | text, images, video and audio |
| Output types | text | text |
| Capability tags | Vision and Reasoning | Vision and Reasoning |
| Endpoints | Chat Completions and Claude Messages | Chat Completions and Gemini generateContent |
| Available since | Oct 15, 2026 | Aug 21, 2026 |
Prices are each model's cheapest group, in CNY; the side marked "lower" is cheaper. Data comes from our price list and model catalog; anything not listed shows as —.
Prices in every group
The same model costs different amounts in different groups; a key's group decides its line and its price.
| Group | Input ¥ per 1M tokens | Output ¥ per 1M tokens | Cache read ¥ per 1M tokens |
|---|---|---|---|
| Official · EnterpriseBoth | ¥1.1 | ¥5.48 | ¥0.11 |
| Claude Direct | ¥0.75 | ¥3.75 | ¥0.075 |
| Claude List Price | ¥1.2 | ¥6 | ¥0.12 |
| Claude PlusCheapest | ¥0.4 | ¥2 | ¥0.04 |
| Group | Input ¥ per 1M tokens | Output ¥ per 1M tokens | Cache read ¥ per 1M tokens |
|---|---|---|---|
| StandardCheapest | ¥1.5 | ¥7.5 | ¥0.15 |
| Official · EnterpriseBoth | ¥8.21 | ¥41.06 | ¥0.821 |
| Gemini Plus | ¥3 | ¥15 | ¥0.3 |
| Gemini High Tier | ¥4.5 | ¥22.5 | ¥0.45 |
How to choose
These points use each model's cheapest-group prices and catalog data. Before going live, run real requests with a key in your target group and check quality, speed and billing.
- On unit prices alone (each at its cheapest group): claude-haiku-5-5 is cheaper on input, output and cache reads, so the same token usage costs less.
- When you resend the same long prefix (a fixed system prompt, the same long document), cached input is billed at the cache-read price: claude-haiku-5-5 ¥0.04, gemini-3.8-flash ¥0.15 (per 1M tokens).
- If you need audio input: gemini-3.8-flash accepts audio; claude-haiku-5-5 lists text and images as input.
- If you need video input: gemini-3.8-flash accepts video; claude-haiku-5-5 lists text and images as input.
- Both support Chat Completions, so requests look the same and switching means changing the model parameter (the key's groups must offer both models).
- To call through Claude Messages: of the two, only claude-haiku-5-5 supports it on this site.
- To call through Gemini generateContent: of the two, only gemini-3.8-flash supports it on this site.
- If production needs a known request source, use official or cloud groups. claude-haiku-5-5: Official · Enterprise, Claude Direct and Claude List Price; gemini-3.8-flash: Official · Enterprise, Gemini Plus and Gemini High Tier.
How to call them
Both models work with a Tutujin API key: set your SDK's base_url to https://www.tutujin.com/v1 and use the model name; everything else is written as with the official SDK.
- claude-haiku-5-5: prices in every group, availability and API docs
- gemini-3.8-flash: prices in every group, availability and API docs
- Every Anthropic model and its price
- Every Google model and its price
- Chat Completions API reference
- Claude Messages API reference
- Gemini generateContent API reference
- Quickstart: create a key and send your first request
- How to choose a group
- Models page: every model with prices in every group
- How billing works: pay as you go, groups and balance
More comparisons
FAQ
Which is cheaper, claude-haiku-5-5 or gemini-3.8-flash?
In each model's cheapest group on this site, claude-haiku-5-5 costs ¥0.4 input and ¥2 output (Claude Plus group) and gemini-3.8-flash costs ¥1.5 input and ¥7.5 output (Standard group), per 1M tokens. claude-haiku-5-5 is cheaper on input, output and cache reads, by 73%, 73% and 73% respectively. What you actually pay depends on the split between input and output tokens and on the group you use. Prices updated Nov 13, 2026, 5:58 PM.
How do I call claude-haiku-5-5 and gemini-3.8-flash?
Create an API key in the console, set your SDK's base_url to https://www.tutujin.com/v1 and use claude-haiku-5-5 or gemini-3.8-flash as the model. claude-haiku-5-5 supports: Chat Completions and Claude Messages. gemini-3.8-flash supports: Chat Completions and Gemini generateContent.
Which groups offer claude-haiku-5-5 and gemini-3.8-flash?
claude-haiku-5-5: Official · Enterprise, Claude Direct, Claude List Price and Claude Plus. gemini-3.8-flash: Standard, Official · Enterprise, Gemini Plus and Gemini High Tier. Groups offering both: Official · Enterprise; a key in any of them can call either model.
What input types do claude-haiku-5-5 and gemini-3.8-flash take?
claude-haiku-5-5 takes text and images and returns text. gemini-3.8-flash takes text, images, video and audio and returns text.
Where do the prices on this page come from?
From our live price list — the same data as the model pages and the models page — shown for each model's cheapest group. Prices updated Nov 13, 2026, 5:58 PM.