Claude Haiku 5.5 with Jev
Claude Haiku 5.5 is a model from Anthropic, released 2026-10-07. It costs $0.100 per million input tokens and $0.500 per million output tokens, reads up to 1M tokens of context, and writes up to 128,000 tokens in one reply. Through llm11, set model to anthropic/claude-haiku-5.5.
- Input price
- $0.100 / 1M
- Output price
- $0.500 / 1M
- Context window
- 1M tokens
- Max output
- 128K tokens
- Cached input
- $0.010 / 1M
- Released
- 2026-10-07
- Accepts
- text, image, file
- Intelligence index
- 43.4
Read from the provider's prompt cache
Artificial Analysis, via the catalogue
Read from the live catalogue and refreshed daily. At blended list price, 77% of the 337 priced models we can call cost more.
Using Claude Haiku 5.5 with Jev
Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. Claude Haiku 5.5 does the answering when Jev sends it work, or when you name it yourself. Claude Haiku 5.5 falls in the llm11-fast band, and the labs and limits it meets make it eligible for that pack. Packs keep a spread of eight models per band, and it is not one of the eight today, so it is only picked when you name it in a custom pool.
Jev is new, so we have not published results for Claude Haiku 5.5 with and without it, and this page does not invent any. Every response comes with a receipt that names the model that answered and what it cost against your most expensive model, so you can measure the pairing on your own traffic.
What a request costs
List price arithmetic, the same sum a receipt does. llm11 adds nothing per request; the only fee is on buying credits.
| Request | Tokens in / out | One | A thousand |
|---|---|---|---|
| Short chat turn | 500 / 200 | $0.00015 | $0.150 |
| Question over retrieved documents | 4,000 / 500 | $0.00065 | $0.650 |
| Long document summary | 30,000 / 1,000 | $0.00350 | $3.50 |
Cheaper models to try
Nothing cheaper scores within a few points of Claude Haiku 5.5 on the intelligence index. These are the nearest cheaper models with a score, so you can see the gap for yourself.
| Model | Input / 1M | Output / 1M | Context | Index | Released |
|---|---|---|---|---|---|
| Mistral Ministral 3 14B 2512 | $0.200 | $0.200 | 262K | 6 | |
| Qwen Qwen3 VL 32B InstructRetires 2026-10-09 | $0.104 | $0.416 | 131K | 11.9 | |
| Google Gemini 2.5 Flash LiteRetires 2026-10-20 | $0.100 | $0.400 | 1.05M | 10.4 | |
| OpenAI GPT-4.1 Nano | $0.100 | $0.400 | 1.05M | 7.8 |
Call it
Same OpenAI request shape. Naming the model pins it, so nothing is routed, and the answer is still checked.
python
from openai import OpenAI
client = OpenAI(base_url="https://www.llm11.com/v1", api_key="llm11_live_...")
res = client.chat.completions.create(
model="anthropic/claude-haiku-5.5",
messages=[{"role": "user", "content": "Hello"}],
)More from Anthropic
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Claude Sonnet 5.5 | $2.00 | $10 | 1M | |
| Claude Opus 5.5 | $4.00 | $20 | 1M | |
| Claude Fable 5.1 | $10 | $50 | 1M | |
| Claude Opus 5 | $5.00 | $25 | 1M | |
| Claude Sonnet 5 | $2.00 | $10 | 1M | |
| Claude Fable 5 | $10 | $50 | 1M |
Questions
- What is Claude Haiku 5.5 with Jev?
- Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. Claude Haiku 5.5 does the answering when Jev sends it work, or when you name it yourself. Claude Haiku 5.5 falls in the llm11-fast band, and the labs and limits it meets make it eligible for that pack. Packs keep a spread of eight models per band, and it is not one of the eight today, so it is only picked when you name it in a custom pool. Routing decisions are made by Jev, TypeSafe AI's System One model.
- Is Claude Haiku 5.5 a System One model?
- No. Claude Haiku 5.5 answers requests. The System One model is Jev, which decides which model answers each one, so the two do different jobs and llm11 uses both.
- How much does Claude Haiku 5.5 cost?
- $0.100 per million input tokens and $0.500 per million output tokens. A 4,000 token prompt with a 500 token answer costs about $0.00065, so a thousand of them is about $0.650. llm11 passes provider list price through and charges 5% when you buy credits.
- What is the Claude Haiku 5.5 context window?
- 1,000,000 tokens, with up to 128,000 tokens in a single reply.
- Does Claude Haiku 5.5 support tool calling and structured output?
- The catalogue lists tool calling, structured output and reasoning controls.
- Can I use Claude Haiku 5.5 through llm11?
- Yes. Set model to anthropic/claude-haiku-5.5 on the OpenAI-compatible endpoint and the request goes to it directly, with verification still running.
- Does Jev route to Claude Haiku 5.5?
- Routing decisions are made by Jev, TypeSafe AI's System One model. Claude Haiku 5.5 falls in the llm11-fast band, and the labs and limits it meets make it eligible for that pack. Packs keep a spread of eight models per band, and it is not one of the eight today, so it is only picked when you name it in a custom pool.
- What is a cheaper alternative to Claude Haiku 5.5?
- Nearest in price and below it: Mistral Ministral 3 14B 2512 at $0.200 in and $0.200 out, Qwen Qwen3 VL 32B Instruct at $0.104 in and $0.416 out and Google Gemini 2.5 Flash Lite at $0.100 in and $0.400 out. Nothing cheaper scores within a few points of Claude Haiku 5.5 on the intelligence index. These are the nearest cheaper models with a score, so you can see the gap for yourself.