LLM prices / Anthropic / Claude Haiku 5.5
Anthropic API · prices checked Oct 23, 2026
Claude Haiku 5.5 API pricing
Short answerClaude Haiku 5.5 costs $0.1 per 1M input tokens and $0.5 per 1M output tokens on the Anthropic API (standard price, checked Oct 23, 2026). A typical chatbot reply (1,500 tokens in, 400 out) costs $0.0003, so 1,000 replies a day is about $10.50 a month and 1M replies is $350. That makes it tied #1 cheapest of the 29 current models for that job (same price as GPT-6 Luna).
Best for
- High-volume simple jobs (support chat, tagging, extraction): tied #1 cheapest of 29 current models for a chatbot reply.
- Chatbot: tied #1 cheapest of the 29 current models that fit ($0.35 per 1,000, same as GPT-6 Luna).
- RAG (answer from your docs): tied #1 cheapest of the 29 current models that fit ($0.85 per 1,000, same as GPT-6 Luna).
- Long repeated prompts (agents, RAG with a fixed prefix): cached input bills at 10% of the normal input price.
- Bulk jobs that can wait: the batch API bills input at 50% of the standard price.
- Whole codebases or contracts in one prompt: 1M tokens of context.
- Reading more than text: takes image input.
Skip if
- Your prompts often run past 100,000 tokens: the price rises to $0.5 input / $2.5 output per 1M.
Rules: Best for = cheapest quarter of current models for a chatbot reply, top 3 on one of our 8 jobs, cache reads at 15% or less of input, batch at 60% or less, 1M+ context, non-text inputs. Skip if = not current on the provider's page, priciest quarter, text only, no cache or batch price, a long-prompt surcharge, preview, under 200K context, no tool calling. Price and spec facts only; we don't score answer quality.
What your volume costs
Pick a job and a monthly volume. Same prices as everything on this page; caching and batch applied where they make it cheaper.
Cost per task, 8 jobs
Per 1,000 requests and per month at a typical volume, billed the cheapest way the price list allows. The rank is among current models that fit the job.
| Job (links to the cheapest model for it) | Per 1,000 | A month | Rank among fits |
|---|---|---|---|
| Chatbota 1,500-token prompt (system prompt plus the conversation so far) and a 400-token reply | $0.35standard price | $10.50at 30,000 a month | tied #1 of 29 |
| RAG (answer from your docs)6,000 tokens of retrieved passages plus the question, and a 500-token answer | $0.85standard price | $25.50at 30,000 a month | tied #1 of 29 |
| Coding agent40,000 tokens of repo context and history, 30,000 of them repeated from the last step and billed at the cache-read price, 2,000 tokens out, tool calling required | $2.30with the repeated 30,000 tokens billed at the cache-read price | $6.90at 3,000 a month | tied #1 of 29 |
| Tool-using agent12,000 tokens of instructions, tool definitions and history, 10,000 of them repeated from the last step and cached, 600 tokens out, tool calling required | $0.60with the repeated 10,000 tokens billed at the cache-read price | $6.00at 10,000 a month | tied #1 of 29 |
| Vision (read an image)one image counted as 1,000 input tokens plus a 300-token question, and a 300-token answer. Providers count image tokens differently, so treat vision costs as a rough guide | $0.28standard price | $2.80at 10,000 a month | tied #1 of 28 |
| Translationa 1,000-token passage in and about 1,100 tokens out (translations run a little longer than the source) | $0.65standard price | $6.50at 10,000 a month | tied #1 of 29 |
| Batch extraction2,000 tokens per record in and 300 tokens of JSON out, through the batch API where there is one (results within 24 hours) | $0.17through the batch API | $17.50at 100,000 a month | tied #1 of 29 |
| Summarize long documentsa 20,000-token document in and an 800-token summary out | $2.40standard price | $2.40at 1,000 a month | tied #1 of 29 |
Cheaper and pricier alternatives
The current models just below and just above Claude Haiku 5.5 on the cost of 1,000 chatbot replies, with what differs. Price only, not quality.
Cheaper
- Nothing current is cheaper for a chatbot reply.
Pricier
- GPT-6 Luna $0.351.00x the cost of a chatbot reply, OpenAI, 1.05M context vs 1M.
- GPT-5.6 Luna $0.782.23x the cost of a chatbot reply, OpenAI, 1.05M context vs 1M.
- DeepSeek Flash $0.932.66x the cost of a chatbot reply, DeepSeek.
Every price tier
| Input | $0.1 per 1M tokens |
| Output | $0.5 per 1M tokens |
| Cache write | $0.125 (5m), $0.2 (1h) |
| Cache read (hit) | $0.01 (10% of the input price) |
| Batch API | $0.05 input / $0.25 output |
| Long prompts | over 100,000 input tokens: $0.5 input / $2.5 output |
| API model id | claude-haiku-5-5 |
| Status on the pricing page | listed |
Provider notes: US-only inference (inference_geo "us") is 1.1x on Claude 4.6 and later
Model facts from Anthropic
| Context window | 1,000,000 tokens |
| Max output | 128,000 tokens |
| Input types | text, image |
| Tool calling | yes |
| Lifecycle | current |
| Provider note | Current model. Page lists 1M tokens context, 128K tokens max output |
Source: https://platform.claude.com/docs/en/about-claude/models/overview, checked Oct 24, 2026.
The 6 classic workloads
Per 1,000 requests at the standard price. "With caching" bills the repeated part of the prompt at the cache-read price (cache writes not counted); "via batch" uses the batch API price. Run your own token counts in the LLM API cost calculator.
| Workload | Claude Haiku 5.5per 1,000 requests |
|---|---|
| Chatbot replya 1,500-token prompt (1,000 of it a fixed system prompt) and a 400-token answer | $0.35$0.26 with caching |
| Answer from your docs (RAG)6,000 tokens of retrieved context plus the question, a 500-token answer | $0.85$0.76 with caching |
| Summarize a long documenta 20,000-token document in, an 800-token summary out | $2.40$2.31 with caching |
| Coding agent step40,000 tokens of repo context and history (30,000 of it repeated from the last step), 2,000 out | $5.00$2.30 with caching |
| Batch extraction2,000 tokens per record in, 300 tokens of JSON out, sent through the batch API where there is one | $0.35$0.17 via batch |
| Long-document Q&Aa 150,000-token contract or codebase in one prompt, a 1,000-token answer | $77.50long-prompt price |
What the numbers say
- Output costs 5x input on Claude Haiku 5.5, so for answer-heavy jobs the output price drives the bill; for document-heavy jobs (RAG, summaries, agents) input does.
- Caching matters: a coding-agent step that rereads 30,000 cached tokens costs 54% less than the same step uncached ($2.30 vs $5.00 per 1,000 steps, cache writes not counted). How to stop paying twice for repeated prompts: LLM semantic cache.
- Prompts over 100,000 input tokens switch to $0.5 / $2.5, which is why the long-document row costs more per token than the rest.
- Among 14 listed Anthropic models it is the cheapest for a chat reply.
- Same standard input/output price as GPT-6 Luna; the differences are in caching, batch and long-prompt tiers.
Every listed Anthropic model, cheapest first
Same chatbot workload, 1,000 replies.
| Model | Input / 1M | Output / 1M | 1,000 chat replies |
|---|---|---|---|
| Claude Haiku 5.5 | $0.1 | $0.5 | $0.35 |
| Claude Haiku 4.5legacy | $1 | $5 | $3.50 |
| Claude Sonnet 5.5 | $2 | $10 | $7.00 |
| Claude Sonnet 5legacy | $2 | $10 | $7.00 |
| Claude Sonnet 4.6legacy | $3 | $15 | $10.50 |
| Claude Sonnet 4.5deprecated | $3 | $15 | $10.50 |
| Claude Opus 5.5 | $4 | $20 | $14.00 |
| Claude Opus 5legacy | $5 | $25 | $17.50 |
| Claude Opus 4.8legacy | $5 | $25 | $17.50 |
| Claude Opus 4.7legacy | $5 | $25 | $17.50 |
| Claude Opus 4.6legacy | $5 | $25 | $17.50 |
| Claude Opus 4.5legacy | $5 | $25 | $17.50 |
| Claude Fable 5.1 | $10 | $50 | $35.00 |
| Claude Fable 5legacy | $10 | $50 | $35.00 |
Closest price from other providers
The current model from each other provider whose chatbot-reply cost is nearest. Price only: we do not rank quality here.
| Model | Input / 1M | Output / 1M | 1,000 chat replies | vs Claude Haiku 5.5 |
|---|---|---|---|---|
| GPT-6 LunaOpenAI | $0.1 | $0.5 | $0.35 | 1.00x |
| Gemini 3.1 Flash-LiteGoogle | $0.25 | $1.5 | $0.97 | 2.79x |
| DeepSeek FlashDeepSeek | $0.3 | $1.2 | $0.93 | 2.66x |
Head-to-head
Price history
- Oct 17, 2026: Claude Haiku 5.5 first recorded: $0.1 input / $0.5 output per 1M tokens.
- Checked against the provider page on 2 dates: Oct 17, 2026, Oct 23, 2026.
Every change we record is on the LLM price changelog.
Sources
- Anthropic API pricing: https://platform.claude.com/docs/en/about-claude/pricing, checked Oct 23, 2026.
- Context, inputs and lifecycle: https://platform.claude.com/docs/en/about-claude/models/overview, checked Oct 24, 2026.
- Dataset: llm-prices (every row names its page and check date) and /llm/prices.csv.
Prices change often. If one is out of date, email matt@tensorust.com and we will fix it.