Neither wins outright: Anthropic: Claude Haiku 4.5 is the pick when you need file / PDF input, Elorian: Glimpse when cost matters at scale.
| Spec | Anthropic: Claude Haiku 4.5 | Elorian: Glimpse |
|---|---|---|
| Provider | Anthropic | Elorian |
| Input price (per 1M tokens) | $1.00 | $0.60 |
| Output price (per 1M tokens) | $5.00 | $3.00 |
| Blended price (3:1 input/output) | $2.00 | $1.20 |
| Cheaper than … of all models we track | 25% | 36% |
| Context window | 200K tokens (~300 pages) | 262K tokens (~393 pages) |
| Larger context than … of all models | 38% | 47% |
| Max output per response | 64K tokens (~48,000 words) | 256K tokens (~192,000 words) |
| Input types | text, image, file | text, image, video |
| Output types | text | text |
| Free variant | No | No |
| Listed since | 2025-10-15 | 2026-10-17 |
Monthly cost at list price for five common workloads. Token counts per unit are stated so you can scale them to your own traffic. A workload that does not fit a model's context window is marked rather than priced.
| Workload (per month) | Anthropic: Claude Haiku 4.5 | Elorian: Glimpse | Difference |
|---|---|---|---|
| Customer-support chatbot 50,000 conversations — each a 6-turn conversation (1,500 in / 400 out tokens) | $175 | $105 | Elorian: Glimpse saves $70.00 |
| RAG search over documents 20,000 questions — each a question answered from ~8 retrieved passages (6,000 in / 500 out tokens) | $170 | $102 | Elorian: Glimpse saves $68.00 |
| Coding / tool-using agent 2,000 tasks — each a multi-step task with tool calls and file context (60,000 in / 6,000 out tokens) | $180 | $108 | Elorian: Glimpse saves $72.00 |
| Batch summarisation 10,000 documents — each a 6,000-word report summarised to a page (8,000 in / 600 out tokens) | $110 | $66.00 | Elorian: Glimpse saves $44.00 |
| Long-document analysis 500 documents — each a 150-page contract or codebase read in one pass (100,000 in / 2,000 out tokens) | $55.00 | $33.00 | Elorian: Glimpse saves $22.00 |
| Capability | Anthropic: Claude Haiku 4.5 | Elorian: Glimpse | What it lets you do |
|---|---|---|---|
| Tool / function calling | ✓ Yes | ✓ Yes | call your APIs and run agent loops |
| Structured output (JSON schema) | ✓ Yes | ✓ Yes | return JSON that validates against your schema |
| Reasoning / thinking mode | ✓ Yes | ✓ Yes | spend extra tokens thinking before answering hard problems |
| Image input | ✓ Yes | ✓ Yes | read screenshots, charts and scanned pages |
| Audio input | — | — | take speech or audio directly |
| File / PDF input | ✓ Yes | — | accept documents without your own parsing step |
| Image output | — | — | generate images, not just text |
| Built-in web search | ✓ Yes | — | answer from live web results |
| Seed (reproducible sampling) | — | — | repeat a generation for tests and evals |
| Log-probabilities | — | ✓ Yes | read token confidence for classification and scoring |
From each model's published parameters and input/output types. “—” means not advertised, not proven absent.
Neither wins outright: Anthropic: Claude Haiku 4.5 is the pick when you need file / PDF input, Elorian: Glimpse when cost matters at scale. In short: Anthropic: Claude Haiku 4.5 when you need file / PDF input, you need built-in web search; Elorian: Glimpse when cost matters at scale, you need log-probabilities, you generate long outputs in one go, you want the newer model.
Elorian: Glimpse is cheaper: $1.20 vs $2.00 per 1M tokens at a typical 3:1 input/output mix, 40% less. For 50,000 support conversations a month that is $105 against $175.
Anthropic: Claude Haiku 4.5 costs $1.00 per 1M input tokens and $5.00 per 1M output tokens; Elorian: Glimpse costs $0.60 input and $3.00 output. Output tokens are billed separately, so long answers shift the gap.
Elorian: Glimpse: 262K tokens, about 393 pages, against 200K (about 300 pages) for Anthropic: Claude Haiku 4.5.
Tool calling — Anthropic: Claude Haiku 4.5: yes, Elorian: Glimpse: yes. JSON-schema structured output — Anthropic: Claude Haiku 4.5: yes, Elorian: Glimpse: yes.
Yes, both accept image input.
No free variant is listed for either; both are pay-per-token.
Anthropic: Claude Haiku 4.5 can write up to 64K tokens (about 48,000 words) per response; Elorian: Glimpse up to 256K (about 192,000 words).
Anthropic: Claude Haiku 4.5 was listed on 2025-10-15; Elorian: Glimpse on 2026-10-17.
Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...
Full Anthropic: Claude Haiku 4.5 specs →Glimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical world. It reasons directly over images and video rather than...
Full Elorian: Glimpse specs →