Neither wins outright: Anthropic: Claude Haiku 4.5 (batch) is the pick when cost matters at scale, Mistral: Mistral Medium 3.5 (batch) when you need seed (reproducible sampling).
| Spec | Anthropic: Claude Haiku 4.5 (batch) | Mistral: Mistral Medium 3.5 (batch) |
|---|---|---|
| Provider | Anthropic | Mistral AI |
| Input price (per 1M tokens) | $0.50 | $0.75 |
| Output price (per 1M tokens) | $2.50 | $3.75 |
| Blended price (3:1 input/output) | $1.00 | $1.50 |
| Cheaper than … of all models we track | 38% | 31% |
| Context window | 200K tokens (~300 pages) | 262K tokens (~393 pages) |
| Larger context than … of all models | 38% | 48% |
| Max output per response | 64K tokens (~48,000 words) | 210K tokens (~157,300 words) |
| Input types | text, image, file | text, image, file |
| Output types | text | text |
| Free variant | No | No |
| Listed since | 2025-10-15 | 2026-04-30 |
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 (batch) | Mistral: Mistral Medium 3.5 (batch) | Difference |
|---|---|---|---|
| Customer-support chatbot 50,000 conversations — each a 6-turn conversation (1,500 in / 400 out tokens) | $87.50 | $131 | Anthropic: Claude Haiku 4.5 (batch) saves $43.75 |
| RAG search over documents 20,000 questions — each a question answered from ~8 retrieved passages (6,000 in / 500 out tokens) | $85.00 | $127 | Anthropic: Claude Haiku 4.5 (batch) saves $42.50 |
| 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) | $90.00 | $135 | Anthropic: Claude Haiku 4.5 (batch) saves $45.00 |
| Batch summarisation 10,000 documents — each a 6,000-word report summarised to a page (8,000 in / 600 out tokens) | $55.00 | $82.50 | Anthropic: Claude Haiku 4.5 (batch) saves $27.50 |
| Long-document analysis 500 documents — each a 150-page contract or codebase read in one pass (100,000 in / 2,000 out tokens) | $27.50 | $41.25 | Anthropic: Claude Haiku 4.5 (batch) saves $13.75 |
| Capability | Anthropic: Claude Haiku 4.5 (batch) | Mistral: Mistral Medium 3.5 (batch) | 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 | ✓ 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) | — | ✓ Yes | repeat a generation for tests and evals |
| Log-probabilities | — | — | 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 (batch) is the pick when cost matters at scale, Mistral: Mistral Medium 3.5 (batch) when you need seed (reproducible sampling). In short: Anthropic: Claude Haiku 4.5 (batch) when cost matters at scale, you need built-in web search; Mistral: Mistral Medium 3.5 (batch) when you need seed (reproducible sampling), you generate long outputs in one go, you want the newer model.
Anthropic: Claude Haiku 4.5 (batch) is cheaper: $1.00 vs $1.50 per 1M tokens at a typical 3:1 input/output mix, 33% less. For 50,000 support conversations a month that is $87.50 against $131.
Anthropic: Claude Haiku 4.5 (batch) costs $0.50 per 1M input tokens and $2.50 per 1M output tokens; Mistral: Mistral Medium 3.5 (batch) costs $0.75 input and $3.75 output. Output tokens are billed separately, so long answers shift the gap.
Mistral: Mistral Medium 3.5 (batch): 262K tokens, about 393 pages, against 200K (about 300 pages) for Anthropic: Claude Haiku 4.5 (batch).
Tool calling — Anthropic: Claude Haiku 4.5 (batch): yes, Mistral: Mistral Medium 3.5 (batch): yes. JSON-schema structured output — Anthropic: Claude Haiku 4.5 (batch): yes, Mistral: Mistral Medium 3.5 (batch): yes.
Yes, both accept image input.
No free variant is listed for either; both are pay-per-token.
Anthropic: Claude Haiku 4.5 (batch) can write up to 64K tokens (about 48,000 words) per response; Mistral: Mistral Medium 3.5 (batch) up to 210K (about 157,300 words).
Anthropic: Claude Haiku 4.5 (batch) was listed on 2025-10-15; Mistral: Mistral Medium 3.5 (batch) on 2026-04-30.
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 (batch) specs →Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...
Full Mistral: Mistral Medium 3.5 (batch) specs →