# Anthropic: claude-opus-4-8

- Model ID: `claude-opus-4-8`
- Provider: Anthropic
- Web version: https://www.moleapi.com/en/models/anthropic/claude-opus-4-8
- Content status: verified

## Model introduction

Claude Opus 4.8 is Anthropic's model for complex agentic coding and enterprise work, with adaptive thinking enabled.

## Model capabilities

- OpenAI compatible
- Anthropic compatible
- Prompt cache
- Reasoning

### Verified specifications

- Official positioning: Complex agentic coding and enterprise work
- Context window: 1,000,000 tokens
- Maximum output: 128,000 tokens
- Verified capability: Adaptive thinking

### Independent capability evaluation

- Adaptive reasoning, max effort
- Intelligence: 56 (#6/186)
- Output speed: 58.8 tok/s (#95/186)
- Time to first token: 28.84s
- Source: https://artificialanalysis.ai/models/claude-opus-4-8

Frontier composite capability, with slower output and high token use and cost at maximum effort.

## Model pricing and access

Pricing is supplied dynamically by the MoleAPI console API.

### Standard (default, x1)

- Input: $5 / 1M tokens
- Output: $25 / 1M tokens
- Cache read: $0.5 / 1M tokens
- Cache write: $6.25 / 1M tokens

### Discount (discount, x0.8)

- Input: $4 / 1M tokens
- Output: $20 / 1M tokens
- Cache read: $0.4 / 1M tokens
- Cache write: $5 / 1M tokens

### Relay (relay, x0.3)

- Input: $1.5 / 1M tokens
- Output: $7.5 / 1M tokens
- Cache read: $0.15 / 1M tokens
- Cache write: $1.875 / 1M tokens

### Access protocols

| Protocol | Method | Endpoint |
| --- | --- | --- |
| anthropic | POST | /v1/messages |
| openai | POST | /v1/chat/completions |

- Live pricing source: https://home.moleapi.com/api/pricing

## About claude-opus-4-8

Claude Opus 4.8 is Anthropic's model for complex agentic coding and enterprise work, with adaptive thinking enabled.

### Best for

Complex agentic coding and enterprise workflows that benefit from a long context window and extended reasoning.

### Core strengths

- Designed for long-running agentic coding, large repositories, and difficult enterprise work.
- A 1M context window and 128K maximum output support unusually long tasks.
- Adaptive thinking adjusts reasoning effort to the task.

### Limitations

- High reasoning effort can add substantial first-answer latency and token use.
- Its price favors high-value work over simple, high-volume processing.

### Selection and production evaluation

Start a claude-opus-4-8 evaluation by mapping its official positioning to real work: Complex agentic coding and enterprise workflows that benefit from a long context window and extended reasoning. The first pass should exercise both its main strength, "Designed for long-running agentic coding, large repositories, and difficult enterprise work.", and its known limitation, "High reasoning effort can add substantial first-answer latency and token use.", instead of relying on a single subjective general-chat comparison.

For access, MoleAPI currently lists anthropic, openai protocols and the Standard, Discount, Relay billing groups for this Anthropic model; the default price summary is Input $5 / 1M tokens · Output $25 / 1M tokens. Pricing, protocols, and groups come from the live catalog, so production planning should still price representative requests using real context length, output size, and cache-hit assumptions.

The capability snapshot uses the exact model ID under the "Adaptive reasoning, max effort" public evaluation profile. A launch decision should add your own task accuracy, structured-output validity, tool-call success, and timeout rates while pinning the model ID, prompt, and sample set so version or effort changes do not hide regressions.

The model material on this page was last checked on 2026-07-23. When upstream model cards, context limits, or tool support change, update the cited bilingual facts before changing the recommendation; live MoleAPI price changes remain separate and update from the catalog automatically.

### Sources

- [Anthropic Claude Opus 4.8 update notes](https://platform.claude.com/docs/en/about-claude/models/whats-new-claude-4-8) — Anthropic
- Last verified: 2026-07-23

## Code examples

### cURL

```bash
curl https://api.moleapi.com/v1/chat/completions \
  -H "Authorization: Bearer $MOLEAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"claude-opus-4-8","messages":[{"role":"user","content":"Hello"}]}'
```

## More related models

- [claude-fable-5](https://www.moleapi.com/en/models/anthropic/claude-fable-5) — Anthropic
- [claude-opus-5](https://www.moleapi.com/en/models/anthropic/claude-opus-5) — Anthropic
- [claude-sonnet-5](https://www.moleapi.com/en/models/anthropic/claude-sonnet-5) — Anthropic
- [gpt-5.6-luna](https://www.moleapi.com/en/models/openai/gpt-5.6-luna) — OpenAI
- [gpt-5.6-sol](https://www.moleapi.com/en/models/openai/gpt-5.6-sol) — OpenAI
- [gpt-5.6-terra](https://www.moleapi.com/en/models/openai/gpt-5.6-terra) — OpenAI

## Frequently asked questions

### How is claude-opus-4-8 priced?

Prices are read from the MoleAPI console API and update with model prices, context tiers, and account groups.

### How can I access claude-opus-4-8?

The catalog currently lists anthropic, openai.

### How do I switch an existing project to claude-opus-4-8?

Keep the MoleAPI API address and key, replace the model parameter, and check protocol-specific parameters.

### Where do the claude-opus-4-8 details come from?

Capabilities and limitations are checked against Anthropic and the other cited pages; pricing and protocols come from the MoleAPI console.