Anthropic: Claude Opus 4.8 Thinking
Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents
Cheapest input
$0.425
$/MTok · models.dev
Cheapest output
$2.13
$/MTok
Context
1.0M
tokens
Sources
4
71 listings
Sources
Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number. Free/$0 listings are hidden by default (1 omitted). Show free/$0 listings.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| tokenstatanthropic/claude-opus-4.8 | Anthropic | $5 | $25 | $0.5 | 1.0M |
| models.devcheapestclaude-opus-4-8 | UnoRouter | $0.425 | $2.13 | $0 | 1M |
| models.devclaude-opus-4-8 | Xpersona | $1.50 | $9.25 | $0.15 | 200K |
| OpenRouteranthropic/claude-opus-4.8:batch | OpenRouter | $2.50 | $12.50 | $0.25 | 1M |
| LiteLLManthropic/claude-opus-4.8:batch | N/A | $2.50 | $12.50 | $0.25 | N/A |
| models.devstealth/claude-opus-4.8 | Kilo Gateway | $4 | $20 | $0.4 | 1M |
| models.devanthropic/claude-opus-4.8 | Poe | $4.29 | $21.46 | $0 | 1.0M |
| models.devanthropic/claude-opus-4.8:thinking | NanoGPT | $5 | $25 | $0.5 | 1M |
| models.devclaude-opus-4-8 | 302.AI | $5 | $25 | $0 | 1M |
| models.devclaude-opus-4-8 | Abacus | $5 | $25 | $0 | 1M |
| models.devclaude-opus-4-8 | AIHubMix | $5 | $25 | $0.5 | 200K |
| models.devclaude-opus-4-8 | Anthropic | $5 | $25 | $0.5 | 1M |
| models.devclaude-opus-4-8 | Azure | $5 | $25 | $0.5 | 1M |
| models.devclaude-opus-4-8 | Azure | $5 | $25 | $0.5 | 1M |
| models.devanthropic/claude-opus-4.8 | Cloudflare | $5 | $25 | $0.5 | 1M |
| models.devanthropic/claude-opus-4-8 | CrossModel | $5 | $25 | $0.5 | 1M |
| models.devclaude-opus-4-8 | DaoXE | $5 | $25 | $0.5 | 1M |
| models.devanthropic/claude-opus-4-8 | Eden AI | $5 | $25 | $0.5 | 1M |
| models.devanthropic/claude-opus-4.8 | FastRouter | $5 | $25 | $0 | 1M |
| models.devclaude-opus-4-8 | FreeModel | $5 | $25 | $0.5 | 1M |
| models.devclaude-opus-4.8 | GitHub Copilot | $5 | $25 | $0.5 | 200K |
| models.devanthropic/claude-opus-4.8 | GMI Cloud | $5 | $25 | $0.5 | 1M |
| models.devanthropic/claude-opus-4-8 | Impossibl | $5 | $25 | $0.5 | 1M |
| models.devanthropic/claude-opus-4.8 | Kilo Gateway | $5 | $25 | $0.5 | 1M |
| models.devazure-anthropic/claude-opus-4-8 | LLM Gateway | $5 | $25 | $0.5 | 1M |
| models.devclaude-opus-4-8 | DevPass (LLM Gateway) | $5 | $25 | $0.5 | 1M |
| models.devanthropic/claude-opus-4-8 | Merge Gateway | $5 | $25 | $0.5 | 1M |
| models.devclaude-opus-4-8 | Modelis | $5 | $25 | $0 | 1M |
| models.devanthropic/claude-opus-4.8 | NanoGPT | $5 | $25 | $0.5 | 1M |
| models.devclaude-opus-4-8 | Neon | $5 | $25 | $0.5 | 1M |
| models.devanthropic/claude-opus-4.8 | Ofox | $5 | $25 | $0.5 | 1M |
| models.devclaude-opus-4-8 | OpenCode Zen | $5 | $25 | $0.5 | 1M |
| OpenRouteranthropic/claude-opus-4.8 | OpenRouter | $5 | $25 | $0.5 | 1M |
| models.devanthropic/claude-opus-4-8 | Opper | $5 | $25 | $0.5 | 1M |
| models.devanthropic/claude-opus-4.8 | OrcaRouter | $5 | $25 | $0.5 | 1M |
| models.devclaude-opus-4-8 | Pioneer | $5 | $25 | $0.5 | 1M |
| models.devclaude-opus-4-8 | Requesty | $5 | $25 | $0.5 | 1M |
| models.devclaude-opus-4-8 | Routing.Run | $5 | $25 | $0 | 1M |
| models.devanthropic/claude-opus-4.8 | Vercel AI Gateway | $5 | $25 | $0.5 | 1M |
| models.devanthropic/claude-opus-4.8 | ZenMux | $5 | $25 | $0.5 | 1M |
| models.devclaude-opus-4-8-think | AIHubMix | $5 | $25 | $0.5 | 200K |
| models.devanthropic.claude-opus-4-8 | Amazon Bedrock | $5 | $25 | $0.5 | 1M |
| models.devanthropic-claude-opus-4.8 | DigitalOcean | $5 | $25 | $0.5 | 1M |
| models.devglobal.anthropic.claude-opus-4-8 | Amazon Bedrock | $5 | $25 | $0.5 | 1M |
| models.devclaude-opus-4-8@default | Vertex (Anthropic) | $5 | $25 | $0.5 | 1M |
| models.devclaude-opus-4-8@default | Google Vertex AI | $5 | $25 | $0.5 | 1M |
| models.devanthropic--claude-4.8-opus | SAP AI Core | $5 | $25 | $0.5 | 1M |
| LiteLLMclaude-opus-4-8 | N/A | $5 | $25 | $0.5 | N/A |
| LiteLLMclaude-opus-4-8-think | N/A | $5 | $25 | $0.5 | N/A |
| LiteLLManthropic.claude-opus-4-8 | N/A | $5 | $25 | $0.5 | N/A |
| LiteLLMglobal.anthropic.claude-opus-4-8 | N/A | $5 | $25 | $0.5 | N/A |
| LiteLLMclaude-opus-4-8@default | N/A | $5 | $25 | $0.5 | N/A |
| LiteLLMazure_ai/claude-opus-4-8 | N/A | $5 | $25 | $0.5 | N/A |
| LiteLLMdeepinfra/anthropic/claude-opus-4-8 | N/A | $5 | $25 | $0.5 | N/A |
| LiteLLMperplexity/anthropic/claude-opus-4-8 | N/A | $5 | $25 | $0.5 | N/A |
| LiteLLMvertex_ai/claude-opus-4-8 | N/A | $5 | $25 | $0.5 | N/A |
| LiteLLMvertex_ai/claude-opus-4-8@default | N/A | $5 | $25 | $0.5 | N/A |
| LiteLLMdatabricks-claude-opus-4-8 | N/A | $5 | $25 | $0.5 | N/A |
| LiteLLMdatabricks/databricks-claude-opus-4-8 | N/A | $5 | $25 | $0.5 | N/A |
| models.devau.anthropic.claude-opus-4-8 | Amazon Bedrock | $5.50 | $27.50 | $0.55 | 1M |
| models.deveu.anthropic.claude-opus-4-8 | Amazon Bedrock | $5.50 | $27.50 | $0.55 | 1M |
| models.devjp.anthropic.claude-opus-4-8 | Amazon Bedrock | $5.50 | $27.50 | $0.55 | 1M |
| models.devus.anthropic.claude-opus-4-8 | Amazon Bedrock | $5.50 | $27.50 | $0.55 | 1M |
| LiteLLMau.anthropic.claude-opus-4-8 | N/A | $5.50 | $27.50 | $0.55 | N/A |
| LiteLLMeu.anthropic.claude-opus-4-8 | N/A | $5.50 | $27.50 | $0.55 | N/A |
| LiteLLMjp.anthropic.claude-opus-4-8 | N/A | $5.50 | $27.50 | $0.55 | N/A |
| LiteLLMus.anthropic.claude-opus-4-8 | N/A | $5.50 | $27.50 | $0.55 | N/A |
| models.devclaude-opus-4-8 | Venice AI | $6 | $30 | $0.6 | 1M |
| LiteLLMbedrock/us-gov-east-1/anthropic.claude-opus-4-8 | N/A | $6 | $30 | $0.6 | N/A |
| LiteLLMus-gov-east-1/anthropic.claude-opus-4-8 | N/A | $6 | $30 | $0.6 | N/A |
| LiteLLMus-gov-west-1/anthropic.claude-opus-4-8 | N/A | $6 | $30 | $0.6 | N/A |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Attachments
- In: text
- In: image
- In: pdf
- In: file
- Out: text
Knowledge cutoff: 2026-01Released: 2026-05-28Family: claude-opus
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.
- Arena code Elo1559i
- Arena agent (net improvement)8.19i
- Arena agent net improvement8.19i
- Arena agent confirmed success6.28i
- Arena vision Elo1283i
Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.
Run this model in a real workspace
Launch agents from the project they work in, use remote management to reach another machine, and see this model's sessions and token usage in your own history. Free to use, runs on your device.
Data and list-price estimates may contain mistakes. Not investment advice.