Claude Opus 4.8 Think
claude-opus-4-8-thinkPricing
List prices at AIHubMix, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $5.00 | $25.00 | |
| Cached input 90% off input | $0.50 | 90% off input | |
| Cache write, 5 minutes | $6.25 |
What it costs a month
At AIHubMix list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$2,970
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$2,220
- Coding agent1,000 requests a day, 40K in / 2K out, cached$3,720
- Overnight batch20,000 requests a day, 4K in / 0.4K out$18,000
Where to run it
1 host serve Claude Opus 4.8 Think. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
AIHubMixGateway claude-opus-4-8-think | $5.00 / $25.00 | claude-opus-4-8-think |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- TextImages
- Produces
- Text
- Features
- Adaptive thinkingPrompt caching
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than AIHubMix.
Smaller Anthropic models
- 20% less
- 60% less
- 98% less
Other frontier labs
- 52% less
- 60% less
- 70% less
- 60% less
Open-weight picks
- 60% less
- 79% less
- 83% less
- 95% less
Call it
Using AIHubMix's API.
from litellm import completion
response = completion(
model="aihubmix/claude-opus-4-8-think",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Claude Opus 4.8 Think cost?
On AIHubMix, Claude Opus 4.8 Think costs $5.00 per million input tokens and $25.00 per million output tokens. Cached input costs $0.50 per million tokens.
Which APIs offer Claude Opus 4.8 Think?
Claude Opus 4.8 Think runs on 1 API: AIHubMix.
What is Claude Opus 4.8 Think's context window?
1M tokens, with up to 128K tokens in one reply.
Is Claude Opus 4.8 Think being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Claude Opus 4.8 Think?
Models that cost less and keep most of what it can do: Claude Opus 5.5 on Anthropic (20% less), GPT-5.3 Codex on OpenAI (52% less), Gemini 4 Carbon on Google AI Studio (60% less) and Kimi K3.1 Pro on Databricks (60% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Claude Opus 4.8 Think's API model id?
Use claude-opus-4-8-think with AIHubMix.
Sources
Raw catalog entry for claude-opus-4-8-think on AIHubMix
{
"cache_read_input_token_cost": 5e-7,
"cache_creation_input_token_cost": 0.00000625,
"input_cost_per_token": 0.000005,
"litellm_provider": "aihubmix",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 0.000025,
"source": "https://aihubmix.com/api/v1/models",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_vision": true,
"prompt_cache_min_tokens": 1024,
"supports_adaptive_thinking": true,
"supports_sampling_params": false
}