Claude Opus 5

LiveAnthropic
Model IDclaude-opus-5

Claude Opus 5 by Anthropic: 1M context, 128K max output, with Vision, Function Calling, Reasoning, Prompt Caching, Response Schema, Streaming, Web Search. Via SoleAPI, Input (prompt) costs 2.5 Credits / M tokens, 92% below list price. 7-day uptime 98.9%. Compatible with Anthropic Messages / OpenAI Responses: swap the base URL and you are connected.

Context window
1Mtokens
1,000,000
Max output
128Ktokens
128,000
7-day uptime
98.9%
377 probes · 4 failed
Measured throughput
43.6tokens / s
Real traffic, last 7 days · output side

Capabilities

Listed exactly as the catalog flags them, including what this model does not support.

7 of 15 supported

Vision

Natively multimodal: captioning, classification, visual Q&A, chart and screenshot understanding. Images are converted to tokens at the input rate.

Function Calling

Connect the model to external tools and APIs: it decides when to call which function and with what arguments, your code runs it. Force or forbid calls with tool_choice.

Reasoning

The model thinks before answering, which markedly improves multi-step planning and reasoning for coding, math and data analysis. Thinking tokens bill at the output rate.

Prompt Caching

Repeated prefixes (system prompts, long documents) hit the cache: reads cost far less than input, writes are priced by retention time.

Response Schema

Constrain output to a JSON Schema you provide for predictable, type-safe results without parsing free text.

Streaming

Tokens arrive over SSE as they are generated; the first frame is forwarded immediately with no buffering. Claude Code, Codex and similar tools depend on this.

Web Search

Vendor-hosted live web retrieval; the model decides when to search and cites sources.

AudioNot supported

Audio input or speech output.

VideoNot supported

Video input understanding or video generation.

File InputNot supported

Upload PDFs and other documents directly; the model reads the whole document with native vision.

RealtimeNot supported

Bidirectional low-latency voice / text sessions over WebSocket.

SessionNot supported

Server-side multi-turn context (e.g. previous_response_id in Responses) so you need not resend history.

MediaNot supported

Image / video / music generation endpoints.

Multipart FormNot supported

multipart/form-data file-upload requests.

Binary ResponseNot supported

Endpoints that return raw audio / image bytes.

Reliability & performance

SoleAPI probes this model through the real supply chain on a schedule — measured, not self-reported.

Last probe: 9/9/2026, 6:19:41 AM
98.9%377 probes in 7 days, 4 failed · automatic failover to backup channels
1.49 s3.67 s2.29 s6.30 s4.53 s3.45 s4.73 s3.97 s1.39 s10.16 s2.88 s6.86 s12.54 s5.00 s25.64 s5.59 s1.52 s30.08 s1.64 s1.91 s✕ 9/8/2026, 10:30:30 AM2.71 s1.76 s2.21 s4.58 s4.90 s1.46 s1.47 s1.58 s1.61 s1.48 s1.52 s1.75 s1.82 s1.83 s1.56 s1.70 s1.70 s1.79 s1.68 s1.68 s2.13 s1.71 s1.77 s1.71 s1.70 s1.72 s1.82 s1.53 s2.61 s1.70 s5.41 s19.06 s17.15 s26.95 s1.91 s5.32 s2.37 s4.82 s35.61 s
9/8/2026, 12:12:53 AMnow
successful probe, bar height = end-to-end latency (0–4 s)failed probegrid 1 s

Latency & throughput

Latest latency35.61s
Avg. of last 605.31s
P95 of last 6026.95s
Output throughput43.6t/s
ProtocolsAnthropic Messages / OpenAI Responses

Protocols & code samples

Change the base URL to SoleAPI, keep everything else. Native protocols pass straight through; “adapted” ones are translated by the gateway.

Claude Code setup guide

Anthropic SDK or any Messages-protocol client: point base_url at https://api.soleapi.com and use a SoleAPI key.

curl https://api.soleapi.com/v1/messages \
  -H "x-api-key: $SOLEAPI_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "content-type: application/json" \
  -d '{
    "model": "claude-opus-5",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "Explain prompt caching in one sentence"}]
  }'
EndpointPathMode
Token countPOST /v1/messages/count_tokensnative

Full price list

List price → SoleAPI price per channel, every pricing dimension, nothing hidden.

1 Credit ≈ $0.151 · rate updated daily
ItemUnitAnthropic list priceKiro-Claude Group ×0.592% offOfficial Claude ×1.380% off
Input (prompt)per 1M tokens$5.002.5 Credits6.5 Credits
Output (completion)per 1M tokens$25.0012.5 Credits32.5 Credits
Cache readper 1M tokens$0.50.25 Credits0.65 Credits
Cache write · 5 minper 1M tokens$6.253.13 Credits8.13 Credits
Cache write · 1 hourper 1M tokens$10.005 Credits13 Credits
Web search (general)per 1K calls$10.005 Credits13 Credits

“Off” is computed at 1 Credit = ¥1 and today’s rate: 1 − channel multiplier × (1 Credit in the list currency). Fast tier ×2: every pricing dimension is multiplied by this factor when request body field speed matches ^fast$; stacks with any channel.

FAQ

How much does the Claude Opus 5 API cost?

Via SoleAPI, Input (prompt) costs 2.5 Credits / M tokens, with 1 Credit = ¥1. That is 92% below the Anthropic list price.

What are the context window and output limit of Claude Opus 5?

Context window 1M tokens, up to 128K tokens per response.

Does Claude Opus 5 support function calling and structured outputs?

Function calling with tool_choice control is supported; structured outputs (JSON Schema) are supported.

How do I use Claude Opus 5 in Claude Code?

Set ANTHROPIC_BASE_URL=https://api.soleapi.com, ANTHROPIC_API_KEY to your SoleAPI key and ANTHROPIC_MODEL=claude-opus-5, then run claude. No config files to edit.

How is the 98.9% uptime measured?

SoleAPI sends probe requests to this model through the real supply chain on a schedule and divides successful probes by total probes over the last 7 days. When one channel fails the gateway fails over to a backup, so the figure reflects what end users actually see.

One API key for Claude Opus 5 and 30+ models

Free credits on sign-up, pay as you go, no monthly fee.

Get an API Key