Cookie Preferences
We use cookies to personalize content and analyze traffic. See our Cookie Policy.
Claude Opus 4.8
Send a message to test this OpenAI-compatible chat completions model.
Explore different use cases and parameter configurations
Transparent pricing with no hidden fees. Pay as you go.
| Rule & Modality | Channel | Credits | Price (USD) | Official / Reference Price | Daily Savings |
|---|---|---|---|---|---|
Claude Code PAYG Claude Opus 4.8 textAnthropicToken | Regular | Input550.06 Output2,750.28 Cache read55.01 Cache write 5m687.57 Cache write 1h1,100.11 credits / 1M tokens | Input: $2.500 Output: $12.501 Cache read: $0.250 Cache write 5m: $3.125 Cache write 1h: $5.0005 per 1M tokens | - | - |
Complete guide to using claude-opus-4-8
Build coding assistants, research workflows, and multi-step agents with Claude Opus 4.8 on ApiPass. Send OpenAI-compatible chat completion requests, work with substantial text context, and choose between a standard response and real-time streaming.
Claude Opus 4.8 is presented as a model for complex reasoning, agentic coding, and professional knowledge work. The source page highlights long-horizon task execution and a 1-million-token context window on supported platforms. On ApiPass, use the public model ID claude-opus-4-8 with text-based chat messages. Context capacity and other upstream capabilities may depend on the selected provider.
Use chat messages to request implementation plans, debugging help, multi-file change reviews, and targeted test suggestions. Provide the relevant code or change details as text in messages.
Ask for summaries, comparisons, and evidence-based analysis of supplied text. The source describes long-context work, but available context limits should be confirmed for your configured provider.
Build multi-step conversations with developer, system, user, and assistant messages. The chat route also accepts OpenAI-compatible tool definitions; actual tool support depends on the upstream model.
The source page emphasizes software engineering, terminal coding, and multi-file code review. Use the API to examine changes, explain suspected defects, and propose verification steps.
The source describes a context window of up to 1 million tokens on supported platforms, suited to lengthy documents and codebases. Confirm your provider's effective limit before relying on a particular request size.
The ApiPass chat route accepts reasoning_effort values low and high. It also accepts optional max_tokens and sampling parameters, allowing you to configure requests without making those values mandatory.
The source highlights planning, tool use, and self-correction in longer workflows. ApiPass accepts tool definitions through the chat endpoint, subject to upstream support.
Create assistants that explain code, investigate bugs, review changes, and suggest tests from the context you provide.
Summarize supplied documents, compare arguments, and extract findings while asking the model to distinguish evidence from inference.
Build conversational workflows that plan actions, use supported tools, and check intermediate results.
The source page emphasizes coding, long-context analysis, and agentic work. Choose request settings and evaluate results against your own workload; benchmark figures on the source page are not a guarantee of performance through every provider.
For software tasks, provide the relevant code and desired review criteria in messages. Assess bug detection and test quality against examples from your repository.
For lengthy material, check the selected provider's effective context limit and evaluate whether answers cite the supplied text accurately.
For multi-step work, test tool availability, error recovery, and response quality. Tool definitions are accepted by the ApiPass route, while execution support depends on the upstream model.
Non-streaming responses include usage.prompt_tokens, usage.completion_tokens, and usage.total_tokens. Use these fields to monitor consumption.
Supply a positive max_tokens value when you need to limit completion length. If omitted, the upstream provider decides the response length.
The supplied page lists token-based credit pricing for its own service, not verified ApiPass rates. Check current ApiPass pricing and your selected channel before estimating production costs.
Create an API key and use it as a Bearer token when calling ApiPass.
POST JSON to https://api.apipass.dev/v1/chat/completions with model set to claude-opus-4-8 and a non-empty messages array. Each message needs a role and content. This is a chat endpoint, not an asynchronous task-creation endpoint.
For a standard request, read choices[0].message.content and the usage fields. For incremental output, set stream to true and consume OpenAI-compatible chat.completion.chunk events until data: [DONE].
All APIs require authentication via Bearer Token.
Authorization: Bearer
Generate text with claude-opus-4-8 through the ApiPass OpenAI-compatible chat completions endpoint.
Send an OpenAI-compatible JSON request body. ApiPass routes claude-opus-4-8 to the APIPASS adapter, which forwards the chat payload to APIPASS's LLM endpoint.
1{
2 "model": "claude-opus-4-8",
3 "messages": [
4 {
5 "role": "user",
6 "content": "Hello!"
7 }
8 ],
9 "stream": false,
10 "temperature": 0.7,
11 "max_tokens": 512,
12 "channel": "auto"
13}modelRequiredstringThe public ApiPass model name. The APIPASS adapter also accepts the gpt-5.5 alias and maps it upstream to claude-opus-4-8.
"claude-opus-4-8"
messagesRequiredarray<object>OpenAI-style chat messages array. The adapter requires a non-empty list, and each message object must include role and content.
[{"role":"user","content":"Write a short product announcement for APIPASS GPT-5.5 support in ApiPass."}]streamOptionalbooleanSet to true to receive Server-Sent Events. When false or omitted, ApiPass returns a single OpenAI-compatible chat.completion response.
false
temperatureOptionalnumberOptional sampling temperature from 0 to 2. If omitted, the adapter does not include temperature in the upstream request.
Allowed range: 0 to 2
0.7
max_tokensOptionalintegerOptional maximum number of completion tokens. If omitted, the upstream provider decides the response length.
Must be greater than 0 when provided
512
top_pOptionalnumberOptional nucleus sampling value accepted by the ApiPass chat endpoint and forwarded to APIPASS when supplied.
Allowed range: 0 to 1
0.9
frequency_penaltyOptionalnumberOptional OpenAI-compatible frequency penalty accepted by ApiPass and forwarded when supplied.
Allowed range: -2 to 2
0
presence_penaltyOptionalnumberOptional OpenAI-compatible presence penalty accepted by ApiPass and forwarded when supplied.
Allowed range: -2 to 2
0
response_formatOptionalobjectOptional response format object accepted by the ApiPass chat endpoint and forwarded to the provider if present.
{"type":"json_object"}toolsOptionalarray<object>Optional OpenAI-compatible tools array. ApiPass accepts tool definitions and forwards them to APIPASS when supplied; support depends on the upstream model.
[{"type":"function","function":{"name":"lookup_order","description":"Look up an order by ID","parameters":{"type":"object","properties":{"order_id":{"type":"string"}},"required":["order_id"]}}}]include_thoughtsOptionalbooleanOptional provider-specific flag accepted by ApiPass and forwarded when true.
false
reasoning_effortOptionalstringOptional reasoning effort value accepted by the ApiPass chat endpoint and forwarded to the provider when supplied.
Available options:
"low"
_provider_config_idOptionalstringOptional ApiPass routing override. Supply a provider_model_configs.id to force this request to a specific configured APIPASS provider.
"provider-config-id"
channelOptionalstringYou may specify the corresponding provider within APIPASS via the channel parameter; these providers handle the actual image and video generation tasks. APIPASS currently offers three provider options:
The default value for the channel parameter is auto. When enabled, APIPASS automatically allocates tasks across available providers based on real-time pricing and stability metrics to balance minimal cost and reliable performance. Retain the default auto value unless you have custom routing requirements.
Available options:
auto
Each item in the messages array follows the OpenAI chat message shape validated by ApiPass before the APIPASS adapter is called.
messages[].roleRequiredstringMessage role. ApiPass accepts developer, system, user, and assistant roles in the chat request model.
Available options:
"user"
messages[].contentRequiredstringMessage content. For GPT-5.5 text generation, use plain text content for the most predictable provider behavior.
"Summarize the following text in three concise bullets."
1curl -X POST "https://api.apipass.dev/v1/chat/completions" \
2 -H "Content-Type: application/json" \
3 -H "Authorization: Bearer YOUR_API_KEY" \
4 -d '{
5 "model": "claude-opus-4-8",
6 "messages": [
7 {
8 "role": "system",
9 "content": "You are a precise and concise assistant."
10 },
11 {
12 "role": "user",
13 "content": "Write a short product announcement for APIPASS grok-4.5 support in ApiPass."
14 }
15 ],
16 "temperature": 0.7,
17 "max_tokens": 512,
18 "stream": false
19 }'1{
2 "id": "chatcmpl_gpt_5_5_demo",
3 "object": "chat.completion",
4 "created": 1765968190,
5 "model": "claude-opus-4-8",
6 "choices": [
7 {
8 "index": 0,
9 "message": {
10 "role": "assistant",
11 "content": "ApiPass now supports APIPASS GPT-5.5 through the standard OpenAI-compatible chat completions endpoint."
12 },
13 "finish_reason": "stop"
14 }
15 ],
16 "usage": {
17 "prompt_tokens": 35,
18 "completion_tokens": 19,
19 "total_tokens": 54
20 }
21}idApiPass chat completion response ID.
objectResponse object type. Non-streaming calls return chat.completion.
modelThe public model name used for the request.
choices[0].message.contentAssistant reply text extracted from the APIPASS OpenAI-compatible response.
choices[0].finish_reasonCompletion finish reason. ApiPass returns stop for successful non-streaming GPT-5.5 completions.
usage.prompt_tokensPrompt token count reported by the upstream provider.
usage.completion_tokensCompletion token count reported by the upstream provider.
usage.total_tokensTotal token count used for ApiPass usage accounting.
xAI
xAI
Starting from
0 credits
OpenAI
OpenAI
GPT-5.6 models shared by Codex-compatible clients and direct API callers.
Starting from
0 credits
Anthropic
Anthropic
Upgrade to Fable 5.1 for sharper, more natural responses with improved context awareness and refined writing quality.
Starting from
0 credits
OpenAI
OpenAI
GPT‑6 Astra brings together years of research and big bets across pre-training, reinforcement learning, and alignment
Starting from
0 credits
Anthropic
Anthropic
Harness Fable 5 to turn raw ideas into vivid, natural-sounding text across any creative or conversational task.
Starting from
0 credits
Anthropic
Anthropic
Trust Opus 5 for deep, nuanced reasoning on your hardest analytical, coding, and research problems.
Starting from
0 credits
Anthropic
Anthropic
Choose Sonnet 5 for stronger reasoning, nuanced conversation, and reliable, safety-optimized performance across everyday tasks.
Starting from
0 credits
Anthropic
Anthropic
Starting from
0 credits
OpenAI
OpenAI
Starting from
0 credits
Gemini 3 Flash Preview - Fast Response Preview
Starting from
0 credits
OpenAI
OpenAI
Orchestrate autonomous AI agents with GPT-5.5 API.
Starting from
0 credits
Gemini 3 Pro Preview - Try out the latest features
Starting from
0 credits
Anthropic
Anthropic
Choose Haiku 5.5 for fast, cost-efficient responses and everyday tasks, with Claude Messages API support.
Starting from
0 credits