Cookie Preferences
We use cookies to personalize content and analyze traffic. See our Cookie Policy.
Claude Fable 5
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 Fable 5 textAnthropicToken | Regular | Input1,100.11 Output5,500.55 Cache read110.01 Cache write 5m1,375.14 Cache write 1h2,200.22 credits / 1M tokens | Input: $5.0005 Output: $25.003 Cache read: $0.500 Cache write 5m: $6.251 Cache write 1h: $10.001 per 1M tokens | - | - |
Complete guide to using claude-fable-5
Build with Claude Fable 5 on ApiPass for multi-step reasoning, codebase planning, research synthesis, and document-heavy workflows. Send OpenAI-compatible messages to /v1/chat/completions and receive a chat completion or streamed response.
Claude Fable 5 is presented as an Anthropic Mythos-class model for advanced general use. The supplied product content highlights sustained reasoning, software engineering, technical research, knowledge work, and visual understanding. It distinguishes Fable 5, intended for general-use access with safeguards, from Claude Mythos 5 in restricted-access contexts. On ApiPass, the documented integration is an OpenAI-compatible chat completions route using the public model name claude-fable-5. For predictable behavior on this route, send plain-text message content; the current API reference does not document an image or file upload parameter.
Use chat messages to specify goals, constraints, intermediate findings, and verification criteria for complex tasks. Carry prior messages into later requests when your application needs conversational continuity.
Ask for migration plans, implementation reviews, debugging suggestions, refactoring guidance, and test strategies. Verify generated changes with your own tooling and review process.
Provide relevant text from reports, policies, technical material, or research notes to request summaries, comparisons, and evidence-aware drafts. The supplied product content also discusses vision and file-based analysis, but those input formats are not specified for this ApiPass endpoint.
The supplied product content emphasizes tracking goals, constraints, revisions, and verification steps across multi-stage work. Include the context needed for each request in your messages.
Use the model to reason about dependencies, propose implementation steps, and draft tests for demanding engineering work. Treat its output as a reviewable proposal, not a substitute for running tests.
The supplied product content notes that some sensitive requests may trigger safeguards or fallback behavior. Evaluate these cases with representative prompts rather than assuming identical behavior across topics.
Draft phased migration plans that account for existing interfaces, dependencies, test updates, compatibility, and rollback.
Summarize long-form business material, separate stated evidence from assumptions, and prepare follow-up questions for analysts.
Compare clauses and flag ambiguous obligations for qualified human review. Do not use model output as the final legal judgment.
Organize supplied research text, compare methods, and prepare structured technical report drafts with clear uncertainty.
The supplied product content discusses benchmark results and the model's relationship to Claude Mythos. Use those claims as evaluation context, not a guarantee for an individual API request.
The source describes Fable 5 as a Mythos-class model positioned for general use with safeguards, while Mythos 5 is discussed in restricted trusted-access contexts. Do not assume the two have identical access policies or behavior.
The source reports results across coding, knowledge work, vision, and reasoning benchmarks. Its comparison combines Mythos 5 and Fable 5 scores and notes that safeguards or fallback can affect some results. Test your own prompts for output quality, consistency, and cost.
The supplied product page lists 800 credits per 1 million input tokens and 4,000 credits per 1 million output tokens. Check your ApiPass dashboard for the rates that apply to your account before budgeting.
Non-streaming chat completions include usage.prompt_tokens, usage.completion_tokens, and usage.total_tokens. Use these fields to monitor consumption during testing and production.
The supplied product content describes credit-based testing rather than unlimited free access. Evaluate representative prompts and output lengths against your available credits.
Create an ApiPass API key and review the current chat completions reference. Use claude-fable-5 as the public model name.
POST a non-empty messages array to /v1/chat/completions. Start with real coding, research, or document-analysis text and inspect choices[0].message.content. Set stream to true if your application needs Server-Sent Events.
Add logging, token-usage monitoring, explicit task boundaries, and human review for consequential outputs. Test sensitive-topic behavior and production prompts. The supplied product page states that function calling/tool use and Claude Code are not currently supported for this model, even though the ApiPass route accepts a tools field.
All APIs require authentication via Bearer Token.
Authorization: Bearer
Generate text with claude-fable-5 through the ApiPass OpenAI-compatible chat completions endpoint.
Send an OpenAI-compatible JSON request body. ApiPass routes claude-fable-5 to the APIPASS adapter, which forwards the chat payload to APIPASS's LLM endpoint.
1{
2 "model": "claude-fable-5",
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-fable-5.
"claude-fable-5"
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 Claude Fable 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 Claude Fable 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-fable-5",
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 Claude Fable 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-fable-5",
6 "choices": [
7 {
8 "index": 0,
9 "message": {
10 "role": "assistant",
11 "content": "ApiPass now supports APIPASS Claude Fable 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 Claude Fable 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
Deploy Opus 4.8's advanced cognitive architecture to tackle your most complex reasoning and multi-step problem-solving challenges.
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