Access to Claude Fable 5 may be interrupted. Anthropic is restricting access to Fable 5 in response to a US government export-control directive. Requests may fail or become unavailable without notice. Learn more: https://www.anthropic.com/news/fable-mythos-access(opens in new tab)
By using Claude Fable 5, you consent to data retention for purposes of monitoring safe and compliant use of AI. Anthropic's data retention policy does not allow zero data retention. Learn more(opens in new tab)
Azure, Google Vertex, and Amazon Bedrock endpoints are BYOK-only while we work on enabling public access.
Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for long-running, complex, and asynchronous tasks that previously required frequent human check-ins.
It is particularly strong at end-to-end work that would otherwise take a person hours, days, or weeks - taking on problems that are long-running, ambiguous, or highly multi-step. It executes well-scoped tasks with few mistakes, automatically self-correcting through verification loops, and ships with robust safeguards.
Modalities
In / Out Price
$10 / $50per 1M
Context
1M
Released
Jun 9, 2026
Providers
Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick — Balanced (price + speed), Nitro (fastest), or Exacto (one fixed provider).
| Provider | Input $/M | Output $/M | Latency | Throughput | Uptime | |
|---|---|---|---|---|---|---|
 | $10 | $50 | -- | -- | 0% | |
 | $10 | $50 | -- | -- | 0% | |
| $10 | $50 | -- | -- | -- | |
 | $10 | $50 | -- | -- | 0% | |
 | $10 | $50 | -- | -- | -- |
Performance
Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).
Throughput
Latency
E2E Latency
Tool Call Error Rate
Structured Output Error Rate
Pricing
List price is the headline rate per million tokens. Effective price is what you actually pay after prompt caching is applied — for repeated context, this can be 60–80% cheaper. The chart below shows the rolling effective price over the past 30 days.
Weighted Average
Weighted Avg Input Price
$0.0000
/M tokens
Weighted Avg Output Price
$0.0000
/M tokens
Input Price / 1M tokens (7 days)
Output Price / 1M tokens (7 days)
Benchmarks
Scores on standardized evaluations. Higher percentages are better — and rank percentile shows where this model lands among all models on OpenRouter.
Overall intelligence score combining multiple benchmarks
64.9
Artificial Analysis
Intelligence Index
Composite coding capability score
62.0
Artificial Analysis
Coding Index
Composite agentic capability score
80.6
Artificial Analysis
Agentic Index
Reasoning
GPQA Diamond
Graduate-level scientific reasoning
92.6%
HLE
Humanity's Last Exam
53.3%
IFBench
Instruction-following benchmark
63.5%
τ²-Bench Telecom
Conversational AI agents in dual-control scenarios
98.5%
AA-LCR
Long context reasoning evaluation
70.0%
GDPval-AA
Economically valuable tasks
71.6%
CritPt
Research-level physics reasoning
28.6%
Coding
SciCode
Python programming for scientific computing
60.2%
Terminal-Bench Hard
Agentic coding & terminal use
62.9%
Knowledge
AA-Omniscience Accuracy
Proportion of correctly answered questions
61.4%
AA-Omniscience Non-Hallucination Rate
Rate of avoiding hallucination among non-correct responses
45.1%
Apps
Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.
Activity
Token volume and request traffic to this model over time.
Prompt tokens measure input size. Reasoning tokens show internal thinking before a response. Completion tokens reflect total output length.
Uptime
Percent of requests that succeeded over the last 30 days. OpenRouter monitors every provider continuously and automatically retries on the next-best provider when one returns an error.
Avg. Provider Uptime (3d)
62.75%
averaged across all endpoints
When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access uptime data programmatically through the Endpoints API. Learn more about our load balancing and customization options.
Quick Start
Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.
Get your API key
Create an API key from your OpenRouter dashboard and set it as an environment variable:
export OPENROUTER_API_KEY=sk-or-v1-...Make your first request
Use anthropic/claude-fable-5 with the OpenRouter API:
OpenRouter supports reasoning-enabled models that can show their step-by-step thinking process. Use the reasoning parameter in your request to enable reasoning, and access the reasoning_details array in the response to see the model's internal reasoning before the final answer. When continuing a conversation, preserve the complete reasoning_details when passing messages back to the model so it can continue reasoning from where it left off. Learn more about reasoning tokens.
In the examples below, the OpenRouter-specific headers are optional. Setting them allows your app to appear on the OpenRouter leaderboards.
import { OpenRouter } from "@openrouter/sdk";
const openrouter = new OpenRouter({
apiKey: "<OPENROUTER_API_KEY>"
});
// Stream the response to get reasoning tokens in usage
const stream = await openrouter.chat.send({
model: "anthropic/claude-fable-5",
messages: [
{
role: "user",
content: "How many r's are in the word 'strawberry'?"
}
],
stream: true
});
let response = "";
for await (const chunk of stream) {
const content = chunk.choices[0]?.delta?.content;
if (content) {
response += content;
process.stdout.write(content);
}
// Usage information comes in the final chunk
if (chunk.usage) {
console.log("\nReasoning tokens:", chunk.usage.reasoningTokens);
}
}Using third-party SDKs
For information about using third-party SDKs and frameworks with OpenRouter, please see our frameworks documentation.
Enable streaming
Add "stream": true to your request body to receive responses as server-sent events:
curl -N https://openrouter.ai/api/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-d '{
"model": "anthropic/claude-fable-5",
"stream": true,
"messages": [
{"role": "user", "content": "Hello"}
]
}'Endpoint
Sends a request for a model response for the given chat conversation. Supports both streaming and non-streaming modes.
https://openrouter.ai/api/v1/chat/completionsBearer $OPENROUTER_API_KEYapplication/jsonoptional — your site URL, for rankingsoptional — your site name, for rankingsanthropic/claude-fable-5Creates a streaming or non-streaming response using the OpenAI Responses API format.
Docshttps://openrouter.ai/api/v1/responsesBearer $OPENROUTER_API_KEYapplication/jsonoptional — your site URL, for rankingsoptional — your site name, for rankingsanthropic/claude-fable-5Creates a message using the Anthropic Messages API format. Supports text, images, PDFs, tools, and extended thinking.
Docshttps://openrouter.ai/api/v1/messagesBearer $OPENROUTER_API_KEYapplication/jsonoptional — your site URL, for rankingsoptional — your site name, for rankingsanthropic/claude-fable-5Parameters
| Name | Type | Default | Description |
|---|---|---|---|
reasoning | map | — | Controls reasoning behavior for models that support thinking tokens, including whether reasoning is enabled, the reasoning effort, maximum reasoning tokens, and whether reasoning is excluded from the response. |
max_tokens | integer | — | This sets the upper limit for the number of tokens the model can generate in response. |
stop | array | — | Stop generation immediately if the model encounter any token specified in the stop array. |
tool_choice | string or object | — | Controls which (if any) tool is called by the model. |
tools | array | — | Tool calling parameter, following OpenAI's tool calling request shape. |
response_format | map | — | Forces the model to produce specific output format. |
verbosity | enum | — | Constrains the verbosity of the model's response. |