Anthropic Claude Mythos preview
Amazon Bedrock chatAnthropic Claude Mythos preview is an Amazon Bedrock chat model.It supports a 1,000,000-token context windowwith up to 128,000 output tokens. Capabilities include function calling, vision, reasoning. Route Anthropic Claude Mythos preview via Future AGI's Agent Command Center for unified observability, caching, and 15 routing strategies including cost-optimized fallback.
We don't have verified per-token pricing for Anthropic Claude Mythos preview yet. If you have a source from Amazon Bedrock's documentation, help us add it — your submission gets reviewed within 48 hours.
Pricing
Per-token rates, expressed in USD per 1M tokens. Verified May 12, 2026.
| Input | — | |
| Output | — |
Limits
- Context window
- 1,000,000 tokens
- Max input
- 1,000,000 tokens
- Max output
- 128,000 tokens
- Modalities
- vision, text
Capabilities
- Function calling ✓ supported
- Parallel tool calls — not advertised
- Vision input ✓ supported
- Audio input — not advertised
- Audio output — not advertised
- PDF input — not advertised
- Streaming ✓ supported
- Structured output — not advertised
- Prompt caching — not advertised
- Reasoning ✓ supported
Where it's strong
- +long-context tasks — context window in the top 8% of peers
Watch out for
- !strict structured output — no JSON-schema enforcement, expect retry loops
Benchmarks pending
We haven't logged public benchmark scores for Anthropic Claude Mythos preview yet. Have one to contribute? Submit a source — citations help us prioritise.
Call Anthropic Claude Mythos preview via Agent Command Center
One OpenAI-compatible endpoint. Routing, fallback, semantic caching, guardrails, and cost tracking come along for the ride. First 100K requests + 100K cache hits free every month.
agentcc / @agentcc/client). Per-call metadata — provider, cost, latency, cache hit, request id — is returned on x-agentcc-* response headers, so any HTTP client can read it.# Anthropic Claude Mythos preview via the Agent Command Center Python SDK
# pip install agentcc
import os
from agentcc import AgentCC
client = AgentCC(
api_key=os.environ["AGENTCC_API_KEY"], # from app.futureagi.com → Settings → API Keys
base_url="https://gateway.futureagi.com/v1",
)
resp = client.chat.completions.create(
model="bedrock/anthropic-claude-mythos-preview",
messages=[{"role": "user", "content": "Hello, Anthropic Claude Mythos preview!"}],
)
print(resp.choices[0].message.content)
print(f"Tokens: {resp.usage.total_tokens}")
# Per-call gateway metadata is returned on x-agentcc-* response headers.
# When you need it programmatically, use .with_raw_response to get them:
raw = client.chat.completions.with_raw_response.create(
model="bedrock/anthropic-claude-mythos-preview",
messages=[{"role": "user", "content": "Same call, but I want the headers."}],
)
print("Provider:", raw.headers.get("x-agentcc-provider"))
print("Latency:", raw.headers.get("x-agentcc-latency-ms"), "ms")
print("Cost: ", raw.headers.get("x-agentcc-cost"), "USD")
print("Cache: ", raw.headers.get("x-agentcc-cache"))AGENTCC_API_KEY with a key fromapp.futureagi.com.Gateway docs ↗Compare with similar models
Anthropic Claude Mythos preview doesn't have a public Arena ELO score yet, so we group by provider only — quality-tier comparisons need a benchmark.
- DeepSeek v3.2Amazon Bedrock · $0.620/M in · $1.85/M out · 163,840 ctx
- Anthropic Claude Haiku 4.5 (2025-10-01)Amazon Bedrock · $1.00/M in · $5.00/M out · 200,000 ctx
- Amazon Nova 2 Lite v1.0Amazon Bedrock · $0.300/M in · $2.50/M out · 1,000,000 ctx
- Amazon Nova 2 Pro preview 20251202 v1.0Amazon Bedrock · $2.19/M in · $17.50/M out · 1,000,000 ctx
FAQ
How much does Anthropic Claude Mythos preview cost?
Public per-token pricing for Anthropic Claude Mythos preview is not yet published. Submit a source on this page to help us add it.
What is the context window of Anthropic Claude Mythos preview?
Anthropic Claude Mythos preview supports a 1,000,000-token context window with up to 128,000 output tokens.
Does Anthropic Claude Mythos preview support function calling?
Yes — Anthropic Claude Mythos preview supports function (tool) calling.
Is Anthropic Claude Mythos preview good for production?
Anthropic Claude Mythos preview is well-suited for long-context tasks — context window in the top 8% of peers. Consider alternatives if you need strict structured output — no JSON-schema enforcement, expect retry loops.
How can I route to Anthropic Claude Mythos preview with fallback?
Use Agent Command Center: a single OpenAI-compatible endpoint that supports cost-optimized routing, latency-aware retries, model fallback, and shadow traffic. Configure once, swap models without app changes.
Useful links for Anthropic Claude Mythos preview
Official sources, independent benchmarks, and pricing aggregators — no random search-engine guesses.
Third-party evals — verify the marketing.
Cross-check our number against the rest of the ecosystem.