Claude Opus 4.6
Claude Opus 4.6 is an Opus-tier model from Anthropic built for agentic coding, large-codebase navigation, financial and research work, and long-horizon planning.
input · usd / 1m tok
$5.00
output · usd / 1m tok
$25.00
context window
1mtokens
modalities · in → out
takes text and image in, gives text out
pricing
base api ratesusd per 1m tokens
- input
- $5.00
- output
- $25.00
- cache read
- $0.50
- cache write · default ttl
- $6.25
- cache write · 1h ttl
- $10.00
providers
Different companies host Claude Opus 4.6. Impossibl routes your request intelligently and handles failover automatically when a provider is down.
- Amazon Bedrock
- Anthropic
specifications
takes text and image in, gives text outanthropic/claude-opus-4-6
- creatorAnthropic
- model typeText generation
- context window1,000,000 tokens
- maximum outputnot published
- input
takes text and image in, gives text out
- outputtext
- tool callingnot verified
- releasedfeb 5, 2026
- endpoint
/v1/chat/completions
unknown means the public catalog does not establish that fact. a model's documented capabilities can differ from what a particular api supports. see the model documentation for integration details.
try it · your prompt, this model, live
# responses API
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["IMPOSSIBL_API_KEY"],
base_url="https://api.impossibl.com/v1",
)
resp = client.responses.create(
model="anthropic/claude-opus-4-6",
input="",
)
print(resp.output_text)
edit the prompt, then run
benchmarks
intelligence index
26.4#57 of 113 models on the gateway
- omniscience2.4#35 of 90
- gpqa84.0%#48 of 82
- humanity’s last exam19.1%#66 of 93
- Tau284.8%
- GPQA84.0%
- MMMU-Pro72.5%
- AA-LCR67.0%
- Terminal-Bench Hard48.5%
- IFBench44.6%
- Humanity’s Last Exam19.1%
- CritPt2.8%
- Intelligence Index26.35
- Omniscience Index2.37
- intelligence index (API)26.4
each configuration is listed separately; these evaluations describe the tested model configuration, and performance and costs can differ on impossibl. unmeasured scores are omitted and api values keep their source units. last checked 2026-10-22.
compare Claude Opus 4.6 with other models
frontier labs and open weights, best-ranked firstusd / 1m tok · in / out
- moonshotai/kimi-k3.1-pro$2.00 / $10.00compare →
- openai/gpt-6-astra$10.00 / $50.00compare →
- google/gemini-4-argon$2.00 / $10.00compare →
- meta/muse-wonder$4.00 / $20.00compare →
frequently asked questions
What is Claude Opus 4.6?
Claude Opus 4.6 is an Opus-tier model from Anthropic built for agentic coding, large-codebase navigation, financial and research work, and long-horizon planning. It introduced adaptive thinking, which lets the model decide when to reason at length, along with a much larger context window, context compaction, and parallel agent teams.
How much does Claude Opus 4.6 cost?
Claude Opus 4.6 costs $5.00 per million input tokens and $25.00 per million output tokens through the Impossibl API. Cache reads cost $0.50 per million tokens; cache writes cost $6.25 per million tokens; cache writes with one-hour retention cost $10.00 per million tokens. All rates are in USD.
What is the context length of Claude Opus 4.6?
Claude Opus 4.6 has a 1,000,000-token context window through the Impossibl API.
What inputs and outputs does Claude Opus 4.6 support?
Claude Opus 4.6 accepts text and image as input. Claude Opus 4.6 returns text.
How do I use Claude Opus 4.6 through an API?
Claude Opus 4.6 is available through the Impossibl API. Use anthropic/claude-opus-4-6 as the model identifier with /v1/chat/completions. The quickstart explains how to create an API key and send your first request.
When was Claude Opus 4.6 released?
Anthropic released Claude Opus 4.6 on February 5, 2026.
this page describes Claude Opus 4.6 as listed by the impossibl public api. prices and availability come from that catalog, refreshed here every five minutes. this is an impossibl offering, not a comparison of independent hosting-provider quotes. model descriptions and release dates, where available, use the creator sources linked under the answers above.
view the source catalog ↗model as markdown ↗report a correction →