Anthropic
·Released on Feb 4, 2026Claude Opus 4.6 API Benchmarks, Pricing & Provider Data
Compare Claude Opus 4.6 with another model
Choose a model to open its comparison page.
LLM
Claude Opus 4.6 benchmark, API pricing, and provider data cover 1090 API providers, with prices starting at $0.0010/M. Claude Opus 4.6 free API options are available from 7 providers. The page also shows measured API speed and first-token latency.
Anthropic Claude Opus 4.6 is the most capable Claude Opus tier, optimized for complex analysis, long-horizon coding, and high-stakes enterprise reasoning workloads.
Quality
#27of 100
65.0
LMSpeed score
Speed
45char/s
5.30 s
Cost
#165of 181
$0.0010/ 1M · 8:1 in:out
$0.0002 in · $0.0009 out
Category Performance
Observed-capability estimates with uncertainty reported separately from independent benchmark families.
- Coverage
- 8 / 8
- Methodology
- V3.0
#1Coding59RatedGlobal rank #83/4 Measured dimensions
80% interval: 50.9–67.0
code generation55.3
livecodebench · live_code_bench_pro / scicode · scicode
repository engineering54.6
react_native_bench · react_native_evals / swe_pro · swe_pro / vibecode · vibe_code_bench
debugging testing66.9
swe_rebench · swe_rebench / swe_verified · swe_verified
tooling qualityPrior only
#2Math56.5Provisional1/4 Measured dimensions
80% interval: 40.4–72.5
foundational mathPrior only
competition mathPrior only
proof frontier56.5
frontiermath · frontier_math_v2_tier4 / frontiermath · frontier_math_v2_tiers13
applied tool mathPrior only
#3Agents54.9RatedGlobal rank #214/4 Measured dimensions
80% interval: 49.2–60.6
planning56.6
deep_planning · gert_labs
tool use50.5
tau · tau2_bench
environment execution52.8
browsecomp · browse_comp / deep_search_qa · deep_search_qa / osworld · os_world_verified / terminalbench · benchlm_agentic_terminal_bench2
recovery reliability59.6
apex_agents · apex_agents_aa / claw_eval · claw_eval / cyber_gym · cyber_gym / jobbench · job_bench / researchclaw · research_claw_bench
#4Multilingual54Provisional1/4 Measured dimensions
80% interval: 36.7–71.3
cross language understanding54
global_mmlu · aa_global_mmlu_lite
multilingual generationPrior only
reasoning transferPrior only
low resource robustnessPrior only
#5Knowledge53.7Provisional1/4 Measured dimensions
80% interval: 40.1–67.4
broad knowledgePrior only
professional knowledge53.7
healthbench · health_bench_hard / medxpert · med_xpert_qa_text / supergpqa · super_gpqa
factualityPrior only
retrieval open bookPrior only
#6Reasoning53.4RatedGlobal rank #293/4 Measured dimensions
80% interval: 44.8–62.1
abstract logicPrior only
scientific causal57.9
critpt · critpt / gpqa · gpqa / hle · hle / hle · hle_no_tools
multistep constraints53.3
mmlu_pro · mmlu_pro
evidence verification49.2
lcr · lcr
#7Multimodal48.4Estimated2/4 Measured dimensions
80% interval: 37.2–59.5
perception ocrPrior only
document spatialPrior only
visual reasoning41.2
erqa · erqa / medxpert · med_xpert_qa_mm / mmmu_pro · mmmu_pro
video action55.5
screenspot · screen_spot_pro
#8Instruction following44.7Provisional1/4 Measured dimensions
80% interval: 28.7–60.8
constraint followingPrior only
structured outputPrior only
novel instruction generalization44.7
ifbench · aa_if_bench
long multiturn instructionPrior only
Specifications
Input and output token limits for this model, plus how it ranks on long-context understanding.
INPUT
1Mtokens
≈ 1.2K pages of text
OUTPUT
128Ktokens
8K128K1M4M
1M
Features
Rankings
Excels at
It's decent at
Falls behind in
Detailed scores
Updated: Sep 1, 2026Overall
undefined metric} other undefined metrics}}
Overall score65.0#27 / 100
Overall
undefined metric} other undefined metrics}}
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Pricing
undefined metric} other undefined metrics}}
Input price$5.00/M#165 / 181Output price$25.00/M#166 / 181
Pricing
undefined metric} other undefined metrics}}
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Agents
V3.0undefined metric} other undefined metrics}} · Rated
Score54.9#2180% interval49.2–60.64/4 Measured dimensionsAgentic score65.3#30 / 69Terminal-Bench 2.065.4#24 / 53
Agents
V3.0undefined metric} other undefined metrics}} · Rated
Dimensions and evidence
Planning & decomposition56.6
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
deep_planning · gert_labs · z 0.89 · q 1.00
Tool use50.5
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
tau · tau2_bench · z -0.05 · q 1.00
Environment & long-horizon execution52.8
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
browsecomp · browse_comp · z 0.31 · q 1.00
deep_search_qa · deep_search_qa · z -0.41 · q 1.00
osworld · os_world_verified · z -0.04 · q 1.00
terminalbench · benchlm_agentic_terminal_bench2 · z 0.10 · q 1.00
Recovery & completion reliability59.6
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
apex_agents · apex_agents_aa · z 0.50 · q 1.00
claw_eval · claw_eval · z 1.87 · q 1.00
cyber_gym · cyber_gym · z -0.87 · q 1.00
jobbench · job_bench · z 0.27 · q 1.00
researchclaw · research_claw_bench · z 0.57 · q 1.00
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Coding
V3.0undefined metric} other undefined metrics}} · Rated
Score59#880% interval50.9–67.03/4 Measured dimensionsSciCode45.7%#45 / 206Coding score63.2#10 / 81
Coding
V3.0undefined metric} other undefined metrics}} · Rated
Dimensions and evidence
Code generation55.3
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
livecodebench · live_code_bench_pro · z -0.90 · q 0.50
scicode · scicode · z 1.27 · q 1.00
Repository engineering54.6
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
react_native_bench · react_native_evals · z 0.80 · q 1.00
swe_pro · swe_pro · z -0.62 · q 1.00
vibecode · vibe_code_bench · z 1.10 · q 1.00
Debugging & testing66.9
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
swe_rebench · swe_rebench · z 2.55 · q 1.00
swe_verified · swe_verified · z 0.85 · q 1.00
Tool-assisted development & qualityPrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Reasoning
V3.0undefined metric} other undefined metrics}} · Rated
Score53.4#2980% interval44.8–62.13/4 Measured dimensionsMMLU-Pro82.0%#50 / 129GPQA84.0%#70 / 213
Reasoning
V3.0undefined metric} other undefined metrics}} · Rated
Dimensions and evidence
Abstract logicPrior only
Scientific & causal reasoning57.9
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
critpt · critpt · z 0.00 · q 1.00
gpqa · gpqa · z 0.91 · q 1.00
hle · hle · z 0.94 · q 1.00
hle · hle_no_tools · z -0.15 · q 1.00
Multi-step constraints53.3
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
mmlu_pro · mmlu_pro · z 0.23 · q 1.00
Evidence integration & verification49.2
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
lcr · lcr · z -0.47 · q 1.00
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Score53.780% interval40.1–67.41/4 Measured dimensionsKnowledge score82.4#12 / 69GPQA-D89.2#18 / 31
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Dimensions and evidence
Broad knowledgePrior only
Professional knowledge53.7
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
healthbench · health_bench_hard · z -2.08 · q 0.88
medxpert · med_xpert_qa_text · z -0.45 · q 0.50
supergpqa · super_gpqa · z 3.00 · q 1.00
FactualityPrior only
Retrieval & open-book usePrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Artificial Analysis Intelligence Index
LMSpeed rank#48
Score38.8
Sourcebenchlm.ai
UpdatedSep 1, 2026
Confidence3
AA-Omniscience Hallucination Rate
LMSpeed rank#43
Score80.1
Sourcebenchlm.ai
UpdatedSep 1, 2026
Confidence3
Math
V3.0undefined metric} other undefined metrics}} · Provisional
Score56.580% interval40.4–72.51/4 Measured dimensionsMath score59.6#28 / 62AIME25 (Arcee)99.8#1 / 5
Math
V3.0undefined metric} other undefined metrics}} · Provisional
Dimensions and evidence
Foundational mathPrior only
Competition mathPrior only
Advanced proofs56.5
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
frontiermath · frontier_math_v2_tier4 · z 0.85 · q 1.00
frontiermath · frontier_math_v2_tiers13 · z 0.45 · q 1.00
Applied & tool-assisted mathPrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
FrontierMath v2 (Tiers 1-3)V3 evidence
LMSpeed rank#10
Score40.7
Sourcebenchlm.ai
UpdatedSep 1, 2026
Confidence3
FrontierMath v2 (Tier 4)V3 evidence
LMSpeed rank#10
Score22.9
Sourcebenchlm.ai
UpdatedSep 1, 2026
Confidence3
Multilingual
V3.0undefined metric} other undefined metrics}} · Provisional
Score5480% interval36.7–71.31/4 Measured dimensionsAA Global-MMLU-Lite92.2#2 / 4
Multilingual
V3.0undefined metric} other undefined metrics}} · Provisional
Dimensions and evidence
Cross-language understanding54
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
global_mmlu · aa_global_mmlu_lite · z 0.00 · q 0.50
Multilingual generationPrior only
Reasoning transferPrior only
Low-resource robustnessPrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Multimodal
V3.0undefined metric} other undefined metrics}} · Estimated
Score48.480% interval37.2–59.52/4 Measured dimensionsMultimodal Grounded score54.8#29 / 44MMMU-Pro77.3#21 / 31
Multimodal
V3.0undefined metric} other undefined metrics}} · Estimated
Dimensions and evidence
Perception & OCRPrior only
Document & spatial understandingPrior only
Visual reasoning41.2
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
erqa · erqa · z -1.94 · q 1.00
medxpert · med_xpert_qa_mm · z -0.93 · q 0.75
mmmu_pro · mmmu_pro · z -0.29 · q 1.00
Video & grounded action55.5
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
screenspot · screen_spot_pro · z 0.44 · q 1.00
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Instruction following
V3.0undefined metric} other undefined metrics}} · Provisional
Score44.780% interval28.7–60.81/4 Measured dimensionsAA-IFBench44.6#59 / 84
Instruction following
V3.0undefined metric} other undefined metrics}} · Provisional
Dimensions and evidence
Constraint followingPrior only
Structured outputPrior only
Novel-instruction generalization44.7
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
ifbench · aa_if_bench · z -0.97 · q 1.00
Multi-turn & long instructionsPrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
OpenRouter endpoints
6 endpointsThird-party OpenRouter endpoint data, shown separately from LMSpeed measurements. Some 30-minute live performance fields only appear after syncing with an OpenRouter API key.
| Provider endpoint | Input | Output | 1d uptime | 30m latency | 30m throughput | Context / output |
|---|---|---|---|---|---|---|
Google google-vertex/europe | $5.50/M | $27.50/M | 100% | — | — | undefined tokens / undefined tokens |
Google google-vertex/global | $5/M | $25/M | 100.0% | — | — | undefined tokens / undefined tokens |
Claude Platform on AWS claude-on-aws | $5/M | $25/M | 100.0% | — | — | undefined tokens / undefined tokens |
Amazon Bedrock amazon-bedrock | $5/M | $25/M | 99.9% | — | — | undefined tokens / undefined tokens |
Anthropic anthropic | $5/M | $25/M | 99.5% | — | — | undefined tokens / undefined tokens |
Azure azure/global | $5/M | $25/M | 97.6% | — | — | undefined tokens / undefined tokens |
Pricing Comparison
Compare Claude Opus 4.6 API pricing across 1083 providers. Prices range from $0.0010/M to $49950.00/M. 钠 API offers the lowest rate at $0.0010/M. 7 providers offer free API credits or a free tier.
| Provider | Health | Model Variant | Group | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit |
|---|---|---|---|---|---|---|---|---|
L1 100% | claude-opus-4-6 | default | $6.00/M Cache read$0.600/MCache write$7.50/MCache write 1h$12.00/M | $30.00/M | 112.9 t/s | 2.19 s | — | |
L1 69% | claude-opus-4-6 | 活动分组1 | -94%$0.286/M | -94%$1.43/M | 83.7 t/s | 3.92 s | — | |
L1 69% | claude-opus-4-6-thinking | 活动分组1 | -94%$0.286/M | -94%$1.43/M | — | — | — | |
L1 100% | claude-opus-4-6 | default | -86%$0.685/M Cache read$0.068/M | -86%$3.42/M | 45.9 t/s | 2.56 s | — | |
L1 0% | claude-opus-4-6 | kiro低缓 | -95%$0.258/M Cache read$0.026/MCache write$0.322/MCache write 1h$0.515/M | -95%$1.29/M | 45.1 t/s | 2.28 s | — | |
L1 0% | anthropic/claude-opus-4.6 | or | -59%$2.06/M Cache read$0.206/MCache write$2.58/MCache write 1h$4.12/M | -59%$10.30/M | — | — | — | |
L1 0% | claude-opus-4-6-fast | 特价纯血-bq渠道 | $6.18/M Cache read$0.618/MCache write$7.72/MCache write 1h$12.36/M | $30.90/M | — | — | — | |
L1 99% | claude-opus-4-6 | Claude-Entry | -94%$0.300/M Cache read$0.030/MCache write$0.375/MCache write 1h$0.600/M | -94%$1.50/M | 44.3 t/s | 2.80 s | ||
L1 100% | claude-opus-4-6 | claude带缓存 | $10.95/M Cache read$1.09/MCache write$13.69/MCache write 1h$21.90/M | $54.75/M | 43.6 t/s | 3.35 s | — | |
L1 99% | claude-opus-4-6 | default | $5.35/M Cache read$0.535/MCache write$6.69/MCache write 1h$10.71/M | $26.77/M | 42.5 t/s | 1.44 s | — | |
L1 99% | claude-opus-4-6 | claude | -91%$0.450/M Cache read$0.150/MCache write$0.300/MCache write 1h$0.480/M | -91%$2.25/M | 40.5 t/s | 16.14 s | — | |
L1 99% | claude-opus-4-6 | default | -98%$0.103/M | -98%$0.514/M | 40.3 t/s | 3.74 s | ||
L1 99% | [按次特价]claude-opus-4-6 | default | $0.0068/request | - | — | — | — | |
L1 100% L2 0% | claude-opus-4-6 | Claude_AG | -98%$0.096/M Cache read$0.0096/M | -98%$0.479/M | 38.4 t/s | 2.61 s | — | |
L1 100% | claude-opus-4-6 | default | $10.00/M Cache read$2.63/MCache write$1.57/MCache write 1h$2.52/M | $50.00/M | 37.2 t/s | 3.09 s | — | |
我不是AI神 Free | L1 19% | claude-opus-4-6 | default | Free | Free | 33.0 t/s | 14.80 s | — |
L1 100% | claude-opus-4-6 | default | $5.00/M Cache read$0.500/MCache write$6.25/MCache write 1h$10.00/M | $25.00/M | 27.0 t/s | 15.40 s | — | |
L1 100% | claude-opus-4-6-20260101 | default | $5.00/M Cache read$0.500/MCache write$6.25/MCache write 1h$10.00/M | $25.00/M | — | — | — | |
L1 100% | claude-opus-4-6 | aws-q | -96%$0.214/M Cache read$0.021/M | -96%$1.07/M | — | — | — | |
L1 100% | claude-opus-4-6 | default | -93%$0.342/M Cache read$0.034/M | -93%$1.71/M | — | — | — |
Showing 20 model IDs of 250.
Alternatives & Similar Models
GPT-5.4
gpt-5-4
OpenAI GPT-5.4 extends the GPT-5 family with stronger instruction following, deeper tool use, and improved performance on coding, math, and long-document analysis.
266 shared providers
Claude Sonnet 4.6
claude-sonnet-4-6
Anthropic Claude Sonnet 4.6 extends the Sonnet line with improved tool use, coding reliability, and long-context performance for everyday production workloads.
263 shared providers
Claude Haiku 4.5
claude-haiku-4-5
Anthropic Claude Haiku 4.5 delivers fast, low-cost responses while retaining solid instruction following for chat, classification, and lightweight coding.
245 shared providers
GPT-5.3 Codex
gpt-5-3-codex
OpenAI GPT-5.3 Codex is a code-specialized variant in the GPT-5 series, optimized for code generation, debugging, and software development tasks.
239 shared providers
Claude Opus 4.7
claude-opus-4-7
Anthropic Claude Opus 4.7 targets frontier-level analysis, complex coding, and autonomous workflows that require deep multi-step reasoning.
239 shared providers
GPT-5.2
gpt-5-2
OpenAI GPT-5.2 is a GPT-5 series model emphasizing advanced reasoning, multimodal understanding, and high-quality outputs for complex enterprise workloads.
227 shared providers
Frequently Asked Questions
- What benchmark data does Claude Opus 4.6 include?
- LMSpeed shows Claude Opus 4.6 benchmark context, API price, output speed, first-token latency, and provider data across 1090 providers when those signals are available.
- What is the Claude Opus 4.6 API price?
- Claude Opus 4.6 has pricing from 1090 providers, ranging from $0.0010/M to $49950.00/M. 钠 API has the lowest listed price.
- What does the Claude Opus 4.6 API pricing table include?
- The Claude Opus 4.6 API pricing table compares 1090 providers by input price, output price, free tier status, speed, first-token latency, and recent health data when available.
- Which provider has the cheapest Claude Opus 4.6 API pricing?
- 钠 API currently has the lowest listed Claude Opus 4.6 price at $0.0010/M across 1090 providers.
- Can I compare Claude Opus 4.6 API price and speed together?
- Yes. LMSpeed shows Claude Opus 4.6 API price, output speed, first-token latency, and provider health on the same page so you can compare cost and performance together.
- Is Claude Opus 4.6 API free?
- Yes, Claude Opus 4.6 free API options are available through 7 providerundefined other undefined} on LMSpeed, including 兔子API, 我不是AI神, 我不是AI神, Moyanjdc API, 兔子API. These providers offer free API credits or a free tier with no per-token charges.
- Where can I get Claude Opus 4.6 free API access?
- LMSpeed currently lists 7 free API providerundefined other undefined} for Claude Opus 4.6: 兔子API, 我不是AI神, 我不是AI神, Moyanjdc API, 兔子API. Check each provider row before using it because free tier limits can change.