Anthropic
·Released on May 27, 2026Claude Opus 4.8 API Benchmarks, Pricing & Provider Data
Compare Claude Opus 4.8 with another model
Choose a model to open its comparison page.
LLM
Claude Opus 4.8 benchmark, API pricing, and provider data cover 795 API providers, with prices starting at $0.0010/M. Claude Opus 4.8 free API options are available from 6 providers. The page also shows measured API speed and first-token latency.
Anthropic Claude Opus 4.8 is Anthropic frontier model for complex reasoning, long-horizon agentic coding, and professional knowledge work, with a 1M-token context window and adaptive thinking support.
Quality
#8of 100
76.0
LMSpeed score
Speed
193char/s
2.96 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
#1Coding65.2RatedGlobal rank #34/4 Measured dimensions
80% interval: 58.6–71.8
code generation61.5
scicode · scicode
repository engineering67.6
swe_pro · swe_pro
debugging testing78.5
swe_multilingual · benchlm_coding_swe_multilingual / swe_verified · swe_verified
tooling quality53.2
terminalbench · benchlm_coding_terminal_bench2
#2Knowledge63.7Provisional1/4 Measured dimensions
80% interval: 49.7–77.7
broad knowledge63.7
aa_omniscience · aa_omniscience_index / benchlm_category_knowledge · benchlm_category_knowledge
professional knowledgePrior only
factualityPrior only
retrieval open bookPrior only
#3Agents62.6RatedGlobal rank #74/4 Measured dimensions
80% interval: 57.1–68.1
planning63.1
deep_planning · gert_labs
tool use63.3
mcp_atlas · mcp_atlas / tau · tau2_bench / toolathlon · toolathlon
environment execution62.9
browsecomp · browse_comp / deep_search_qa · deep_search_qa / gdpval_aa · benchlm_agentic_gdpval_aa / osworld · os_world2 / osworld · os_world_verified / terminalbench · benchlm_agentic_terminal_bench2
recovery reliability61.1
harvey_lab · aa_harvey_lab / researchclaw · research_claw_bench
#4Multimodal59.6Estimated2/4 Measured dimensions
80% interval: 47.6–71.6
perception ocrPrior only
document spatial58.9
charxiv · charxiv
visual reasoningPrior only
video action60.3
screenspot · screen_spot_pro
#5Math58Provisional1/4 Measured dimensions
80% interval: 41.9–74.0
foundational mathPrior only
competition mathPrior only
proof frontier58
frontiermath · frontier_math_v2_tier4 / frontiermath · frontier_math_v2_tiers13
applied tool mathPrior only
#6Reasoning56.4RatedGlobal rank #133/4 Measured dimensions
80% interval: 47.7–65.2
abstract logic51.3
arc_agi · arc_agi2
scientific causal63.8
critpt · critpt / gpqa · gpqa / hle · hle / hle · hle_no_tools
multistep constraintsPrior only
evidence verification54.2
lcr · lcr
#7Multilingual55Provisional1/4 Measured dimensions
80% interval: 37.9–72.2
cross language understanding55
include · include
multilingual generationPrior only
reasoning transferPrior only
low resource robustnessPrior only
#8Instruction following49.9Provisional1/4 Measured dimensions
80% interval: 33.9–65.9
constraint followingPrior only
structured outputPrior only
novel instruction generalization49.9
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 score76.0#8 / 100Factuality hallucination rate3.4#1 / 4
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
Score62.6#780% interval57.1–68.14/4 Measured dimensionsAgentic score82.8#16 / 69Terminal-Bench 2.074.6#14 / 53
Agents
V3.0undefined metric} other undefined metrics}} · Rated
Dimensions and evidence
Planning & decomposition63.1
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
deep_planning · gert_labs · z 1.75 · q 1.00
Tool use63.3
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
mcp_atlas · mcp_atlas · z 0.92 · q 1.00
tau · tau2_bench · z 0.55 · q 1.00
toolathlon · toolathlon · z 1.22 · q 1.00
Environment & long-horizon execution62.9
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
browsecomp · browse_comp · z 0.37 · q 1.00
deep_search_qa · deep_search_qa · z 0.98 · q 1.00
gdpval_aa · benchlm_agentic_gdpval_aa · z 1.24 · q 1.00
osworld · os_world2 · z 0.10 · q 1.00
osworld · os_world_verified · z 1.12 · q 1.00
terminalbench · benchlm_agentic_terminal_bench2 · z 0.75 · q 1.00
Recovery & completion reliability61.1
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
harvey_lab · aa_harvey_lab · z 0.09 · q 1.00
researchclaw · research_claw_bench · z 0.90 · q 1.00
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Coding
V3.0undefined metric} other undefined metrics}} · Rated
Score65.2#380% interval58.6–71.84/4 Measured dimensionsSciCode53.5%#16 / 206Coding score68.8#4 / 81
Coding
V3.0undefined metric} other undefined metrics}} · Rated
Dimensions and evidence
Code generation61.5
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
scicode · scicode · z 1.41 · q 1.00
Repository engineering67.6
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
swe_pro · swe_pro · z 2.41 · q 1.00
Debugging & testing78.5
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
swe_multilingual · benchlm_coding_swe_multilingual · z 2.42 · q 1.00
swe_verified · swe_verified · z 3.00 · q 1.00
Tool-assisted development & quality53.2
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
terminalbench · benchlm_coding_terminal_bench2 · z 0.44 · q 1.00
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Reasoning
V3.0undefined metric} other undefined metrics}} · Rated
Score56.4#1380% interval47.7–65.23/4 Measured dimensionsGPQA92.0%#17 / 213HLE48.7%#6 / 210
Reasoning
V3.0undefined metric} other undefined metrics}} · Rated
Dimensions and evidence
Abstract logic51.3
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
arc_agi · arc_agi2 · z -0.00 · q 1.00
Scientific & causal reasoning63.8
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
critpt · critpt · z 0.91 · q 1.00
gpqa · gpqa · z 1.18 · q 1.00
hle · hle · z 1.17 · q 1.00
hle · hle_no_tools · z 0.89 · q 1.00
Multi-step constraintsPrior only
Evidence integration & verification54.2
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
lcr · lcr · z 0.20 · q 1.00
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Score63.780% interval49.7–77.71/4 Measured dimensionsKnowledge score86.8#4 / 69GPQA-D93.6#4 / 31
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Dimensions and evidence
Broad knowledge63.7
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
aa_omniscience · aa_omniscience_index · z 1.11 · q 1.00
benchlm_category_knowledge · benchlm_category_knowledge · z 1.29 · q 1.00
Professional knowledgePrior only
FactualityPrior only
Retrieval & open-book usePrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Artificial Analysis Intelligence IndexV3 evidence
LMSpeed rank#7
Score57.3
Sourcebenchlm.ai
UpdatedSep 1, 2026
Confidence3
AA-Omniscience Hallucination Rate
LMSpeed rank#85
Score39.3
Sourcebenchlm.ai
UpdatedSep 1, 2026
Confidence3
Math
V3.0undefined metric} other undefined metrics}} · Provisional
Score5880% interval41.9–74.01/4 Measured dimensionsUSAMO 202696.7#1 / 2Math score66.8#22 / 62
Math
V3.0undefined metric} other undefined metrics}} · Provisional
Dimensions and evidence
Foundational mathPrior only
Competition mathPrior only
Advanced proofs58
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
frontiermath · frontier_math_v2_tier4 · z 1.09 · q 1.00
frontiermath · frontier_math_v2_tiers13 · z 0.60 · q 1.00
Applied & tool-assisted mathPrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
FrontierMath v2 (Tiers 1-3)V3 evidence
LMSpeed rank#8
Score47.2
Sourcebenchlm.ai
UpdatedSep 1, 2026
Confidence3
FrontierMath v2 (Tier 4)V3 evidence
LMSpeed rank#7
Score31.3
Sourcebenchlm.ai
UpdatedSep 1, 2026
Confidence3
Multilingual
V3.0undefined metric} other undefined metrics}} · Provisional
Score5580% interval37.9–72.21/4 Measured dimensionsINCLUDE87.6#2 / 4
Multilingual
V3.0undefined metric} other undefined metrics}} · Provisional
Dimensions and evidence
Cross-language understanding55
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
include · include · z 0.35 · q 0.33
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
Score59.680% interval47.6–71.62/4 Measured dimensionsMultimodal Grounded score85.4#5 / 44OfficeQA Pro66.2#2 / 9
Multimodal
V3.0undefined metric} other undefined metrics}} · Estimated
Dimensions and evidence
Perception & OCRPrior only
Document & spatial understanding58.9
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
charxiv · charxiv · z 1.31 · q 1.00
Visual reasoningPrior only
Video & grounded action60.3
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
screenspot · screen_spot_pro · z 1.08 · q 1.00
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Instruction following
V3.0undefined metric} other undefined metrics}} · Provisional
Score49.980% interval33.9–65.91/4 Measured dimensionsAA-IFBench62.2#49 / 84
Instruction following
V3.0undefined metric} other undefined metrics}} · Provisional
Dimensions and evidence
Constraint followingPrior only
Structured outputPrior only
Novel-instruction generalization49.9
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
ifbench · aa_if_bench · z -0.28 · q 1.00
Multi-turn & long instructionsPrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
OpenRouter endpoints
10 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 |
|---|---|---|---|---|---|---|
Amazon Bedrock amazon-bedrock/eu-west-1 | $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/us | $5/M | $25/M | 89.7% | — | — | undefined tokens / undefined tokens |
Azure azure/global | $5/M | $25/M | 86.3% | — | — | undefined tokens / undefined tokens |
Google google-vertex/us | $5.50/M | $27.50/M | — | — | — | undefined tokens / undefined tokens |
Google google-vertex/europe | $5.50/M | $27.50/M | — | — | — | undefined tokens / undefined tokens |
Amazon Bedrock amazon-bedrock/us | $5.50/M | $27.50/M | — | — | — | undefined tokens / undefined tokens |
Pricing Comparison
Compare Claude Opus 4.8 API pricing across 789 providers. Prices range from $0.0010/M to $49950.00/M. 钠 API offers the lowest rate at $0.0010/M. 6 providers offer free API credits or a free tier.
| Provider | Health | Model Variant | Group | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit |
|---|---|---|---|---|---|---|---|---|
L1 99% | claude-opus-4-8 | aws | -99%$0.059/M Cache read$0.0059/MCache write$0.073/MCache write 1h$0.117/M | -99%$0.294/M | 50.5 t/s | 4.82 s | — | |
L1 100% | claude-opus-4-8 | claude--kiro | -86%$0.685/M Cache read$0.068/MCache write$0.856/MCache write 1h$1.37/M | -86%$3.42/M | 46.6 t/s | 3.31 s | — | |
L1 100% | claude-opus-4-8-thinking | claude--kiro | -86%$0.685/M Cache read$0.068/MCache write$0.856/MCache write 1h$1.37/M | -86%$3.42/M | — | — | — | |
L1 99% | claude-opus-4-8 | Claude-Entry | -94%$0.300/M Cache read$0.030/M | -94%$1.50/M | 46.4 t/s | 2.54 s | ||
L1 99% | claude-opus-4-8 | default | -20%$4.00/M Cache read$0.400/MCache write$5.00/MCache write 1h$8.00/M | -20%$20.00/M | 45.6 t/s | 2.08 s | ||
L1 100% | claude-opus-4-8 | aws-q | -96%$0.214/M Cache read$0.021/M | -96%$1.07/M | — | — | ||
L1 100% | claude-opus-4-8 | default | -93%$0.342/M Cache read$0.034/M | -93%$1.71/M | — | — | ||
L1 100% | claude-opus-4-8-thinking | claude_kiro | -65%$1.75/M | -65%$8.75/M | — | — | ||
L1 100% | claude-opus-4-8-max | claude_kiro | -65%$1.75/M | -65%$8.75/M | — | — | — | |
L1 100% | claude-opus-4-8-medium | claude_kiro | -65%$1.75/M | -65%$8.75/M | — | — | — | |
L1 100% | claude-opus-4-8-xhigh | claude_kiro | -65%$1.75/M | -65%$8.75/M | — | — | — | |
L1 100% | claude-opus-4-8 | claude_kiro | -65%$1.75/M | -65%$8.75/M | — | — | ||
L1 100% | claude-opus-4-8-high | claude_kiro | -65%$1.75/M | -65%$8.75/M | — | — | — | |
L1 100% | claude-opus-4-8-low | claude_kiro | -65%$1.75/M | -65%$8.75/M | — | — | — | |
L1 100% | claude-opus-4-8 | default | $0.068/request | - | — | — | — | |
L1 100% | claude-opus-4-8-thinking | default | -86%$0.685/M | -86%$3.42/M | — | — | — | |
L1 100% | claude-opus-4-8 | default | -86%$0.685/M Cache read$0.068/M | -86%$3.42/M | — | — | — | |
L1 100% | claude-opus-4-8 | default | $5.00/M Cache read$0.500/MCache write$6.25/MCache write 1h$10.00/M | $25.00/M | — | — | — | |
兔子API Free | L1 100% | claude-opus-4-8 | 原价分组 | Free | Free | — | — | — |
L1 100% | 熊猫-特供-按量-满血逆-claude-opus-4-8 | default | -100%$0.015/M Cache read$0.0015/MCache write$0.019/MCache write 1h$0.030/M | -100%$0.076/M | — | — | — |
Showing 20 model IDs of 167.
Alternatives & Similar Models
Claude Opus 4.6
claude-opus-4-6
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.
186 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.
184 shared providers
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.
183 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.
180 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.
175 shared providers
GPT-5.4 Mini
gpt-5-4-mini
OpenAI GPT-5.4 Mini is a compact language model in the GPT-5 series, optimized for quick responses and high throughput.
162 shared providers
Frequently Asked Questions
- What benchmark data does Claude Opus 4.8 include?
- LMSpeed shows Claude Opus 4.8 benchmark context, API price, output speed, first-token latency, and provider data across 795 providers when those signals are available.
- What is the Claude Opus 4.8 API price?
- Claude Opus 4.8 has pricing from 795 providers, ranging from $0.0010/M to $49950.00/M. 钠 API has the lowest listed price.
- What does the Claude Opus 4.8 API pricing table include?
- The Claude Opus 4.8 API pricing table compares 795 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 4.8 API pricing?
- 钠 API currently has the lowest listed Claude Opus 4.8 price at $0.0010/M across 795 providers.
- Can I compare Claude Opus 4.8 API price and speed together?
- Yes. LMSpeed shows Claude Opus 4.8 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 4.8 API free?
- Yes, Claude Opus 4.8 free API options are available through 6 providerundefined other undefined} on LMSpeed, including 兔子API, 我不是AI神, 我不是AI神, 兔子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 4.8 free API access?
- LMSpeed currently lists 6 free API providerundefined other undefined} for Claude Opus 4.8: 兔子API, 我不是AI神, 我不是AI神, 兔子API, 兔子API. Check each provider row before using it because free tier limits can change.