HappyHorse 1.0 Coming SoonLearn More
Claude collection

Claude API Family

Use one EvoLink API to access every Claude model. Compare Opus, Sonnet, and Haiku on pricing, context, coding benchmarks, and capabilities — then pick the right model for your workload.

7 modelsUnified API accessText & coding AI

Flagship intelligence

Claude Opus 4.6 is Anthropic's most intelligent model — hybrid reasoning, extended thinking, and 80.8% SWE-bench for the hardest coding and research tasks.

Best balance

Claude Sonnet 4.6 delivers the ideal mix of speed, intelligence, and cost with 128K max output and extended thinking at 40% less than Opus.

Fastest & cheapest

Claude Haiku 4.5 matches Sonnet 4 on coding at $1/$5 per MTok — built for high-volume agents, sub-agents, and free-tier products.

Compare the Claude models

Choose based on your primary constraint: quality, cost, context length, or output size.

ModelBest forInput / MTokOutput / MTokContextMax outputSWE-bench
Complex coding, agent orchestration, extended thinking, and research synthesis.$5.00$25.001M64K80.8%
Claude Sonnet 4.6

Best Balance

Everyday coding, agentic workflows, and extended thinking at balanced cost.$3.00$15.001M128K
High-volume agents, sub-agents, latency-sensitive chat, and free-tier products.$1.00$5.00200K73.3%
Best coding model to date, complex agents, recommended default.$3.00$15.00200K (1M beta)
Previous-gen flagship with pinned versioned ID for stable production.$5.00$25.00200K64K
Multi-file refactoring, agentic coding, and deep research analysis.$15.00$75.00200K74.5%
Production workloads with 1M context beta for large documents.$3.00$15.00200K (1M beta)

Which Claude model should you choose?

Think of the Claude family as three tiers — Opus for the hardest work, Sonnet for everyday production, and Haiku for speed and scale.

Choose Opus if

Quality and depth matter most

Pick Opus when your tasks require extended thinking, complex multi-step reasoning, agent orchestration, or the highest coding accuracy. Opus 4.6 leads SWE-bench at 80.8% and supports the effort parameter for quality/cost control.

Choose Sonnet if

You need the best everyday model

Sonnet is Anthropic's recommended default. Sonnet 4.6 offers 128K max output (double Opus), extended thinking, and strong coding at $3/$15 per MTok. Sonnet 4.5 is the best coding model to date for agentic workflows.

Choose Haiku if

Speed and cost drive your decisions

Haiku 4.5 matches Sonnet 4 on coding (73.3% SWE-bench) at 3x lower cost. Ideal for parallelized sub-agents, latency-sensitive chat, and free-tier products where every token counts.

Explore each Claude model

Use this page to compare, then visit individual model pages for pricing details, playground access, and integration guides.

Flagship

Claude Opus 4.6

Complex coding, agent orchestration, extended thinking, and research synthesis.

Pricing
$5.00 input / $25.00 output per MTok
Context
1M
Max output
64K
Best Balance

Claude Sonnet 4.6

Everyday coding, agentic workflows, and extended thinking at balanced cost.

Pricing
$3.00 input / $15.00 output per MTok
Context
1M
Max output
128K
Fastest

Claude Haiku 4.5

High-volume agents, sub-agents, latency-sensitive chat, and free-tier products.

Pricing
$1.00 input / $5.00 output per MTok
Context
200K
Max output

Pricing summary

All Claude models use per-token pricing. Prompt caching (0.1x cache reads) and batch processing (50% off) are available across all tiers. EvoLink offers discounted access — see each model page for current EvoLink rates.

Opus tier

$5 / $25 per MTok

Flagship tier — use for complex reasoning, coding, and agent tasks where quality is the priority.

Sonnet tier

$3 / $15 per MTok

Balanced tier — recommended default for most production workloads at 40% less than Opus.

Haiku tier

$1 / $5 per MTok

Speed tier — 5x cheaper than Opus, ideal for high-volume and latency-sensitive applications.

Related Claude guides

Use this page to compare models, then visit guides for pricing details, comparisons, and integration.

Claude API Family FAQ

Everything you need to know about the product and billing.

The Claude API family on EvoLink includes all Anthropic Claude models — Opus 4.6, Opus 4.5, Opus 4.1, Sonnet 4.6, Sonnet 4.5, Sonnet 4.0, and Haiku 4.5. All are accessible through one EvoLink API key and endpoint at discounted rates. See the pricing guide for current EvoLink pricing.
Anthropic recommends Sonnet 4.5 as the default when you're unsure. It offers the best balance of intelligence, speed, and cost for most use cases. If you need maximum quality, use Opus 4.6. If cost or speed is the priority, use Haiku 4.5.
Opus is Anthropic's flagship tier for the hardest reasoning and coding tasks ($5/$25 per MTok). Sonnet is the balanced tier for everyday production workloads ($3/$15 per MTok). Sonnet 4.6 actually offers 128K max output vs Opus's 64K, making it better for large code generation.
Claude Haiku 4.5 at $1 input / $5 output per million tokens. It's 5x cheaper than Opus and 3x cheaper than Sonnet, while matching Sonnet 4 on coding benchmarks (73.3% SWE-bench Verified).
Yes. EvoLink provides a single API key and OpenAI-compatible endpoint for all Claude models. You can switch between Opus, Sonnet, and Haiku by changing the model parameter — no separate accounts or keys needed.

Where this page fits

Use this page to compare Claude models and choose a tier. Visit individual model pages for live pricing, playground access, and API integration details. Visit blog guides for pricing breakdowns and cross-provider comparisons.