Claude API Family
Use one EvoLink API to access Claude Fable, Opus, Sonnet, and Haiku routes. Compare pricing, context, output limits, coding-agent fit, and routing value before you choose the right Claude model for each workload.
10 models
Fable, Opus, Sonnet, and Haiku tiers
Unified API access
OpenAI compatible, fast onboarding
Choose by workflow
Match model to task before integrating
Compare Claude models: Fable 5, Opus 4.8, Sonnet, and Haiku
Choose based on your primary constraint: maximum capability, strong default quality, cost, context length, output size, or fallback stability.
| Model | Best for | Input / MTok | Output / MTok | Context | Max output | SWE-bench |
|---|---|---|---|---|---|---|
Claude Fable 5 Most Powerful | The hardest coding, longest agent runs, and highest-stakes long-context work where stronger reasoning earns its premium. | $10.00 | $50.00 | 1M | 128K | — |
Claude Opus 4.8 Current Flagship | Complex coding agents, long-context planning, tool-heavy workflows, and high-value reasoning. | $5.00 | $25.00 | 1M | 128K | — |
Claude Opus 4.7 Previous Opus | Stable fallback for teams comparing or migrating hard Opus workloads to Opus 4.8. | $5.00 | $25.00 | 1M | 128K | — |
Claude Opus 4.6 Previous Opus | Previous-generation Opus route for teams migrating premium coding and agent workloads to newer Opus routes. | $5.00 | $25.00 | 1M | 128K | 80.8% |
Claude Sonnet 4.6 Best Balance | Everyday coding, agentic workflows, and extended thinking at balanced cost. | $3.00 | $15.00 | 1M | 128K | — |
Claude Haiku 4.5 Fastest | High-volume agents, sub-agents, latency-sensitive chat, and free-tier products. | $1.00 | $5.00 | 200K | — | 73.3% |
Claude Sonnet 4.5 Previous Sonnet | Previous-generation Sonnet route for existing coding and agent workflows. | $3.00 | $15.00 | 200K (1M beta) | — | — |
Claude Opus 4.5 Stable | Previous-gen flagship with pinned versioned ID for stable production. | $5.00 | $25.00 | 200K | 64K | — |
Claude Opus 4.1 Agentic | Multi-file refactoring, agentic coding, and deep research analysis. | $15.00 | $75.00 | 200K | — | 74.5% |
Claude Sonnet 4.0 1M Beta | Production workloads with 1M context beta for large documents. | $3.00 | $15.00 | 200K (1M beta) | — | — |
How to decide which Claude model to use
Use these rules to pick a starting model before you wire it into production.
Start with task complexity
For most premium Claude workloads, start with Opus 4.8. Escalate to Fable 5 only when the task is frontier-difficulty and the extra reasoning is worth the higher price.
Then check cost sensitivity
If you need strong results at lower cost, Sonnet is the safer default. Haiku is the high-volume route for simple tasks.
Then check context and output needs
Fable 5, Opus 4.8, Opus 4.7, Opus 4.6, and Sonnet 4.6 support 1M context. Long context still needs retrieval, compaction, and caching discipline.
Finally, consider routing
If task difficulty changes inside one workflow, use EvoLink Smart Router instead of hardcoding one Claude model.
Smart Router →If you already know your task type, find the recommended starting point in the table below.
Which Claude model should you use for coding agents?
Match the primary workflow to the right Claude route before you optimize prompts or fallback policy.
| Your task | Recommended start | Good fit if... | Watch out for |
|---|---|---|---|
| Coding agents | Claude Sonnet, Opus 4.8, or Fable 5 | You need reliable code generation, review, debugging, and tool-heavy agent behavior | Start with Sonnet for balanced cost, use Opus 4.8 as the strong premium default, and reserve Fable 5 for the hardest repo-scale tasks |
| Deep reasoning and analysis | Claude Opus 4.8 or Fable 5 | Tasks require extended thinking, multi-step reasoning, or highest-quality output | Use Fable 5 only when Opus 4.8 leaves quality on the table and the request value justifies the top-tier price |
| High-volume assistants and sub-agents | Claude Haiku | Tasks are simple, call volume is high, latency matters | Not suited for complex reasoning |
| Long-context document or codebase analysis | Claude Fable 5, Opus 4.8, or Sonnet 4.6 | You need 1M context for large documents, codebases, or long agent traces | Do not stuff context blindly; measure cost per completed workflow before moving long-context traffic to Fable 5 |
| Mixed text workflows | EvoLink Smart Router | Same workflow has both simple and complex tasks | Best when you do not want to maintain manual routing logic |
When to use Claude Opus 4.8 instead of Opus 4.7
Use this section as a routing shortcut. The full head-to-head comparison belongs in the Opus 4.8 vs Opus 4.7 guide.
Use Opus 4.8 for hard agent work
Prioritize 4.8 for long coding sessions, tool-heavy workflows, repo-scale review, and high-value reasoning tasks.
Keep Opus 4.7 as fallback
If a 4.7 workflow is already stable, keep it as a rollback route while you test 4.8 on real traces.
Compare by completed task cost
Same headline price does not mean same production cost. Measure retries, output length, latency, and accepted results.
Claude API workflows
Choose the right Claude model for real production workflows.
Coding agents
Use Sonnet for balanced coding workloads and Opus 4.8 for hard repo-scale agent tasks, review, debugging, and tool-heavy planning.
Long-context document analysis
Use the latest Opus and Sonnet routes for large documents, contracts, research papers, and long codebase traces; keep context discipline to control cost.
Customer support assistants
Use Haiku for high-volume, low-latency support agents. Upgrade to Sonnet or Opus only when the request needs deeper reasoning.
Agent routing and mixed text tasks
For supported text and agent workflows, EvoLink Smart Router can help route simple turns to cheaper models and hard turns to stronger Claude routes.
View Claude model details
Pick a model, then visit its detail page for full capabilities, pricing, and integration.
Claude Fable 5
Most Powerful
- Context
- 1M
- Pricing
- $10.00 / $50.00
Claude Opus 4.8
Current Flagship
- Context
- 1M
- Pricing
- $5.00 / $25.00
Claude Opus 4.7
Previous Opus
- Context
- 1M
- Pricing
- $5.00 / $25.00
Claude Opus 4.6
Previous Opus
- Context
- 1M
- Pricing
- $5.00 / $25.00
Claude Sonnet 4.6
Best Balance
- Context
- 1M
- Pricing
- $3.00 / $15.00
Claude Haiku 4.5
Fastest
- Context
- 200K
- Pricing
- $1.00 / $5.00
Claude Sonnet 4.5
Previous Sonnet
- Context
- 200K (1M beta)
- Pricing
- $3.00 / $15.00
Claude Opus 4.5
Stable
- Context
- 200K
- Pricing
- $5.00 / $25.00
Claude Opus 4.1
Agentic
- Context
- 200K
- Pricing
- $15.00 / $75.00
Claude Sonnet 4.0
1M Beta
- Context
- 200K (1M beta)
- Pricing
- $3.00 / $15.00
Access Claude models through one EvoLink API
All Claude models are available through a single EvoLink API key and OpenAI-compatible endpoint. Switch between Opus, Sonnet, and Haiku by changing the model parameter — no separate accounts or keys needed.
How to think about Claude API cost: reasoning depth, volume, and context
Deep reasoning amplifies output cost
Extended thinking, complex agents, and multi-step analysis produce longer outputs. Use Opus 4.8 when task value is high; use Sonnet or Haiku for simpler work.
High volume favors Haiku
Support bots, sub-agents, and high-call-volume products should start with Haiku, then escalate only the hard turns.
Context length affects input cost
Latest Opus and Sonnet routes support 1M context, but retrieval, compaction, and caching still matter before you default to Opus 4.8.
Pricing summary
All Claude models use per-token pricing. Prompt caching and batch processing may change effective cost. Use each model page for current EvoLink rates and use this family page to choose the right Claude tier.
Fable tier
$10.00 input
$50.00 output
Context: 1M
Top tier — route deliberately for the hardest coding, agent, and long-context tasks where stronger reasoning can justify the premium.
Opus tier
$5.00 input
$25.00 output
Context: 200K–1M
Flagship tier — use for complex reasoning, coding, and agent tasks where quality is the priority.
Sonnet tier
$3.00 input
$15.00 output
Context: 200K–1M
Balanced tier — recommended default for most production workloads at 40% less than Opus.
Haiku tier
$1.00 input
$5.00 output
Context: 200K
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 Fable 5 API Developer Guide
Confirmed model facts, limits, safeguards, pricing, and production routing guidance for EvoLink users.
How to Use Claude Fable 5 API
A first-call guide for using claude-fable-5 through the EvoLink unified API.
Claude Fable 5 vs Claude Opus 4.8
Compare the premium Fable route with the strong Opus default before changing production traffic.
Claude Opus 4.8 Review
A practical review based on Claude Code, long context, migration, and production routing questions.
Claude API Pricing Guide 2026
Pricing breakdown for Claude models, caching, batch discounts, and cost optimization tips.
Claude API Family FAQ
Everything you need to know about the product and billing.