Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...
Best coding model APIs for agents and code review
Compare coding model APIs by context length, tools, JSON output, latency, price, and what role they should play in production.
Waar is deze shortlist voor?: Coding models
A model that completes a 20-line function is not the same product as a model that reads half a monorepo and calls tools. Output is expensive, tool calls fail in boring ways, and long context burns money. Use this page to pick a primary coding model and a cheaper fallback, then decide budget rules before agents run unsupervised.
Bronbasis: NextModel use-case taxonomy and OpenRouter supported-parameter metadata when available. · Bijgewerkt 2026-07-01
Fit score
Aanbevolen kandidaten coding models
Begin met de shortlist, test daarna echte prompts en vergelijk de maandelijkse kosten voor productie-routing.
Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...
Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...
Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...
Vergelijkingstabel
Vergelijk de shortlist op prijs, provider, context, capaciteiten en bron.
Gebruik dit overzicht om een productieshortlist te verkleinen, een fallbackbeleid op te bouwen of modeleconomie te vergelijken.
| Model | Provider | Input | Output | Context | Capabilities | Best for | Latency | Status | Source |
|---|---|---|---|---|---|---|---|---|---|
| Anthropic: Claude Fable 5anthropic/claude-fable-5 | Anthropic | $1.45 / 1M tokens | $7.23 / 1M tokens | 1M | StreamingTool callingJSON modeVision | image understanding, multimodal chat | 1000-3000ms | Catalog | Platform curated |
| Anthropic: Claude Haiku 4.5anthropic/claude-haiku-4.5 | Anthropic | $0.145 / 1M tokens | $0.723 / 1M tokens | 200k | StreamingTool callingJSON modeVision | image understanding, multimodal chat | 1000-3000ms | Catalog | Platform curated |
| Anthropic: Claude Opus 4.5anthropic/claude-opus-4.5 | Anthropic | $0.723 / 1M tokens | $3.62 / 1M tokens | 200k | StreamingTool callingJSON modeVision | image understanding, multimodal chat | 1000-3000ms | Catalog | Platform curated |
| Anthropic: Claude Opus 4.6anthropic/claude-opus-4.6 | Anthropic | $0.723 / 1M tokens | $3.62 / 1M tokens | 1M | StreamingTool callingJSON modeVision | image understanding, multimodal chat | 1000-3000ms | Catalog | Platform curated |
| Anthropic: Claude Opus 4.7anthropic/claude-opus-4.7 | Anthropic | $0.723 / 1M tokens | $3.62 / 1M tokens | 1M | StreamingTool callingJSON modeVision | image understanding, multimodal chat | 1000-3000ms | Catalog | Platform curated |
| Anthropic: Claude Opus 4.8anthropic/claude-opus-4.8 | Anthropic | $0.723 / 1M tokens | $3.62 / 1M tokens | 1M | StreamingTool callingJSON modeVision | image understanding, multimodal chat | 1000-3000ms | Catalog | Platform curated |
| Claude Opus 5anthropic/claude-opus-5 | Anthropic | $0.723 / 1M tokens | $3.62 / 1M tokens | 1M | StreamingTool callingJSON modeVision | image understanding, multimodal chat | 1000-3000ms | Catalog | Platform curated |
| Anthropic: Claude Sonnet 4.5anthropic/claude-sonnet-4.5 | Anthropic | $0.434 / 1M tokens | $2.17 / 1M tokens | 1M | StreamingTool callingJSON modeVision | image understanding, multimodal chat | 1000-3000ms | Catalog | Platform curated |
FAQ
Coding models FAQ
What makes a model good for coding agents?
Reliable tool calling, structured output, enough context for the repo slice you send, and instructions it actually follows. Token price alone is a poor proxy.
How should teams control coding-agent cost?
Cap budgets per project, watch output tokens, and send simple tasks to cheaper models. Escalate only when quality checks fail.
Rankings