Top pick
Claude Fable 5
Anthropic · $10.00/1M
AI coding buying guide · updated Sep 26
Find the right AI model for coding.
One guide, three picks (top, value, and budget), chosen from public benchmarks and current prices. No lab pays for placement.
See our coding picks →Backed by 197+ models, live pricing, and public benchmarks.
Top ranked
All 197 models →| # | Model | Lab | Context | Input price |
|---|---|---|---|---|
| 1 | Claude Fable 5 | Anthropic | 1M | $10.00/1M |
| 2 | Claude Opus 4.8 | Anthropic | 1M | $5.00/1M |
| 3 | Claude Opus 4.7 | Anthropic | 1M | $5.00/1M |
| 4 | GPT-5.6 Sol | OpenAI | 1.1M | $2.00/1M |
| 5 | Claude Opus 4.5 | Anthropic | 200K | $5.00/1M |
| 6 | GPT-5.5 Pro | OpenAI | 1.1M | $30.00/1M |
| 7 | Claude Sonnet 5 | Anthropic | 1M | $2.00/1M |
| 8 | GPT-5.5 | OpenAI | 1.1M | $5.00/1M |
| 9 | GPT-5 | OpenAI | 400K | $1.25/1M |
| 10 | GPT-5.1 | OpenAI | 400K | $1.25/1M |
Browse by category
All categories →Overall
The leading models in LMRank overall, ordered by leaderboard rank across the public benchmark mix.
Coding
The strongest models for code generation, refactoring, debugging, and multi-file edits, based on public coding benchmarks and LMRank ranking.
Budget
Models that pair strong capability with low listed input pricing. Pricing is compared at list price per million input tokens.
Open-Weight
The best open-weight models available on OpenRouter, usable for self-hosting, fine-tuning, and local evaluation.
Long Context
Models that support the largest context windows, ideal for long documents, codebases, and multi-turn workflows.
Fast
The lowest-latency variants from each provider (Flash, Turbo, Mini, and Instant models) for interactive apps.
Latest articles
View all →
Newest releases
View all models →| # | Model | Lab | Released |
|---|---|---|---|
| 01 | Hy4 | Tencent | Nov 2026 |
| 02 | Ling 3.1 Flash | InclusionAI | Oct 2026 |
| 03 | Nemotron 3.5 Super VL | NVIDIA | Oct 2026 |
| 04 | X Xing4.0 29B A4B | XingChen AGI | Oct 2026 |
| 05 | MiniMax M3.1 Flash | MiniMax | Oct 2026 |