Top pick
Claude Fable 5
Anthropic · $10.00/1M
AI coding buying guide · updated daily
Find the right AI model for coding.
One guide, three picks — top, value, and budget — chosen from live benchmarks and real prices. No lab pays for placement.
See our coding picks →Backed by 156+ models, live pricing, and public benchmarks.
Top ranked
All models →| # | Model | Pricing |
|---|---|---|
| 1 | Claude Fable 5 Anthropic | $10.00/1M |
| 2 | Claude Opus 4.8 Anthropic | $15.00/1M |
| 3 | Claude Opus 4.7 Anthropic | $15.00/1M |
| 4 | GPT-5.6 Sol OpenAI | $5.00/1M |
| 5 | Claude Opus 4.5 Anthropic | $15.00/1M |
| 6 | GPT-5.5 Pro OpenAI | $30.00/1M |
| 7 | Claude Sonnet 5 Anthropic | $2.00/1M |
| 8 | GPT-5.5 OpenAI | $12.50/1M |
| 9 | GPT-5.3 OpenAI | $11.00/1M |
| 10 | GPT-5 OpenAI | $10.00/1M |
| 11 | GPT-5.1 OpenAI | $10.00/1M |
| 12 | GPT-5.2 OpenAI | $10.00/1M |
| 13 | GPT-5.6 Terra OpenAI | $2.50/1M |
| 14 | Claude Opus 4.6 Anthropic | $5.00/1M |
| 15 | GLM 5.2 Z Ai | $1.40/1M |
| 16 | Z.ai: GLM 5.1 Z Ai | $0.98/1M |
| 17 | Claude Sonnet 4.6 Anthropic | $3.00/1M |
| 18 | DeepSeek V4 Pro preview DeepSeek | $0.44/1M |
| 19 | Qwen3.7 Max Qwen | $2.50/1M |
| 20 | GPT-5.4 OpenAI | $2.50/1M |
| 21 | GPT-5.6 Luna OpenAI | $1.00/1M |
| 22 | Qwen3.6 Max Preview Qwen | $1.04/1M |
| 23 | Z.ai: GLM 5 Z Ai | $0.60/1M |
| 24 | Claude Sonnet 4 Anthropic | $3.00/1M |
| 25 | Gemini 3.1 Pro Preview Google DeepMind | $2.00/1M |
| 26 | Qwen3 235B A22B Qwen | $0.46/1M |
| 27 | Hy3 Tencent | $0.14/1M |
| 28 | Grok 4.20 xAI | $1.25/1M |
| 29 | Deep Cogito: Cogito v2.1 671B Deepcogito | $1.25/1M |
| 30 | Llama 4 405B Meta | $0.00/1M |
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.
Cheap Model
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 Model
The lowest-latency variants from each provider — Flash, Turbo, Mini, and Instant models — for interactive apps.
Latest articles
View all →
Recent additions
View all models →| # | Model | Lab | Added |
|---|---|---|---|
| 01 | Claude Fable 5.1 | Anthropic | 2026-09-01 00:00:00 |
| 02 | Muse Spark 1.3 | Meta | 2026-09-01 00:00:00 |
| 03 | Gemini 3.8 Flash | 2026-09-01 00:00:00 | |
| 04 | Mercury 2.5 Preview | Inception | 2026-08-01 00:00:00 |
| 05 | I IBM: Granite 4.2 8B | Ibm-granite | 2026-08-01 00:00:00 |