Compare 2026 LLM Models
Per-token pricing, context windows, and trade-offs across the leading commercial and open-weights large language models. Updated for the 2026 frontier.
All models
| Model | Vendor | $/1M in | $/1M out | Context | Tier |
|---|---|---|---|---|---|
| Gemini 2.5 Flash | $0.07 | $0.30 | 1,000K | cheap | |
| GPT-4o mini | OpenAI | $0.15 | $0.60 | 128K | cheap |
| GPT-5 mini | OpenAI | $0.25 | $2.00 | 400K | balanced |
| Llama 3.3 70B | Meta (via Bedrock / Together / Groq) | $0.72 | $0.72 | 128K | cheap |
| Amazon Nova Pro | AWS Bedrock | $0.80 | $3.20 | 300K | balanced |
| Claude Haiku 4.5 | Anthropic | $1.00 | $5.00 | 200K | balanced |
| GPT-5 | OpenAI | $1.25 | $10.00 | 400K | premium |
| Gemini 2.5 Pro | $1.25 | $10.00 | 2,000K | premium | |
| Claude Sonnet 4.5 | Anthropic | $3.00 | $15.00 | 200K | premium |
| Claude Opus 4.7 | Anthropic | $15.00 | $75.00 | 200K | premium |
Pairwise comparisons
Claude Sonnet 4.5 vs GPT-5
Claude Sonnet 4.5 vs Gemini 2.5 Pro
GPT-5 vs Gemini 2.5 Pro
Claude Haiku 4.5 vs GPT-5 mini
Claude Haiku 4.5 vs Gemini 2.5 Flash
GPT-5 mini vs Gemini 2.5 Flash
GPT-4o mini vs Claude Haiku 4.5
GPT-4o mini vs Gemini 2.5 Flash
Llama 3.3 70B vs Gemini 2.5 Flash
Claude Opus 4.7 vs GPT-5
Amazon Nova Pro vs Claude Sonnet 4.5
Amazon Nova Pro vs GPT-5 mini
Claude Opus 4.7 vs Gemini 2.5 Pro
Llama 3.3 70B vs GPT-4o mini
Claude Haiku 4.5 vs GPT-4o mini
Pick by use case
Cheapest 1M-context model: Gemini 2.5 Flash -- $0.075 in / $0.30 out.
Best long-context recall: Claude Sonnet 4.5 (200K) or Gemini 2.5 Pro (2M).
Best price for high-output workloads: Llama 3.3 70B at $0.72/$0.72 symmetric.
Frontier reasoning: Claude Opus 4.7 or GPT-5.
If your application calls more than one of these, you don't have to commit. Inference Labs routes each request to the best model per your policy -- without code changes.
Start free → 500 credits, no card.