NanoGPT vs OpenRouter.
Prices checked
NanoGPT is cheaper on 62 of the 194 models both sell, the widest gap gpt-oss-120b at $0.28 against $8 per M tokens, checked .
Where to start
NanoGPTall 221 models →A pay-as-you-go router with hundreds of models and crypto payment.
Cheapest of the shared models
$0.12/M tokens
Mercury 2.5
OpenRouterall 270 models →The reference router: charges each host's own price and routes open-weight models to the cheapest healthy host, so its price for an open model is often below the maker's.
Cheapest of the shared models
8.7¢/M tokens
Mistral Nemo
Side by side
| Fact | NanoGPT | OpenRouter |
|---|---|---|
| Kind of provider | Router | Router |
| Models we track | 221 | 270 |
| Cheaper of the two | 62 of 194 | 44 of 194 |
| Trains on your prompts | does not say | does not say |
| Keeps your requests | does not say | does not say |
| How you pay | card, crypto | does not say |
| Smallest top-up | does not say | does not say |
| Free tier | none listed | none listed |
| Where it runs | does not say | does not say |
Every model both sell
194 models, most widely sold first. Per M tokens, blended 3 in : 1 out.
| Model | NanoGPT | OpenRouter |
|---|---|---|
| DeepSeek V4 FlashDeepSeek · 1M context | $0.31 5¢ in · $0.16 out | $1.29 1.2¢ in · $1.25 out |
| GLM-5.2Z.ai · 1M context | $2.58 $0.42 in · $1.32 out | $5.24 $0.28 in · $4.40 out |
| GLM-5.3-FlashZ.ai · 1M context | $0.24 7.5¢ in · 1.5¢ out | $0.95 $0.15 in · $0.50 out |
| DeepSeek V4 ProDeepSeek · 1M context | $4 $1.32 in · 4.4¢ out | $5.64 $0.48 in · $4.20 out |
| Kimi K3Moonshot AI · 1M context | $6.20 $2 in · $0.20 out | $24 $3 in · $15 out |
| GLM-5.3Z.ai · 1M context | $4.46 $1.40 in · $0.26 out | $8.60 $1.40 in · $4.40 out |
| Kimi K2.6Moonshot AI · 262k context | $4.10 $0.50 in · $2.60 out | $5.36 $0.65 in · $3.41 out |
| DeepSeek V4.1 FlashDeepSeek · 1M context | $0.91 $0.13 in · $0.52 out | $2.10 $0.30 in · $1.20 out |
| Kimi K2.7 CodeMoonshot AI · 262k context | $6.85 $0.95 in · $4 out | $5.27 $0.66 in · $3.30 out |
| GLM-5.1Z.ai · 200k context | $4.85 $0.75 in · $2.60 out | $8.60 $1.40 in · $4.40 out |
| gpt-oss-120bOpenAI · 131k context | $8 $2 in · $2 out | $0.28 3.7¢ in · $0.17 out |
| MiniMax-M3MiniMax · 1M context | $2.10 $0.30 in · $1.20 out | $2.10 $0.30 in · $1.20 out |
| Qwen3.8 27BAlibaba Cloud · 1M context | $0.49 $0.15 in · 4¢ out | $4.53 4.5¢ in · $4.40 out |
| DeepSeek V3.2DeepSeek · 164k context | $1.26 $0.28 in · $0.42 out | $1.26 $0.28 in · $0.42 out |
| Claude Sonnet 4.6Anthropic · 1M context | $24 $3 in · $15 out | $24 $3 in · $15 out |
| Claude Haiku 4.5 (latest)Anthropic · 200k context | $8 $1 in · $5 out | $8 $1 in · $5 out |
| Claude Opus 4.8Anthropic · 1M context | $40 $5 in · $25 out | $40 $5 in · $25 out |
| GLM-5Z.ai · 205k context | $4.05 $0.50 in · $2.55 out | $3.72 $0.60 in · $1.92 out |
| Claude Opus 4.7Anthropic · 1M context | $40 $5 in · $25 out | $40 $5 in · $25 out |
| GPT-5.5OpenAI · 1.1M context | $45 $5 in · $30 out | $45 $5 in · $30 out |
| Kimi K2.5Moonshot AI · 262k context | $2.80 $0.30 in · $1.90 out | $3.60 $0.45 in · $2.25 out |
| MiniMax-M2.7MiniMax · 205k context | $2.21 $0.32 in · $1.26 out | $1.47 $0.21 in · $0.84 out |
| GPT-5.4OpenAI · 1.1M context | $22.50 $2.50 in · $15 out | $22.50 $2.50 in · $15 out |
| MiniMax-M2.5MiniMax · 205k context | $2.10 $0.30 in · $1.20 out | $1.89 $0.27 in · $1.08 out |
| Llama-3.3-70B-InstructMeta · 128k context | $0.38 5¢ in · $0.23 out | $0.62 $0.10 in · $0.32 out |
| Qwen3.5 397B-A17BAlibaba Cloud · 262k context | $5.15 $0.55 in · $3.50 out | $5.15 $0.55 in · $3.50 out |
| Claude Fable 5Anthropic · 1M context | $80 $10 in · $50 out | $80 $10 in · $50 out |
| Claude Sonnet 5Anthropic · 1M context | $16 $2 in · $10 out | $16 $2 in · $10 out |
| Claude Opus 4.6Anthropic · 1M context | $40 $5 in · $25 out | $40 $5 in · $25 out |
| Gemma 4 31B ITGoogle · 262k context | $0.35 $0.10 in · 5¢ out | $0.61 9¢ in · $0.34 out |
| GPT-5.6 LunaOpenAI · 1.1M context | $1.80 $0.20 in · $1.20 out | $1.80 $0.20 in · $1.20 out |
| gpt-oss-20bOpenAI · 131k context | $0.90 $0.20 in · $0.30 out | $0.14 1.8¢ in · 9¢ out |
| Claude Opus 5Anthropic · 1M context | $40 $5 in · $25 out | $40 $5 in · $25 out |
| GPT-5.6 TerraOpenAI · 1.1M context | $18 $2 in · $12 out | $18 $2 in · $12 out |
| Claude Sonnet 4.5 (latest)Anthropic · 1M context | $24 $3 in · $15 out | $24 $3 in · $15 out |
| Gemini 3.1 Pro PreviewGoogle · 1M context | $18 $2 in · $12 out | $18 $2 in · $12 out |
| GLM-4.7Z.ai · 205k context | $1.40 $0.20 in · $0.80 out | $4 $0.60 in · $2.20 out |
| Claude Opus 4.5 (latest)Anthropic · 200k context | $40 $5 in · $25 out | $40 $5 in · $25 out |
| Gemini 3.5 FlashGoogle · 1M context | $13.50 $1.50 in · $9 out | $13.50 $1.50 in · $9 out |
| Qwen3.6 35B-A3BAlibaba Cloud · 262k context | $1.14 $0.11 in · $0.80 out | $1.45 $0.15 in · $1 out |
The 40 most widely sold of 194 · every row in the open dataset
How we count
NanoGPT is cheaper on 62 of the 194 models both sell, OpenRouter on 44, and 88 cost the same at both. Both are the same kind of provider, routers running the same models, so the price is most of what separates them.
Each price is the cheapest that provider charges for the model, per M tokens, blended 3 in : 1 out. The smaller line under it is the price in and the price out.
A free tier is a limit rather than a price, and a price below the maker's own with nothing published to account for it is left out, so neither can be marked as the cheaper of the two.
Frequently asked
- Is NanoGPT cheaper than OpenRouter?
- On the 194 models both sell, NanoGPT is cheaper on 62, OpenRouter on 44, and 88 cost the same at both. The widest gap is gpt-oss-120b: $0.28 per million tokens against $8. Prices are per M tokens, blended 3 in : 1 out, and read on 29 Sept 2026.
- Which models do NanoGPT and OpenRouter both sell?
- 194 of the models we track, led by DeepSeek V4 Flash, GLM-5.2, GLM-5.3-Flash. NanoGPT sells 221 in all and OpenRouter 270, so most of each catalog has no counterpart at the other.
- Does NanoGPT or OpenRouter train on what you send it?
- NanoGPT does not say whether it trains on what you send it, and does not say how long it keeps requests. OpenRouter does not say whether it trains on what you send it, and does not say how long it keeps requests. A provider that may train on prompts is often how a price below the maker's own is paid for.
- How current are these prices?
- Both catalogs are read every day. NanoGPT was last read 29 Sept 2026 and OpenRouter 29 Sept 2026; the whole index was refreshed 29 Sept 2026. Prices exclude tax, and a price below the maker's own with nothing published to account for it is left out of this table entirely.
Provider pages