OpenRouter app · rank #35Snapshot 2026-04-27
Nous Research API
Nous Research is an AI research team focused on advancing open-source AI.
https://api.nousresearch.com/ →
19.9B
Tokens (30d)
1.2M
Requests
$228K
Monthly cost
$2.49
Blended $/M tokens
Ranks in the 37th percentile by spend and 17th by raw tokens among the top 30 apps.
Primary driver
Xiaomi: MiMo-V2-Pro is Nous Research API's top model at 64.2B — 323.1% of total token volume and 43.9% of monthly cost ($100K).
Top-20 model breakdown
Ranked by monthly cost. Prices from OpenRouter's live catalog. Blended $/M = price_in × 72% + price_out × 28%.
| # | Model | Vendor | Tokens | % of vol. | $/M in | $/M out | Blended $/M | Monthly cost | % of spend |
|---|---|---|---|---|---|---|---|---|---|
| 1 | Xiaomi: MiMo-V2-Pro xiaomi/mimo-v2-pro-20260318 | xiaomi | 64.2B | 323.1% | $1.00 | $3.00 | $1.56 | $100K | 43.9% |
| 2 | Anthropic: Claude Opus 4.7 anthropic/claude-4.7-opus-20260416 | anthropic | 6.2B | 31.1% | $5.00 | $25.00 | $10.60 | $65K | 28.7% |
| 3 | Anthropic: Claude Opus 4.6 anthropic/claude-4.6-opus-20260205 | anthropic | 2.4B | 12.0% | $5.00 | $25.00 | $10.60 | $25K | 11.1% |
| 4 | Google: Gemini 3.1 Pro Preview Custom Tools google/gemini-3.1-pro-preview-20260219 | 3.1B | 15.6% | $2.00 | $12.00 | $4.80 | $15K | 6.5% | |
| 5 | Xiaomi: MiMo-V2-Omni xiaomi/mimo-v2-omni-20260318 | xiaomi | 7.8B | 39.0% | $0.40 | $2.00 | $0.85 | $7K | 2.9% |
| 6 | Anthropic: Claude Sonnet 4.6 anthropic/claude-4.6-sonnet-20260217 | anthropic | 849.9M | 4.3% | $3.00 | $15.00 | $6.36 | $5K | 2.4% |
| 7 | OpenAI: GPT-5.4 openai/gpt-5.4-20260305 | openai | 382.9M | 1.9% | $2.50 | $15.00 | $6.00 | $2K | 1.0% |
| 8 | Google: Gemini 2.5 Pro google/gemini-2.5-pro | 580.1M | 2.9% | $1.25 | $10.00 | $3.70 | $2K | 0.9% | |
| 9 | Anthropic: Claude Sonnet 4.5 anthropic/claude-4.5-sonnet-20250929 | anthropic | 293.4M | 1.5% | $3.00 | $15.00 | $6.36 | $2K | 0.8% |
| 10 | Google: Gemini 3 Flash Preview google/gemini-3-flash-preview-20251217 | 650.0M | 3.3% | $0.50 | $3.00 | $1.20 | $780 | 0.3% | |
| 11 | Z.ai: GLM 5.1 z-ai/glm-5.1-20260406 | z-ai | 447.0M | 2.2% | $1.05 | $3.50 | $1.74 | $776 | 0.3% |
| 12 | MoonshotAI: Kimi K2.6 moonshotai/kimi-k2.6-20260420 | moonshotai | 295.8M | 1.5% | $0.74 | $4.66 | $1.84 | $544 | 0.2% |
| 13 | OpenAI: GPT-5.4 Mini openai/gpt-5.4-mini-20260317 | openai | 247.3M | 1.2% | $0.75 | $4.50 | $1.80 | $445 | 0.2% |
| 14 | Qwen: Qwen3.6 Plus qwen/qwen3.6-plus-04-02 | qwen | 540.5M | 2.7% | $0.33 | $1.95 | $0.78 | $422 | 0.2% |
| 15 | MiniMax: MiniMax M2.7 minimax/minimax-m2.7-20260318 | minimax | 674.5M | 3.4% | $0.30 | $1.20 | $0.55 | $372 | 0.2% |
| 16 | StepFun: Step 3.5 Flash stepfun/step-3.5-flash | stepfun | 2.0B | 10.1% | $0.10 | $0.30 | $0.16 | $312 | 0.1% |
| 17 | Z.ai: GLM 5 z-ai/glm-5-20260211 | z-ai | 170.3M | 0.9% | $0.60 | $2.08 | $1.01 | $173 | 0.1% |
| 18 | Qwen: Qwen3 Next 80B A3B Instruct qwen/qwen3-next-80b-a3b-instruct-2509 | qwen | 210.7M | 1.1% | $0.09 | $1.10 | $0.37 | $79 | 0.0% |
| 19 | Xiaomi: MiMo-V2-Flash xiaomi/mimo-v2-flash-20251210 | xiaomi | 407.4M | 2.0% | $0.09 | $0.29 | $0.15 | $59 | 0.0% |
| 20 | DeepSeek: DeepSeek V3.2 deepseek/deepseek-v3.2-20251201 | deepseek | 188.2M | 0.9% | $0.25 | $0.38 | $0.29 | $54 | 0.0% |
Cross-references
- Full leaderboard: OpenRouter app leaderboard
- Inverted view: Which models AI agents actually use
- Related benchmarks: /agentic
- Source: openrouter.ai/apps/nous-research-api
We reply within 48 hours
Know Nous Research API better than we do?
If these numbers don't match what you see from inside this app, tell us. We reply within 48 hours and update the analysis.
Tell us what you found →
✓ No newsletter✓ Real humans read this✓ 30 seconds to send