OpenRouter models,
ranked by real agent usage.
Direct answer: OpenRouter is a model router and catalog. This page ranks OpenRouter models by app adoption, token volume, estimated spend, and top-1 usage so you can choose by coding, price, context length, latency, or breadth instead of reading a flat provider list.
One number explains the whole market.
Of every dollar agents spend on inference, this is who collects it. The top three vendors take more than the rest combined — that's the entire story before any leaderboard.
One market, four different leaders.
The same 30-day window produces four different #1s depending on what you measure. Dollars, tokens, breadth of adoption, and depth of adoption disagree — that disagreement is the story.
- Most dollarsAnthropic: Claude Opus 4.6$22.58M/month across 22 apps. Premium pricing compounds even at modest volume.
- Most tokensXiaomi: MiMo-V2-Pro4.92T through 15 apps. High-volume cheap models absorb the long tail.
- Most adoptedQwen: Qwen3.6 PlusShows up in 28 of 30 apps. “Everyone tries it at least a little” is not the same as “anyone uses it primarily”.
- Most #1 slotsXiaomi: MiMo-V2-ProThe top model in 4 of 30 apps. The closest proxy for what agents actually lean on when it matters.
Rolled up by vendor.
Same data, one level coarser. Every model per vendor, summed into one row. Blended $/M is vendor-weighted by real usage, so premium vendors show their true price per token.
| # | Vendor | Models | Apps | Tokens | Monthly cost | Avg $/M | #1 slots |
|---|---|---|---|---|---|---|---|
| 1 | anthropic | 11 | 26 | 6.34T | $50.42M | $7.95 | 7 |
| 2 | xiaomi | 3 | 17 | 5.39T | $7.93M | $1.47 | 4 |
| 3 | openai | 19 | 23 | 900.1B | $4.72M | $5.25 | 2 |
| 4 | z-ai | 6 | 21 | 2.03T | $3.70M | $1.82 | 0 |
| 5 | qwen | 13 | 22 | 3.32T | $2.57M | $0.77 | 4 |
| 6 | minimax | 2 | 18 | 4.92T | $2.35M | $0.48 | 3 |
| 7 | 13 | 28 | 2.10T | $2.35M | $1.12 | 4 | |
| 8 | moonshotai | 2 | 19 | 576.0B | $661K | $1.15 | 1 |
| 9 | deepseek | 8 | 20 | 1.50T | $448K | $0.30 | 4 |
| 10 | stepfun | 1 | 15 | 2.73T | $426K | $0.16 | 0 |
| 11 | nvidia | 1 | 12 | 1.43T | $274K | $0.19 | 0 |
| 12 | arcee-ai | 2 | 7 | 412.3B | $105K | $0.26 | 0 |
| 13 | x-ai | 4 | 7 | 75.6B | $42K | $0.55 | 0 |
| 14 | amazon | 1 | 1 | 19.6B | $18K | $0.92 | 0 |
| 15 | mistralai | 2 | 1 | 184.8B | $5K | $0.03 | 1 |
| 16 | aion-labs | 1 | 1 | 576.4M | $590 | $1.02 | 0 |
| 17 | sao10k | 2 | 1 | 9.4B | $578 | $0.06 | 0 |
| 18 | microsoft | 1 | 1 | 884.4M | $548 | $0.62 | 0 |
| 19 | kwaipilot | 1 | 1 | 517.1M | $285 | $0.55 | 0 |
| 20 | anthracite-org | 1 | 1 | 41.9M | $149 | $3.56 | 0 |
| 21 | thedrummer | 2 | 1 | 204.2M | $75 | $0.37 | 0 |
| 22 | nousresearch | 2 | 1 | 150.7M | $30 | $0.20 | 0 |
| 23 | gryphe | 1 | 1 | 34.7M | $2 | $0.06 | 0 |
| 24 | openrouter | 1 | 8 | 431.2B | $0 | — | 0 |
| 25 | inclusionai | 2 | 2 | 312.9B | $0 | — | 0 |
| 26 | tencent | 1 | 4 | 65.0B | $0 | — | 0 |
Where every vendor actually sits.
Monthly spend vs token volume, one bubble per vendor. Bubble size scales with apps using that vendor. The diagonal is even pricing — anything above charges more per token than the cluster, anything below charges less.
Top 30 by monthly cost.
Where the dollars actually go. Summed across every app that uses each model.
| # | Model | Vendor | $/M in | $/M out | Tokens | Monthly | Apps | #1 | Top-3 |
|---|---|---|---|---|---|---|---|---|---|
| 1 | Anthropic: Claude Opus 4.6 | anthropic | $5.00 | $25.00 | 2.13T | $22.58M | 22 | 3 | 9 |
| 2 | Anthropic: Claude Sonnet 4.6 | anthropic | $3.00 | $15.00 | 3.09T | $19.65M | 23 | 3 | 10 |
| 3 | Xiaomi: MiMo-V2-Pro | xiaomi | $1.00 | $3.00 | 4.92T | $7.68M | 15 | 4 | 5 |
| 4 | Anthropic: Claude Opus 4.7 | anthropic | $5.00 | $25.00 | 510.0B | $5.41M | 13 | 0 | 2 |
| 5 | OpenAI: GPT-5.4 | openai | $2.50 | $15.00 | 520.4B | $3.12M | 15 | 1 | 3 |
| 6 | Z.ai: GLM 5 Turbo | z-ai | $1.20 | $4.00 | 1.56T | $3.09M | 3 | 0 | 1 |
| 7 | Qwen: Qwen3.6 Plus | qwen | $0.33 | $1.95 | 3.25T | $2.53M | 28 | 3 | 8 |
| 8 | Anthropic: Claude Sonnet 4.5 | anthropic | $3.00 | $15.00 | 267.7B | $1.70M | 15 | 1 | 3 |
| 9 | OpenAI: GPT-5.3-Codex | openai | $1.75 | $14.00 | 276.8B | $1.43M | 9 | 1 | 2 |
| 10 | MiniMax: MiniMax M2.5 | minimax | $0.15 | $1.15 | 3.02T | $1.30M | 12 | 3 | 3 |
| 11 | Google: Gemini 3 Flash Preview | $0.50 | $3.00 | 891.1B | $1.07M | 20 | 3 | 4 | |
| 12 | MiniMax: MiniMax M2.7 | minimax | $0.30 | $1.20 | 1.91T | $1.05M | 17 | 0 | 3 |
| 13 | Google: Gemini 3.1 Pro Preview Custom Tools | $2.00 | $12.00 | 141.5B | $679K | 19 | 0 | 2 | |
| 14 | Anthropic: Claude Haiku 4.5 | anthropic | $1.00 | $5.00 | 306.0B | $649K | 9 | 0 | 1 |
| 15 | Z.ai: GLM 5.1 | z-ai | $1.05 | $3.50 | 255.9B | $444K | 17 | 0 | 2 |
| 16 | StepFun: Step 3.5 Flash | stepfun | $0.10 | $0.30 | 2.73T | $426K | 15 | 0 | 3 |
| 17 | Anthropic: Claude Opus 4.5 | anthropic | $5.00 | $25.00 | 37.5B | $397K | 6 | 0 | 1 |
| 18 | MoonshotAI: Kimi K2.5 | moonshotai | $0.44 | $2.00 | 413.8B | $363K | 14 | 0 | 0 |
| 19 | DeepSeek: DeepSeek V3.2 | deepseek | $0.25 | $0.38 | 1.23T | $355K | 20 | 4 | 5 |
| 20 | MoonshotAI: Kimi K2.6 | moonshotai | $0.74 | $4.66 | 162.2B | $298K | 11 | 1 | 1 |
| 21 | Google: Gemini 2.5 Flash | $0.30 | $2.50 | 318.9B | $292K | 9 | 1 | 2 | |
| 22 | NVIDIA: Nemotron 3 Super | nvidia | $0.09 | $0.45 | 1.43T | $274K | 12 | 0 | 0 |
| 23 | Xiaomi: MiMo-V2-Omni | xiaomi | $0.40 | $2.00 | 257.2B | $218K | 2 | 0 | 1 |
| 24 | Google: Gemini 2.5 Pro | $1.25 | $10.00 | 43.4B | $161K | 7 | 0 | 0 | |
| 25 | Google: Gemini 2.5 Flash Lite | $0.10 | $0.40 | 643.7B | $118K | 6 | 0 | 2 | |
| 26 | Z.ai: GLM 5 | z-ai | $0.60 | $2.08 | 115.1B | $117K | 11 | 0 | 1 |
| 27 | Arcee AI: Trinity Large Preview | arcee-ai | $0.15 | $0.45 | 356.9B | $84K | 6 | 0 | 0 |
| 28 | OpenAI: GPT-5.4 Mini | openai | $0.75 | $4.50 | 40.6B | $73K | 5 | 0 | 0 |
| 29 | OpenAI: GPT-5.5 | openai | $5.00 | $30.00 | 2.9B | $35K | 3 | 0 | 0 |
| 30 | Xiaomi: MiMo-V2-Flash | xiaomi | $0.09 | $0.29 | 214.2B | $31K | 4 | 0 | 0 |
Top 30 by raw token volume.
How much work each model carries. Cheap models lead here.
| # | Model | Vendor | $/M in | $/M out | Tokens | Monthly | Apps | #1 | Top-3 |
|---|---|---|---|---|---|---|---|---|---|
| 1 | Xiaomi: MiMo-V2-Pro | xiaomi | $1.00 | $3.00 | 4.92T | $7.68M | 15 | 4 | 5 |
| 2 | Qwen: Qwen3.6 Plus | qwen | $0.33 | $1.95 | 3.25T | $2.53M | 28 | 3 | 8 |
| 3 | Anthropic: Claude Sonnet 4.6 | anthropic | $3.00 | $15.00 | 3.09T | $19.65M | 23 | 3 | 10 |
| 4 | MiniMax: MiniMax M2.5 | minimax | $0.15 | $1.15 | 3.02T | $1.30M | 12 | 3 | 3 |
| 5 | StepFun: Step 3.5 Flash | stepfun | $0.10 | $0.30 | 2.73T | $426K | 15 | 0 | 3 |
| 6 | Anthropic: Claude Opus 4.6 | anthropic | $5.00 | $25.00 | 2.13T | $22.58M | 22 | 3 | 9 |
| 7 | MiniMax: MiniMax M2.7 | minimax | $0.30 | $1.20 | 1.91T | $1.05M | 17 | 0 | 3 |
| 8 | Z.ai: GLM 5 Turbo | z-ai | $1.20 | $4.00 | 1.56T | $3.09M | 3 | 0 | 1 |
| 9 | NVIDIA: Nemotron 3 Super | nvidia | $0.09 | $0.45 | 1.43T | $274K | 12 | 0 | 0 |
| 10 | DeepSeek: DeepSeek V3.2 | deepseek | $0.25 | $0.38 | 1.23T | $355K | 20 | 4 | 5 |
| 11 | Google: Gemini 3 Flash Preview | $0.50 | $3.00 | 891.1B | $1.07M | 20 | 3 | 4 | |
| 12 | Google: Gemini 2.5 Flash Lite | $0.10 | $0.40 | 643.7B | $118K | 6 | 0 | 2 | |
| 13 | OpenAI: GPT-5.4 | openai | $2.50 | $15.00 | 520.4B | $3.12M | 15 | 1 | 3 |
| 14 | Anthropic: Claude Opus 4.7 | anthropic | $5.00 | $25.00 | 510.0B | $5.41M | 13 | 0 | 2 |
| 15 | openrouter/elephant-alpha | openrouter | — | — | 431.2B | $0 | 8 | 0 | 0 |
| 16 | MoonshotAI: Kimi K2.5 | moonshotai | $0.44 | $2.00 | 413.8B | $363K | 14 | 0 | 0 |
| 17 | Arcee AI: Trinity Large Preview | arcee-ai | $0.15 | $0.45 | 356.9B | $84K | 6 | 0 | 0 |
| 18 | Google: Gemini 2.5 Flash | $0.30 | $2.50 | 318.9B | $292K | 9 | 1 | 2 | |
| 19 | Anthropic: Claude Haiku 4.5 | anthropic | $1.00 | $5.00 | 306.0B | $649K | 9 | 0 | 1 |
| 20 | OpenAI: GPT-5.3-Codex | openai | $1.75 | $14.00 | 276.8B | $1.43M | 9 | 1 | 2 |
| 21 | Anthropic: Claude Sonnet 4.5 | anthropic | $3.00 | $15.00 | 267.7B | $1.70M | 15 | 1 | 3 |
| 22 | Xiaomi: MiMo-V2-Omni | xiaomi | $0.40 | $2.00 | 257.2B | $218K | 2 | 0 | 1 |
| 23 | Z.ai: GLM 5.1 | z-ai | $1.05 | $3.50 | 255.9B | $444K | 17 | 0 | 2 |
| 24 | inclusionAI: Ling-2.6-1T (free)Free | inclusionai | $0.00 | $0.00 | 231.3B | $0 | 2 | 0 | 0 |
| 25 | Xiaomi: MiMo-V2-Flash | xiaomi | $0.09 | $0.29 | 214.2B | $31K | 4 | 0 | 0 |
| 26 | Mistral: Mistral Nemo | mistralai | $0.02 | $0.04 | 184.6B | $5K | 1 | 1 | 1 |
| 27 | MoonshotAI: Kimi K2.6 | moonshotai | $0.74 | $4.66 | 162.2B | $298K | 11 | 1 | 1 |
| 28 | Google: Gemini 3.1 Pro Preview Custom Tools | $2.00 | $12.00 | 141.5B | $679K | 19 | 0 | 2 | |
| 29 | Z.ai: GLM 5 | z-ai | $0.60 | $2.08 | 115.1B | $117K | 11 | 0 | 1 |
| 30 | DeepSeek: DeepSeek V3 0324 | deepseek | $0.20 | $0.77 | 86.8B | $31K | 3 | 0 | 2 |
Top 30 by number of apps using it.
Breadth of adoption — models that appear in the top-20 mix of the most apps.
| # | Model | Vendor | $/M in | $/M out | Tokens | Monthly | Apps | #1 | Top-3 |
|---|---|---|---|---|---|---|---|---|---|
| 1 | Qwen: Qwen3.6 Plus | qwen | $0.33 | $1.95 | 3.25T | $2.53M | 28 | 3 | 8 |
| 2 | Anthropic: Claude Sonnet 4.6 | anthropic | $3.00 | $15.00 | 3.09T | $19.65M | 23 | 3 | 10 |
| 3 | Anthropic: Claude Opus 4.6 | anthropic | $5.00 | $25.00 | 2.13T | $22.58M | 22 | 3 | 9 |
| 4 | DeepSeek: DeepSeek V3.2 | deepseek | $0.25 | $0.38 | 1.23T | $355K | 20 | 4 | 5 |
| 5 | Google: Gemini 3 Flash Preview | $0.50 | $3.00 | 891.1B | $1.07M | 20 | 3 | 4 | |
| 6 | Google: Gemini 3.1 Pro Preview Custom Tools | $2.00 | $12.00 | 141.5B | $679K | 19 | 0 | 2 | |
| 7 | MiniMax: MiniMax M2.7 | minimax | $0.30 | $1.20 | 1.91T | $1.05M | 17 | 0 | 3 |
| 8 | Z.ai: GLM 5.1 | z-ai | $1.05 | $3.50 | 255.9B | $444K | 17 | 0 | 2 |
| 9 | Xiaomi: MiMo-V2-Pro | xiaomi | $1.00 | $3.00 | 4.92T | $7.68M | 15 | 4 | 5 |
| 10 | StepFun: Step 3.5 Flash | stepfun | $0.10 | $0.30 | 2.73T | $426K | 15 | 0 | 3 |
| 11 | OpenAI: GPT-5.4 | openai | $2.50 | $15.00 | 520.4B | $3.12M | 15 | 1 | 3 |
| 12 | Anthropic: Claude Sonnet 4.5 | anthropic | $3.00 | $15.00 | 267.7B | $1.70M | 15 | 1 | 3 |
| 13 | MoonshotAI: Kimi K2.5 | moonshotai | $0.44 | $2.00 | 413.8B | $363K | 14 | 0 | 0 |
| 14 | Anthropic: Claude Opus 4.7 | anthropic | $5.00 | $25.00 | 510.0B | $5.41M | 13 | 0 | 2 |
| 15 | MiniMax: MiniMax M2.5 | minimax | $0.15 | $1.15 | 3.02T | $1.30M | 12 | 3 | 3 |
| 16 | NVIDIA: Nemotron 3 Super | nvidia | $0.09 | $0.45 | 1.43T | $274K | 12 | 0 | 0 |
| 17 | MoonshotAI: Kimi K2.6 | moonshotai | $0.74 | $4.66 | 162.2B | $298K | 11 | 1 | 1 |
| 18 | Z.ai: GLM 5 | z-ai | $0.60 | $2.08 | 115.1B | $117K | 11 | 0 | 1 |
| 19 | Google: Gemini 2.5 Flash | $0.30 | $2.50 | 318.9B | $292K | 9 | 1 | 2 | |
| 20 | Anthropic: Claude Haiku 4.5 | anthropic | $1.00 | $5.00 | 306.0B | $649K | 9 | 0 | 1 |
| 21 | OpenAI: GPT-5.3-Codex | openai | $1.75 | $14.00 | 276.8B | $1.43M | 9 | 1 | 2 |
| 22 | openrouter/elephant-alpha | openrouter | — | — | 431.2B | $0 | 8 | 0 | 0 |
| 23 | Google: Gemini 2.5 Pro | $1.25 | $10.00 | 43.4B | $161K | 7 | 0 | 0 | |
| 24 | Google: Gemini 3.1 Flash Lite Preview | $0.25 | $1.50 | 39.1B | $23K | 7 | 0 | 1 | |
| 25 | Google: Gemini 2.5 Flash Lite | $0.10 | $0.40 | 643.7B | $118K | 6 | 0 | 2 | |
| 26 | Arcee AI: Trinity Large Preview | arcee-ai | $0.15 | $0.45 | 356.9B | $84K | 6 | 0 | 0 |
| 27 | xAI: Grok 4.1 Fast | x-ai | $0.20 | $0.50 | 57.7B | $16K | 6 | 0 | 0 |
| 28 | Anthropic: Claude Opus 4.5 | anthropic | $5.00 | $25.00 | 37.5B | $397K | 6 | 0 | 1 |
| 29 | OpenAI: GPT-5.4 Mini | openai | $0.75 | $4.50 | 40.6B | $73K | 5 | 0 | 0 |
| 30 | Xiaomi: MiMo-V2-Flash | xiaomi | $0.09 | $0.29 | 214.2B | $31K | 4 | 0 | 0 |
Models that rank #1 in an app's mix (14 models).
Strongest 'primary driver' signal. Being #1 in even one app beats showing up in a long tail.
| # | Model | Vendor | $/M in | $/M out | Tokens | Monthly | Apps | #1 | Top-3 |
|---|---|---|---|---|---|---|---|---|---|
| 1 | Xiaomi: MiMo-V2-Pro | xiaomi | $1.00 | $3.00 | 4.92T | $7.68M | 15 | 4 | 5 |
| 2 | DeepSeek: DeepSeek V3.2 | deepseek | $0.25 | $0.38 | 1.23T | $355K | 20 | 4 | 5 |
| 3 | Qwen: Qwen3.6 Plus | qwen | $0.33 | $1.95 | 3.25T | $2.53M | 28 | 3 | 8 |
| 4 | Anthropic: Claude Sonnet 4.6 | anthropic | $3.00 | $15.00 | 3.09T | $19.65M | 23 | 3 | 10 |
| 5 | MiniMax: MiniMax M2.5 | minimax | $0.15 | $1.15 | 3.02T | $1.30M | 12 | 3 | 3 |
| 6 | Anthropic: Claude Opus 4.6 | anthropic | $5.00 | $25.00 | 2.13T | $22.58M | 22 | 3 | 9 |
| 7 | Google: Gemini 3 Flash Preview | $0.50 | $3.00 | 891.1B | $1.07M | 20 | 3 | 4 | |
| 8 | OpenAI: GPT-5.4 | openai | $2.50 | $15.00 | 520.4B | $3.12M | 15 | 1 | 3 |
| 9 | Google: Gemini 2.5 Flash | $0.30 | $2.50 | 318.9B | $292K | 9 | 1 | 2 | |
| 10 | OpenAI: GPT-5.3-Codex | openai | $1.75 | $14.00 | 276.8B | $1.43M | 9 | 1 | 2 |
| 11 | Anthropic: Claude Sonnet 4.5 | anthropic | $3.00 | $15.00 | 267.7B | $1.70M | 15 | 1 | 3 |
| 12 | Mistral: Mistral Nemo | mistralai | $0.02 | $0.04 | 184.6B | $5K | 1 | 1 | 1 |
| 13 | MoonshotAI: Kimi K2.6 | moonshotai | $0.74 | $4.66 | 162.2B | $298K | 11 | 1 | 1 |
| 14 | Qwen: Qwen3 235B A22B | qwen | $0.46 | $1.82 | 15.1B | $13K | 1 | 1 | 1 |
How the inverted view is built.
Data source, matching rules, and known limitations — in the open.
- App leaderboard, inverted.Built by inverting the app leaderboard JSON — for every (app, model) pair in the top-20 slice, aggregate by model.
- Permaslug matching.Permaslugs with date suffixes (e.g.
anthropic/claude-4.6-opus-20260205) are matched back to the base catalog ID via vendor-scoped token-bag overlap, so dollar totals are not missed. - What '#1 in N apps' means.The model holds the top token slot for that app's 30-day window. It does not mean the model is objectively best — just that this particular app routes the most tokens to it.
- Free and stealth lanes.Free models contribute to token and adoption rankings but $0 to spend. Stealth / alpha lanes without listed pricing are counted in adoption but not dollars.
- Regenerate locally.
npx tsx scripts/fetch-openrouter-apps.ts— fetches fresh data and rebuilds the index.
What to read next.
- /agenticAgentic · indexThe overview of the agentic section — benchmarks, market data, comparison pages.
- /agentic/openrouter-appsOpenRouter appsThe opposite slice: per-app leaderboard ranked by 30-day spend and token volume.
- /agentic/openrouter-trendsOpenRouter trendsA year of weekly token data — who gained share, who lost it, and at what price.
- /agentic/openrouter-categoriesOpenRouter categoriesThe same data rolled up by app category: coding, agents, productivity, roleplay.
- /llmLLM · benchmarksQuality leaderboards for the same models, scored against public test splits.
- /methodologyMethodologyWhat Codesota requires from a benchmark, a result, and a verification.
Model getting ignored?
Think a model deserves a closer look or isn't priced correctly? Tell us and we'll re-run the match against our catalog.