OpenRouter app · rank #76Snapshot 2026-04-27
Codex
OpenAI Codex CLI
28.1B
Tokens (30d)
254K
Requests
$167K
Monthly cost
$5.96
Blended $/M tokens
Ranks in the 30th percentile by spend and 27th by raw tokens among the top 30 apps.
Primary driver
OpenAI: GPT-5.4 is Codex's top model at 20.5B — 72.9% of total token volume and 73.4% of monthly cost ($123K).
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 | OpenAI: GPT-5.4 openai/gpt-5.4-20260305 | openai | 20.5B | 72.9% | $2.50 | $15.00 | $6.00 | $123K | 73.4% |
| 2 | OpenAI: GPT-5.3-Codex openai/gpt-5.3-codex-20260224 | openai | 5.8B | 20.8% | $1.75 | $14.00 | $5.18 | $30K | 18.1% |
| 3 | OpenAI: GPT-5.4 Pro openai/gpt-5.4-pro-20260305 | openai | 111.0M | 0.4% | $30.00 | $180.00 | $72.00 | $8K | 4.8% |
| 4 | OpenAI: GPT-5.2-Codex openai/gpt-5.2-codex-20260114 | openai | 662.2M | 2.4% | $1.75 | $14.00 | $5.18 | $3K | 2.0% |
| 5 | OpenAI: GPT-5 Codex openai/gpt-5-codex | openai | 222.0M | 0.8% | $1.25 | $10.00 | $3.70 | $821 | 0.5% |
| 6 | Anthropic: Claude Sonnet 4.6 anthropic/claude-4.6-sonnet-20260217 | anthropic | 119.1M | 0.4% | $3.00 | $15.00 | $6.36 | $757 | 0.5% |
| 7 | OpenAI: GPT-5.4 Mini openai/gpt-5.4-mini-20260317 | openai | 205.9M | 0.7% | $0.75 | $4.50 | $1.80 | $371 | 0.2% |
| 8 | OpenAI: GPT-5.2 openai/gpt-5.2-20251211 | openai | 63.4M | 0.2% | $1.75 | $14.00 | $5.18 | $328 | 0.2% |
| 9 | OpenAI: GPT-5.1-Codex-Max openai/gpt-5.1-codex-max-20251204 | openai | 44.1M | 0.2% | $1.25 | $10.00 | $3.70 | $163 | 0.1% |
| 10 | Z.ai: GLM 5.1 z-ai/glm-5.1-20260406 | z-ai | 50.7M | 0.2% | $1.05 | $3.50 | $1.74 | $88 | 0.1% |
| 11 | Xiaomi: MiMo-V2-Pro xiaomi/mimo-v2-pro-20260318 | xiaomi | 34.0M | 0.1% | $1.00 | $3.00 | $1.56 | $53 | 0.0% |
| 12 | Qwen: Qwen3.6 Plus qwen/qwen3.6-plus-preview | qwen | 60.3M | 0.2% | $0.33 | $1.95 | $0.78 | $47 | 0.0% |
| 13 | OpenAI: GPT-5 openai/gpt-5-2025-08-07 | openai | 12.5M | 0.0% | $1.25 | $10.00 | $3.70 | $46 | 0.0% |
| 14 | OpenAI: GPT-5.4 Nano openai/gpt-5.4-nano-20260317 | openai | 66.1M | 0.2% | $0.20 | $1.25 | $0.49 | $33 | 0.0% |
| 15 | MoonshotAI: Kimi K2.6 moonshotai/kimi-k2.6-20260420 | moonshotai | 17.2M | 0.1% | $0.74 | $4.66 | $1.84 | $32 | 0.0% |
| 16 | OpenAI: GPT-5.1 openai/gpt-5.1-20251113 | openai | 5.4M | 0.0% | $1.25 | $10.00 | $3.70 | $20 | 0.0% |
| 17 | MiniMax: MiniMax M2.5 minimax/minimax-m2.5-20260211 | minimax | 17.0M | 0.1% | $0.15 | $1.15 | $0.43 | $7 | 0.0% |
| 18 | OpenAI: GPT-5 Mini openai/gpt-5-mini-2025-08-07 | openai | 8.9M | 0.0% | $0.25 | $2.00 | $0.74 | $7 | 0.0% |
| 19 | OpenAI: gpt-oss-120b openai/gpt-oss-120b | openai | 7.6M | 0.0% | $0.04 | $0.19 | $0.08 | $1 | 0.0% |
| 20 | Tencent: Hy3 preview (free)FREE tencent/hy3-preview-20260421 | tencent | 40.6M | 0.1% | $0.00 | $0.00 | — | $0 | 0.0% |
Cross-references
- Full leaderboard: OpenRouter app leaderboard
- Inverted view: Which models AI agents actually use
- Related benchmarks: /agentic
- Source: openrouter.ai/apps/codex
We reply within 48 hours
Know Codex 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