The Gateway Charts · Week 46, 2026
Last week in AI. Who climbed. Who slipped.
Every request through the Requesty gateway names a model, a host and the app that sent it. Each week we rank them against the week before and pull out what changed, and what it means for what you build.
- 01 / Rankings28.3%deepseek-v4.1-flash pulled further ahead.
- 02 / Apps33.4%Coding agents sent a third of tokens.
- 03 / Usage67.6%Most teams used more than one model.
- 04 / Speed1.3×claude-haiku-5-5 started 1.3× sooner.
- 05 / Reliability96.1%96% of failed requests still got served.
- 06 / Caching78.1%78.1% of input came from cache.
01 Rankings
deepseek-v4.1-flash pulled further ahead.
deepseek-v4.1-flash held #1 on the Requesty gateway in week 46 (Nov 9 to 15, 2026) with 28.3% of tokens, up 2.27 points on the week before.
- Rank 1. =deepseek-v4.1-flash=DeepSeek28.3%+2.27 pts
- Rank 2. =claude-opus-5-5=Anthropic10.5%+0.28 pts
- Rank 3. =gpt-6-luna=OpenAI8.46%+0.13 pts
- Rank 4. =glm-5.3-flash=Z.ai5.42%−0.62 pts
- Rank 5. 1Up 1 from #6claude-sonnet-5-51Up 1 from #6Anthropic5.35%+0.08 pts
- Rank 6. 1Down 1 from #5gpt-6.1-sol1Down 1 from #5OpenAI5.04%−0.36 pts
- Rank 7. =deepseek-v4-flash=DeepSeek4.57%+0.31 pts
- Rank 8. =claude-haiku-5-5=Anthropic3.75%+0.25 pts
- Rank 9. 1Up 1 from #10nemotron-3-ultra-550b-a55b1Up 1 from #10NVIDIA2.40%+0.03 pts
- Rank 10. 1Up 1 from #11claude-sonnet-51Up 1 from #11Anthropic2.18%+0.17 pts
- This week
- #7 · 4.57%
- Last week
- #7 · 4.26%
- Change
- +0.31 pts
- Peak
- #1
- Weeks on chart
- 12 of 12
Data
| Rank | Last week | Name | Share | Change |
|---|---|---|---|---|
| 1 | 1 | deepseek-v4.1-flash | 28.3% | +2.27 pts |
| 2 | 2 | claude-opus-5-5 | 10.5% | +0.28 pts |
| 3 | 3 | gpt-6-luna | 8.46% | +0.13 pts |
| 4 | 4 | glm-5.3-flash | 5.42% | −0.62 pts |
| 5 | 6 | claude-sonnet-5-5 | 5.35% | +0.08 pts |
| 6 | 5 | gpt-6.1-sol | 5.04% | −0.36 pts |
| 7 | 7 | deepseek-v4-flash | 4.57% | +0.31 pts |
| 8 | 8 | claude-haiku-5-5 | 3.75% | +0.25 pts |
| 9 | 10 | nemotron-3-ultra-550b-a55b | 2.40% | +0.03 pts |
| 10 | 11 | claude-sonnet-5 | 2.18% | +0.17 pts |
01b Where the week's tokens went
DeepSeek took a third of all tokens.
DeepSeek models took 34.1% of tokens on the Requesty gateway in week 46 (Nov 9 to 15, 2026); Azure served the most of any host, 15.3%, and the OpenAI Python SDK sent the most of any app, 21.3%.
- Inference Providers
- 88%
- AI Labs
- 12%
DataShares of the week's tokens, each team capped at 2%
| OpenAI Python SDK | 21.27% |
|---|---|
| OpenCode | 13.14% |
| Vercel AI SDK | 10.06% |
| Claude Code | 9.82% |
| Pi | 6.64% |
| JS runtime fetch | 5.49% |
| Python HTTP | 3.86% |
| Anthropic SDK | 2.50% |
| OpenAI SDK (other) | 2.36% |
| DeepSeek Harness | 2.15% |
| Everything else | 22.70% |
| DeepSeek | 34.07% |
|---|---|
| Anthropic | 24.40% |
| OpenAI | 19.69% |
| Z.ai | 6.62% |
| 4.47% | |
| NVIDIA | 3.59% |
| MiniMax | 0.94% |
| Other labs | 6.23% |
| Inference Providers | 45.16% |
|---|---|
| Hyperscalers | 38.93% |
| AI Labs | 15.91% |
| Azure | 15.28% |
|---|---|
| Bedrock | 12.92% |
| Sference | 11.62% |
| DeepInfra | 8.90% |
| Melious | 7.28% |
| Vertex (Claude) | 6.60% |
| Anthropic | 4.84% |
| OpenAI | 4.41% |
| Vertex (Gemini) | 4.08% |
| DeepSeek | 4.05% |
| Other hosts | 20.03% |
02 Apps
Coding agents sent a third of tokens.
Five coding agents (OpenCode, Claude Code, Pi, DeepSeek Harness and GitHub Copilot) sent 33.4% of tokens through the Requesty gateway in week 46 (Nov 9 to 15, 2026).
- OpenAI Python SDKSDK or framework21.3%+2.16 pts
- OpenCodeCoding agent13.1%−1.00 pts
- Vercel AI SDKSDK or framework10.1%+0.77 pts
- Claude CodeCoding agent9.83%−1.65 pts
- PiCoding agent6.64%+3.11 pts
- Anthropic SDKSDK or framework2.51%−0.16 pts
- OpenAI SDK (other)SDK or framework2.36%−0.13 pts
- DeepSeek HarnessCoding agent2.15%−0.54 pts
- LiteLLMSDK or framework2.11%+0.21 pts
- GitHub CopilotCoding agent1.60%−0.33 pts
- This week
- 13.1%
- Last week
- 14.1%
- Change
- −1.00 pts
- Place in this chart
- #2 of 10
Data
| Name | This week | Last week |
|---|---|---|
| OpenAI Python SDK | 21.3% | 19.1% |
| OpenCode | 13.1% | 14.1% |
| Vercel AI SDK | 10.1% | 9.3% |
| Claude Code | 9.8% | 11.5% |
| Pi | 6.6% | 3.5% |
| Anthropic SDK | 2.5% | 2.7% |
| OpenAI SDK (other) | 2.4% | 2.5% |
| DeepSeek Harness | 2.1% | 2.7% |
| LiteLLM | 2.1% | 1.9% |
| GitHub Copilot | 1.6% | 1.9% |
02b What agents do all day
Agents call bash 2.5× as often as read.
read was the tool the most teams' models called on the Requesty gateway in week 46 (Nov 9 to 15, 2026); bash was called 2.5x as often.
- read
- write
- bash
- edit
- read_file
- grep
- glob
- web_search
- shell
- skill
- terminal
- execute_code
- write_file
- search_files
- webfetch
- skill_view
Dot on a square-root scale. Tools named by 20+ teams; MCP server tools left out.
02c A few long sessions burn most of the tokens
0.2% of sessions used 55% of tokens.
Sessions of 23 requests or more were 0.19% of sessions on the Requesty gateway in week 46 (Nov 9 to 15, 2026), but used 54.7% of tokens.
- 96.4%1 request22.6%
- 1.4%22.1%
- 1.3%3 to 55.4%
- 0.6%6 to 117.0%
- 0.2%12 to 228.1%
- 0.1%23 to 4511.9%
- 0.05%46 to 9015.0%
- 0.02%91 to 18114.0%
- <0.01%182 to 3629.4%
- <0.01%363 to 7243.7%
- <0.01%725 or more0.6%
03 Usage
Most teams used more than one model.
67.6% of active teams on the Requesty gateway used two or more models in week 46 (Nov 9 to 15, 2026); 58.6% used two or more labs and 60.2% two or more providers.
of active teams used two or more models in week 46
- Median team
- 2 models
- Loyal to one
- 32.4%
- Use 6 or more
- 18.6%
Data
| 1 | 2 | 3 | 4 to 5 | 6 or more | Two or more | |
|---|---|---|---|---|---|---|
| Models | 32.4% | 19.0% | 13.6% | 16.5% | 18.6% | 67.6% |
| Labs | 41.4% | 25.4% | 13.7% | 12.2% | 7.3% | 58.6% |
| Providers | 39.8% | 26.3% | 12.2% | 12.3% | 9.4% | 60.2% |
04 Speed
claude-haiku-5-5 started 1.3× sooner.
claude-haiku-5-5 reached its first token 1.3x sooner on the Requesty gateway in week 46 (Nov 9 to 15, 2026): a median of 1.76 s, down from 2.21 s the week before, on streaming requests.
- claude-haiku-5-52.21 s1.75 s1.3× sooner
- deepseek-v4-flash1.43 s1.14 s1.3× sooner
- deepseek-v4.1-flash972 ms834 ms1.2× sooner
- glm-5.3842 ms737 ms1.1× sooner
- leanstral-1-51.85 s1.66 s1.1× sooner
- Last week
- 2.21 s
- This week
- 1.75 s
- Change
- 1.26× sooner
- Relative
- −20% Faster
Data
| Model | Last week | This week | Change |
|---|---|---|---|
| claude-haiku-5-5 | 2.21 s | 1.75 s | 1.3× sooner |
| deepseek-v4-flash | 1.43 s | 1.14 s | 1.3× sooner |
| deepseek-v4.1-flash | 972 ms | 834 ms | 1.2× sooner |
| glm-5.3 | 842 ms | 737 ms | 1.1× sooner |
| leanstral-1-5 | 1.85 s | 1.66 s | 1.1× sooner |
04c Same weights, different metal
Same model, 4.6× apart by host.
The same model, deepseek-v4.1-flash, reached its first token 4.6x sooner on Sference (375 ms median) than on TensorX (1.71 s) on the Requesty gateway in week 46 (Nov 9 to 15, 2026).
- TTFT p25
- 238 ms
- Median
- 375 ms
- p75
- 674 ms
- p90
- 1.30 s
- p99
- 6.5 s
- Speed median
- 260 tok/s
- Provider errors
- 0.40%
- Share of this model
- 19.5%
04b Latency is a distribution
glm-5.3-flash was quickest to start.
glm-5.3-flash had the quickest median first token of the 12 busiest models on the Requesty gateway in week 46 (Nov 9 to 15, 2026), 746 ms; for deepseek-v4-flash the slowest 1% of requests waited 36x its median.
- Fastest 10%
- under 246 ms
- Median
- 746 ms
- p75
- 1.51 s
- p90
- 3.3 s
- p99
- 14 s
- p99 vs median
- 19×
05 Reliability
96% of failed requests still got served.
In week 46 (Nov 9 to 15, 2026), 96.1% of requests on a fallback policy whose first attempt hit a provider error were still served by another host on the Requesty gateway, up from 86.4% the week before.
- Fallback policy
- 96.1%
- First host failed, still served
- Latency policy
- 79.0%
- First host failed, still served
- Same model served
- 79.1%
- Of rescues, same model on another host
- Served by another host
- 96.1%
- Still failed
- 3.9%
- One dot
- 0.5% of these requests
Data
| Measure | Value |
|---|---|
| Still served | 96.1% |
| Still failed | 3.9% |
| Fallback policy | 96.1% |
| Latency policy | 79.0% |
| Same model served | 79.1% |
05b Host form
9 of 15 hosts had a clean week.
9 of the 15 busiest hosts on the Requesty gateway kept provider errors under 0.3% in week 46 (Nov 9 to 15, 2026); Bedrock had the most, 2.30%.
05c The week, hour by hour
Bedrock's worst hour: 48.9% errors.
The worst hour for any busy host on the Requesty gateway in week 46 (Nov 9 to 15, 2026) was Saturday Nov 14 at 16:00 UTC, when 48.9% of requests to Bedrock came back with a provider error.
- Provider error rate
- 48.9%
- Week average
- 2.30%
- Week before
- 0.24%
06 Caching
78.1% of input came from cache.
78.1% of input tokens through the Requesty gateway in week 46 (Nov 9 to 15, 2026) were read from a prompt cache; models read 46 input tokens for every output token.
- Input read from cache
- 78.1%
- Against the week before
- +1.0 pts
- 12-week average
- 76.2%
Data
| Week of | Input read from cache |
|---|---|
| 2026-08-24 | 81.7% |
| 2026-08-31 | 76.3% |
| 2026-09-07 | 71.9% |
| 2026-09-14 | 74.9% |
| 2026-09-21 | 73.6% |
| 2026-09-28 | 76.3% |
| 2026-10-05 | 75.3% |
| 2026-10-12 | 74.4% |
| 2026-10-19 | 77.1% |
| 2026-10-26 | 78.1% |
| 2026-11-02 | 77.1% |
| 2026-11-09 | 78.1% |
06b What a warm cache buys
A warm cache started 8.2× sooner.
On the Requesty gateway in week 46 (Nov 9 to 15, 2026), deepseek-v4.1-flash prompts over 512k tokens reached the first token 8.2x sooner when more than half of the input came from cache: 2.65 s against 22 s at the median.
- Cold median
- 22 s
- Warm median
- 2.65 s
Vital signs
How the traffic behaved
Week 46Full rankings
Models · 40Apps · 15Labs · 12Hosts · 20ShowHide
| Rank | Move | Model | Share | 12 weeks | This week | Change | Peak |
|---|---|---|---|---|---|---|---|
| 1 | = | deepseek-v4.1-flashDeepSeek | 28.3% | +2.27 pts | #1 | ||
| 2 | = | claude-opus-5-5Anthropic | 10.5% | +0.28 pts | #1 | ||
| 3 | = | gpt-6-lunaOpenAI | 8.46% | +0.13 pts | #3 | ||
| 4 | = | glm-5.3-flashZ.ai | 5.42% | −0.62 pts | #2 | ||
| 5 | 1Up 1 from #6 | claude-sonnet-5-5Anthropic | 5.35% | +0.08 pts | #5 | ||
| 6 | 1Down 1 from #5 | gpt-6.1-solOpenAI | 5.04% | −0.36 pts | #4 | ||
| 7 | = | deepseek-v4-flashDeepSeek | 4.57% | +0.31 pts | #1 | ||
| 8 | = | claude-haiku-5-5Anthropic | 3.75% | +0.25 pts | #8 | ||
| 9 | 1Up 1 from #10 | nemotron-3-ultra-550b-a55bNVIDIA | 2.40% | +0.03 pts | #9 | ||
| 10 | 1Up 1 from #11 | claude-sonnet-5Anthropic | 2.18% | +0.17 pts | #4 | ||
| 11 | 2Up 2 from #13 | gpt-6.1-terraOpenAI | 2.16% | +0.82 pts | #11 | ||
| 12 | 3Down 3 from #9 | gpt-5.6-lunaOpenAI | 2.02% | −0.37 pts | #3 | ||
| 13 | 1Up 1 from #14 | gemini-3.8-flashGoogle | 1.45% | +0.16 pts | #6 | ||
| 14 | 2Down 2 from #12 | nemotron-3.5-lightning-30b-a3bNVIDIA | 1.11% | −0.41 pts | #12 | ||
| 15 | = | glm-5.3Z.ai | 0.88% | −0.35 pts | #7 | ||
| 16 | New | gemini-4-carbonGoogle | 0.73% | +0.73 pts | #16 | ||
| 17 | = | claude-opus-5Anthropic | 0.59% | −0.14 pts | #5 | ||
| 18 | 1Up 1 from #19 | claude-sonnet-4-6Anthropic | 0.58% | +0.01 pts | #13 | ||
| 19 | 4Up 4 from #23 | minimax-m3.1-flashMiniMax | 0.56% | +0.05 pts | #12 | ||
| 20 | 4Up 4 from #24 | leanstral-1-5Mistral | 0.53% | +0.03 pts | #9 | ||
| 21 | 5Down 5 from #16 | ling-3.1-flashOther | 0.52% | −0.40 pts | #16 | ||
| 22 | = | gemini-4-argonGoogle | 0.47% | −0.04 pts | #22 | ||
| 23 | 5Down 5 from #18 | deepseek-v4-proDeepSeek | 0.43% | −0.29 pts | #5 | ||
| 24 | 3Down 3 from #21 | gpt-6-solOpenAI | 0.38% | −0.17 pts | #9 | ||
| 25 | 5Down 5 from #20 | gemini-3.5-flash-liteGoogle | 0.31% | −0.25 pts | #18 | ||
| 26 | = | gemini-3.1-flash-liteGoogle | 0.24% | −0.14 pts | #17 | ||
| 27 | 1Up 1 from #28 | gemini-2.5-flash-liteGoogle | 0.24% | −0.01 pts | #25 | ||
| 28 | 3Down 3 from #25 | kimi-k3.1-proMoonshot | 0.22% | −0.22 pts | #25 | ||
| 29 | New | gemini-4-hydrogenGoogle | 0.20% | +0.20 pts | #29 | ||
| 30 | 1Down 1 from #29 | gemini-3.7-flashGoogle | 0.19% | −0.06 pts | #8 | ||
| 31 | 1Up 1 from #32 | claude-haiku-4-5Anthropic | 0.14% | −0.07 pts | #19 | ||
| 32 | 3Up 3 from #35 | gemma-4-31b-itGoogle | 0.14% | −0.03 pts | #32 | ||
| 33 | 1Up 1 from #34 | gemini-3.1-pro-previewGoogle | 0.11% | −0.08 pts | #33 | ||
| 34 | 3Up 3 from #37 | gemini-2.5-flashGoogle | 0.10% | −0.04 pts | #32 | ||
| 35 | 3Up 3 from #38 | glm-5.2Z.ai | 0.10% | −0.01 pts | #6 | ||
| 36 | = | gpt-5.4OpenAI | 0.09% | −0.07 pts | #18 | ||
| 37 | 6Down 6 from #31 | gpt-5.6-solOpenAI | 0.09% | −0.13 pts | #2 | ||
| 38 | 5Down 5 from #33 | mistral-large-4Mistral | 0.09% | −0.11 pts | #31 | ||
| 39 | 1Up 1 from #40 | gpt-5.5OpenAI | 0.09% | 0.00 pts | #28 | ||
| 40 | 1Down 1 from #39 | gemini-3.5-flashGoogle | 0.08% | −0.02 pts | #27 |
| Rank | Move | App | Share | 12 weeks | This week | Change | Peak |
|---|---|---|---|---|---|---|---|
| 1 | = | OpenAI Python SDKSDK or framework | 21.3% | +2.16 pts | #1 | ||
| 2 | = | OpenCodeCoding agent | 13.1% | −1.00 pts | #2 | ||
| 3 | 1Up 1 from #4 | Vercel AI SDKSDK or framework | 10.1% | +0.77 pts | #3 | ||
| 4 | 1Down 1 from #3 | Claude CodeCoding agent | 9.83% | −1.65 pts | #3 | ||
| 5 | = | PiCoding agent | 6.64% | +3.11 pts | #4 | ||
| 6 | 1Up 1 from #7 | Anthropic SDKSDK or framework | 2.51% | −0.16 pts | #6 | ||
| 7 | 1Up 1 from #8 | OpenAI SDK (other)SDK or framework | 2.36% | −0.13 pts | #3 | ||
| 8 | 2Down 2 from #6 | DeepSeek HarnessCoding agent | 2.15% | −0.54 pts | #6 | ||
| 9 | 1Up 1 from #10 | LiteLLMSDK or framework | 2.11% | +0.21 pts | #9 | ||
| 10 | 1Down 1 from #9 | GitHub CopilotCoding agent | 1.60% | −0.33 pts | #6 | ||
| 11 | = | Kilo CodeCoding agent | 1.39% | +0.12 pts | #8 | ||
| 12 | 2Up 2 from #14 | Zoo CodeCoding agent | 0.27% | +0.09 pts | #11 | ||
| 13 | = | Open WebUIApp | 0.25% | −0.01 pts | #13 | ||
| 14 | 2Down 2 from #12 | LangChainSDK or framework | 0.21% | −0.09 pts | #10 | ||
| 15 | 2Up 2 from #17 | LoreBaryApp | 0.01% | 0.00 pts | #15 |
| Rank | Move | Lab | Share | 12 weeks | This week | Change | Peak |
|---|---|---|---|---|---|---|---|
| 1 | = | DeepSeek | 34.1% | +2.04 pts | #1 | ||
| 2 | = | Anthropic | 24.4% | +0.50 pts | #1 | ||
| 3 | = | OpenAI | 19.7% | −0.51 pts | #2 | ||
| 4 | = | Z.ai | 6.62% | −1.17 pts | #2 | ||
| 5 | = | 4.47% | +0.37 pts | #4 | |||
| 6 | = | NVIDIA | 3.59% | −0.39 pts | #5 | ||
| 7 | = | MiniMax | 0.94% | −0.15 pts | #7 | ||
| 8 | 1Up 1 from #9 | Mistral | 0.70% | −0.03 pts | #7 | ||
| 9 | 1Down 1 from #8 | Moonshot | 0.69% | −0.17 pts | #6 | ||
| 10 | = | Alibaba | 0.33% | +0.07 pts | #8 | ||
| 11 | Re | Xiaomi | 0.22% | −0.73 pts | #7 | ||
| 12 | 1Down 1 from #11 | xAI | 0.09% | −0.05 pts | #10 |
| Rank | Move | Host | Share | 12 weeks | This week | Change | Peak |
|---|---|---|---|---|---|---|---|
| 1 | = | Azure | 16.3% | +0.21 pts | #1 | ||
| 2 | = | Bedrock | 12.8% | +0.05 pts | #2 | ||
| 3 | = | Sference | 10.4% | −1.11 pts | #1 | ||
| 4 | 2Up 2 from #6 | Melious | 9.69% | +3.90 pts | #4 | ||
| 5 | = | DeepInfra | 7.59% | +0.05 pts | #2 | ||
| 6 | 2Down 2 from #4 | Vertex (Claude) | 7.09% | −0.68 pts | #4 | ||
| 7 | 1Up 1 from #8 | Anthropic | 4.33% | +0.18 pts | #4 | ||
| 8 | 2Up 2 from #10 | Vertex (Gemini) | 4.16% | +0.21 pts | #3 | ||
| 9 | 2Down 2 from #7 | OpenAI | 3.74% | −0.86 pts | #6 | ||
| 10 | 2Up 2 from #12 | TensorX | 3.58% | −0.03 pts | #5 | ||
| 11 | 2Down 2 from #9 | DeepSeek | 3.43% | −0.70 pts | #2 | ||
| 12 | 1Down 1 from #11 | NVIDIA | 3.06% | −0.57 pts | #8 | ||
| 13 | 3Up 3 from #16 | Fireworks | 1.12% | +0.30 pts | #11 | ||
| 14 | = | Mistral | 0.83% | −0.31 pts | #12 | ||
| 15 | = | Novita | 0.57% | −0.46 pts | #9 | ||
| 16 | 2Up 2 from #18 | Z.ai | 0.29% | −0.04 pts | #12 | ||
| 17 | 3Up 3 from #20 | Alibaba | 0.14% | −0.01 pts | #15 | ||
| 18 | Re | Xiaomi | 0.14% | −0.68 pts | #18 | ||
| 19 | Re | Inceptron | 0.11% | +0.02 pts | #19 | ||
| 20 | 1Down 1 from #19 | Moonshot | 0.10% | −0.13 pts | #17 |
Method
How we count
Week 46 covers Nov 9 to 15, 2026 (UTC), compared with Nov 2 to 8, 2026.
- 01Aggregated from the Requesty production gateway for the week (Monday to Sunday, UTC), compared with the week before and the ten weeks before that.
- 02We publish shares, rates, ranks and latency only: no volumes, no customer data, no prompt content.
- 03In the model, lab and app charts each team counts for at most 2% of a week's tokens, so one heavy team can't bend the chart.
- 04An entry is named only when at least 20 teams used it and no single team is more than 60% of it.
- 05Latency is measured at the gateway on streaming requests. It includes the host and the network, and reflects the prompts teams sent, not a controlled benchmark.
- 06Bring-your-own-key traffic, internal test traffic, synthetic load and abusive accounts are excluded.
- Source
- model share · scripts/weekly/sql/model_share.sql
- Source
- app share · scripts/weekly/sql/app_share.sql
- Source
- lab share · scripts/weekly/sql/lab_share.sql
- Source
- host share errors · scripts/weekly/sql/host_share_errors.sql
- Source
- vitals · scripts/weekly/sql/vitals.sql
- Source
- breadth · scripts/weekly/sql/breadth.sql
- Source
- request settings · scripts/weekly/sql/request_settings.sql
- Source
- speed · scripts/weekly/sql/speed.sql
- Source
- rescues · scripts/weekly/sql/rescues.sql
- Source
- flow · scripts/weekly/sql/flow.sql
- Source
- latency dist · scripts/weekly/sql/latency_dist.sql
- Source
- host race · scripts/weekly/sql/host_race.sql
- Source
- cache ttft · scripts/weekly/sql/cache_ttft.sql
- Source
- tools · scripts/weekly/sql/tools.sql
- Source
- sessions · scripts/weekly/sql/sessions.sql
- Source
- pulse · scripts/weekly/sql/pulse.sql
- Source
- host hourly · scripts/weekly/sql/host_hourly.sql
For agents
Read this week as data
- Markdown
- /data/weekly/2026-w46/data.md
- Latest
- /data/weekly/latest.json
- llms.txt
- /data/weekly/llms.txt
# Any week URL returns Markdown when asked for it
curl -H "Accept: text/markdown" \
https://www.requesty.ai/data/weekly/2026-w46Next · Week 47
