06 Evidence & Methods
Who Runs Open Models?
Where each chart’s numbers come from, in one card per chart. The full calculations are in the files named on each card.
The charts
Who serves
- What it shows
- The share of OpenRouter’s monthly tokens served by model makers, independent hosts and the big clouds, and the largest hosts.
- Source
- OpenRouter providers page, as displayed on 9 November 2026; JetBrains Developer Ecosystem Survey 2025.
- How we calculated it
- Monthly tokens as displayed, open and closed models together, grouped by us; providers per open model from the endpoints API.
- Main limit
- The traffic one router sends; not market share; a host’s headquarters is not where it runs the model.
- Files
analysis/infra/p29/or_provider_volumes_2026_11_09.csv·analysis/infra/p29/or_models_open_2026_11_09.csv
API or capacity
- What it shows
- Three ways to run an open model, with example prices; how many hosts charge the developer’s own price.
- Source
- Providers’ price pages and OpenRouter endpoints, 9 November 2026; GPU list prices, November 2026.
- How we calculated it
- Standard list prices on each host’s own page, the developer’s price as reference; median on-demand GPU price.
- Main limit
- List prices only; discounts and committed-use prices are not public; cheaper OpenRouter endpoints often declare 4-bit precision.
- Files
analysis/infra/p29/primary_prices_focus_summary_2026_11_09.csv·analysis/infra/p29/or_models_open_2026_11_09.csv
When it pays
- What it shows
- The cost of a rented node per million output tokens against the share of the month it runs, compared with the developer’s API; the same break-even for other models.
- Source
- Providers’ price pages; SemiAnalysis InferenceX throughput measurements.
- How we calculated it
- A modelled scenario: node cost at the median on-demand price (730 hours) against the developer’s API price with three input tokens per output token; break-even utilisation = throughput needed at full use / measured throughput.
- Main limit
- Not the total cost of production: staff, storage, network, redundancy, set-up and idle peaks are not counted; measured throughput comes from agentic coding traces; no Helmcode figure is used.
- Files
analysis/infra/p29/breakeven_models_headline.csv·analysis/infra/p29/breakeven_models.csv·analysis/infra/p29/model_serving_configs.csv
Hardware and place
- What it shows
- GPU prices and memory, documented configurations, declared precision of endpoints, formats of downloaded copies, and Europe.
- Source
- Providers’ price pages; model cards and vLLM and SGLang recipes; OpenRouter endpoints (as displayed); Hugging Face hub-stats; EU providers’ price pages.
- How we calculated it
- Medians and ranges of public on-demand prices; price per GB of memory; shares of endpoints by declared precision; downloads of quantised copies by format; EU-headquartered providers’ share of the page’s tokens.
- Main limit
- Price per GB is not an inference cost; declared precision is not verified; GGUF downloads are inflated by how the Hub counts files; Vast.ai is left out; the EU share is of one router’s traffic.
- Files
analysis/infra/p29/gpu_price_summary_2026_11.csv·analysis/infra/p29/or_precision_open_2026_11_09.csv·analysis/infra/p29/quant_formats_2026_10_22.csv·analysis/infra/europe_p29/or_eu_share_summary_2026_11_09.csv
More data
Figures from the research that the chapter’s charts do not show.
- Other GPUs, median public on-demand list price per GPU and hour in November 2026: AMD MI300X $4.73, L40S $1.57. Spot capacity, which can be withdrawn at short notice, was cheaper: a median $4.90 for a B200 and $2.68 for an H100.
- The throughput behind the break-even scenario was measured on agentic coding sessions with about 127,000 input tokens and 986 output tokens per request, around 129 to one, with 84% of the input served from cache; the API price assumes three input tokens per output token. The two sides do not describe the same workload.
Sources and notes
Show the 20 notes
- 1OpenRouter, providers page (https://openrouter.ai/providers), captured 2026-11-09 (
research/editorial/extreme-edit-pass29/ch06-infra/raw/openrouter/2026-11-09/pages/providers.html, SHA-256f79bf51e…7a83), and OpenRouter endpoints API, same date. Figures used as displayed; the page gives no dates or window, and the monthly column is read as a rolling month (our inference). OpenRouter's terms reserve the materials (ch06-infra/sources.md, P1 and P2). - 2
analysis/infra/p29/or_provider_volumes_2026_11_09.csvandor_provider_volumes_summary_2026_11_09.csv: sum of monthly tokens 797.0T over 97 providers; shares 0.52 (first-party lab), 0.39 (third-party host), 0.09 (hyperscaler: Google Vertex, Claude Platform on AWS, Amazon Bedrock, Azure); hosts with ≥90% of endpoints on open or downloadable weights 0.35; top 10 third-party hosts 0.73 of third-party-host tokens. Classification (kind_our_classification) is ours. Fifteen largest bymonthly_tokens; TypeSafe gives no headquarters. Traffic routed by OpenRouter, not market share. Method:ch06-infra/scripts/parse_or_providers_page.py. - 3
analysis/infra/p29/or_models_open_2026_11_09.csvandkey_numbers.csv(or_verified_open_models_with_endpoints99,or_median_providers_per_verified_open_model2,or_verified_open_models_with_1_provider39,or_top10_open_by_tokens_median_providers17.5). "Verified open": classes OW-P/OW-N in the effective openness registry with DEC-099 suspensions. Token ranking from OpenRouterrankings-daily, 2026-10-01 to 14 (CC BY 4.0); provider counts from endpoints on 2026-11-09. Method:ch06-infra/scripts/openrouter_providers.py. - 4JetBrains Developer Ecosystem Survey 2025,
analysis/adoption/jetbrains_t2b_route_by_family.csv, family "DeepSeek (R1, V3)": website or app 70.5% (95% CI 67.3–73.8), developer's API 27.8% (24.6–31.0), weighted, base 1,267 respondents; options are not exclusive. Survey method as in the previous version of this chapter (research/editorial/editorial-rewrite/before/06-infrastructure.md). - 5
analysis/infra/p29/primary_prices_focus_summary_2026_11_09.csv, columnshare_at_developer_price(Kimi K3 0.89 of 9; GLM-5.3 0.7 of 10; DeepSeek-V4.1-Flash 0.8 of 10; Qwen3.8-27B 0.14 of 7). Standard list price on each host's own page or API, one price per host, 2026-11-09, fromch06-infra/raw/web/model_prices_primary.csv(169 rows). Method:ch06-infra/scripts/primary_prices.py. - 6
analysis/infra/p29/or_models_open_2026_11_09.csv(GLM-5.3: 34 providers, output 1.40–8.80; Kimi K3: 21, 9.50–22.50) andkey_numbers.csv(spread_models_with_5plus_priced_providers42,spread_median_max_over_min_output2.62). OpenRouter endpoints, 2026-11-09, as displayed. Not a like-for-like comparison: endpoints differ in precision, speed and tier. - 7
analysis/infra/p29/focus_prices_summary_2026_11_09.csv,cheapest_providerandcheapest_declared_precision(Kimi K3: Wafer, mxfp4; GLM-5.3: Wafer, fp4). DeepInfra promotion, DeepSeek off-peak tariff and cloud regional variants:research/editorial/extreme-edit-pass29/ch06-infra/ch06-infra.md§1e and §2a, from the providers' pages on 2026-11-09. - 8
analysis/infra/p29/gpu_price_summary_2026_11.csv,commitment= on-demand: columnsn_list_prices,min,median,max. Combines the 2026-10-26 observations used in Chapter 04 with 149 rows collected on 2026-11-09 (ch06-infra/raw/web/gpu_prices_2026_11.csv). Per GPU and hour, USD, list prices; the big clouds sell eight-GPU instances with CPU, memory and disk included. Method:ch06-infra/scripts/gpu_price_summary.py. - 9Spot medians:
gpu_price_summary_2026_11.csv,commitment= spot. Announced increases: Lambda (https://lambda.com/pricing) and Crusoe (https://www.crusoe.ai/cloud/pricing), both read on 2026-11-09 (ch06-infra/ch06-infra.md§3a); a fact about two price lists, not a market trend. Vast.ai: terms of 2026-09-01; its rows are kept out of every median (ch06-infra/sources.md, P3; columnvast_internal_only_median). - 10
analysis/infra/p29/model_serving_configs.csv(gpus,nodes,precision,hardware_basis, with the source row of each configuration inch06-infra/raw/web/models_serving_observations.csvandmodels_serving_notes.md). On B200, B300 and RTX PRO 6000 the configurations use NVFP4, a third-party conversion for every model: memory from the NVFP4 variants of the vLLM recipes (Kimi K3 1,650 GB; GLM-5.3 558 GB, within four B200s by our arithmetic; GLM-5.3-Flash 229 GB; Qwen3.5-397B-A17B 238 GB; Qwen3.8-27B 24.6 GiB) and profiles from the Nvidia NIM support matrix, a vendor source and the only one for DeepSeek-V4-Pro and DeepSeek-V4.1-Flash at NVFP4. H200 and H100 rows keep the developer's release. Parameters from the model cards. Monthly cost = GPUs × median on-demand price ingpu_price_summary_2026_11.csv× 730 hours, rounded to the nearest $100, as in the chapter's visual report (pipelines/web/ch06_2026.py,gpu_widget). B300 median from two list prices. - 11
analysis/infra/p29/breakeven_models_headline.csv(rows withapi_price= developer_api) and the full gridbreakeven_models.csv. Break-even V* = monthly node cost ÷ API price per output token including R input tokens (R = 1, 3 or 10; 3 in the headline). Node cost = GPUs × price × 730 h; B200 at the 2026-10-26 median of $8.35 (node of 8: $48,735 a month; Kimi K3's 16: $97,470). Sensitivities from the same file (gpu_pricemin, max, spot;input_per_output_R;api_price= openrouter_cheapest). Throughput never enters the calculation. Columnexcluded_costs: labour; storage; egress; load balancing; redundancy; setup engineering; model updates. Label (DEC-114): "Modelled infrastructure break-even — not observed production cost". Published under the owner's lifting of DEC-110 rule 7 (external review), 2026-11-09. Method:ch06-infra/scripts/breakeven_models.py. Break-even utilisation = throughput needed per GPU at full use / measured throughput per GPU (pipelines/web/ch06_2026.py,be_rows()): DeepSeek-V4-Pro on 8 × B200, 292.7 / 523.0 = 0.56; Qwen3.5-397B-A17B on 2 × B200, 429.3 / 627.4 = 0.68; DeepSeek-V4.1-Flash on 8 × B200, 1,103.8 / 2,799.5 = 0.39; Kimi K3 on 16 × B200, 96.6 / 56.3 (not reached); GLM-5.3-Flash on 8 × B200 FP4, 2,440.1 / 264.7 (not reached). Cost per million output tokens at full use: $48,735 / (523 × 8 × 3,600 × 730 / 10⁶) = $4.43. DeepSeek-V4-Pro developer price: input $1.32, output $3.96 per million (primary_prices_focus_summary_2026_11_09.csv), $3.96 + 3 × $1.32 = $7.92. Against the cheapest OpenRouter endpoint (3.96 for the same mix), the throughput needed is 585.4, above the 523 measured. Sensitivity for DeepSeek-V4-Pro on 8 × B200 (breakeven_models.csv, throughput needed at full use / 523): spot median 172.0 (0.33); highest on-demand price 499.5 (0.96); R = 10, 135.1 (0.26); R = 1, 439.0 (0.84). Single-turn measurement: 381.3 output tokens per second per GPU, 8 × B200, TensorRT-LLM, 8,192 input / 1,024 output tokens, at least 50 tokens per second per user (ch06-infra/raw/web/models_serving_observations.csv); 292.7 / 381.3 = 0.77 (ch06_2026.sensitivity()). - 12Needed throughput:
breakeven_models_headline.csv,needed_output_tok_s_per_gpu_at_100pctand_at_50pct. Published throughput:reported_tok_s_per_gpu,reported_conditionsandreported_sourceinmodel_serving_configs.csv, each an observation from SemiAnalysis InferenceX (https://inferencex.semianalysis.com, accessed 2026-11-09; rows ofch06-infra/raw/web/models_serving_observations.csv). GLM-5.3: the only independent row is 8 × B300 FP4 with synthetic MTP acceptance; GLM-5.3-Flash at 265 is on 8 × B200 FP4. InferenceX labels its Blackwell runs FP4 without naming the variant (NVFP4 or MXFP4), so a measured throughput is not tied to the NVFP4 conversion. Kimi K3 retired from InferenceX on 2026-11-03, DeepSeek-V4-Pro on 2026-10-29. InferenceX code is Apache-2.0; the dashboard reserves its rights; observations cited individually (sources.md, P5). No MLPerf figure is used in this comparison. Agentic traces of 85,000 to 240,000 input tokens per request (ch06-infra/ch06-infra.md§3); the 8 × B200 vLLM run behind the 523: mean input 127,081 and output 986 tokens per request, server GPU cache hit 0.84 (ch06-infra/raw/web/models_serving_observations.csv). - 13David Abitbol (Revolut), talk at AI Engineer, New York, published on YouTube by AI Engineer on 2026-10-29; automatic captions in
ch06-infra/raw/web/alt/talk_transcript_Ok6QdZHCcI8_asr.txt; notes inch06-infra/raw/web/revolut_glm_notes.md;key_numbers.csv(revolut_engineers2000,revolut_b200_gpus56,revolut_blended_usd_per_m0.3). Single primary source; press coverage (The Register, 2026-11-03) repeats the talk. Self-reported; no token volume is derived from it. - 14
analysis/infra/p29/or_precision_open_2026_11_09.csv: 595 endpoints; fp8 0.43 (token-weighted 0.49); fp4 0.18 + mxfp4 0.02 + nvfp4 0.02 + int4 0.02 = 0.24; bf16 0.08 + fp16 0.01 + fp32 <0.01 = 0.09; unknown 0.25. OpenRouter endpoints, 2026-11-09, as displayed; declared by each provider, not verified. - 15
analysis/infra/p29/quant_formats_2026_10_22.csv(share_of_downloads: GGUF 0.55, MLX 0.11, AWQ 0.10, NVFP4/FP4 0.08, FP8 0.07) andkey_numbers.csv(hub_quant_bits_*: 4 bit 0.28, 8 bit 0.10, multiple in one repo 0.52). Population: 103,023 repositories declaring a "quantized" relation to a model on the ATOM list, 313.1 million 30-day downloads, Hugging Face hub-stats read on 2026-10-22. Format classified from the repository name; sensitivity without the largest repositories inquant_formats_sensitivity_2026_10_22.csv. Counting difference:ch06-infra/ch06-infra.md§4a. Method:ch06-infra/scripts/quant_formats.py. - 16Moonshot AI, K2 Vendor Verifier, 2025-11-15, as summarised in
ch06-infra/ch06-infra.md§4d. - 17
research/editorial/extreme-edit-pass29/europe/data/eu_focus_price_summary_2026_11_09.csv(alsoanalysis/infra/europe_p29/), columneu_median_over_first_party: GLM-5.3 1.06×, DeepSeek V4.1 Flash 1.06×, Kimi K3 1.0×, Qwen3.8-27B 0.98×, GLM-5.3-Flash 1.41×. Providers headquartered in the EU/EEA with a declared European location for the model (eu_providers_catalog_2026_11_09.csv, 68 rows); output price plus three times input, USD per million, VAT excluded, euros at the ECB rate of 2026-11-06 (1 € = $1.12, our conversion). Helmcode not included. Method:europe/scripts/eu_price_comparison.py. - 18
analysis/infra/europe_p29/eu_gpu_compare_2026_11_09.csv: H100 6 European list prices, median $3.76, against $4.46 (18); H200 4, median $5.93, against $6.15 (10). Per GPU and hour, on demand; euro prices converted at the ECB rate of 2026-11-06. Method:europe/scripts/eu_gpu_compare.py. - 19
analysis/infra/europe_p29/or_eu_share_summary_2026_11_09.csv: EU/EEA-headquartered providers (Mistral, Nebius, Inceptron, NextBit) 0.01 of all displayed tokens; EU hosts 0.01 of third-party-host tokens (Inceptron reclassified as a host). Headquarters as displayed by OpenRouter (note 1).europe/data/mistral_shares.csv:hf_tracked_downloads_share_mistralai0.02 (30-day counter to 2026-10-01, rank 8; Mistral is the only developer with region "eu" on the tracked list); OpenRouterrankings-dailytop-50 share 0.04 (2025-01) and <0.01 (2026-09), CC BY 4.0. - 20Mistral model pages ("served without Mistral modifications"), and provider pages and regions, 2026-11-09:
europe/europe.md§0 and §2a–2b;europe/data/nebius_catalog_regions_2026_11_09.csv(31 models: 10 eu-north1, 1 eu-west2, 3 uk-south1, 17 in US regions). Residency and sovereignty statements quoted as the providers' own. Revolut's headquarters and location statement:ch06-infra/raw/web/revolut_glm_notes.md.