LIVE
OPUS 4.7$15 / $75per Mtok
SONNET 4.6$3 / $15per Mtok
GPT-5.5$10 / $30per Mtok
GEMINI 3.1$3.50 / $10.50per Mtok
SWE-BENCHleader Claude Opus 4.772.1%
MMLU-PROleader Opus 4.788.4
VALS FINANCEleader Opus 4.764.4%
AFTAv1.0 whitepaper live at /whitepaper
OPUS 4.7$15 / $75per Mtok
SONNET 4.6$3 / $15per Mtok
GPT-5.5$10 / $30per Mtok
GEMINI 3.1$3.50 / $10.50per Mtok
SWE-BENCHleader Claude Opus 4.772.1%
MMLU-PROleader Opus 4.788.4
VALS FINANCEleader Opus 4.764.4%
AFTAv1.0 whitepaper live at /whitepaper
All systems operational0 AI providers monitored, polled every 2 minutes
Live status

API reference

Per-endpoint reference pages with input parameters, response schemas, code samples in curl / Python / TypeScript, MCP tool names, and endpoint-specific FAQs. The full machine-readable spec is at /openapi.json.

Two ways to consume the API

Free endpoints return open AI ecosystem data and require no auth. Premium endpoints are pay-per-call in USDC on Base, gated by a bearer token from /developers/agent-payments. MCP tools wrap both tiers for Claude Desktop / Code consumption (see /glossary/mcp).

News

Service status

Models, benchmarks, comparison

Models

Free
GET /api/models

TensorFeed /api/models returns AI model pricing, context windows, capabilities, and tiers across all major providers. Updated daily. Free, no auth.

Benchmarks

Free
GET /api/benchmarks

TensorFeed /api/benchmarks returns AI model benchmark scores: SWE-bench, MMLU-Pro, HumanEval, GPQA, MATH. Updated weekly. Free, no auth.

Harnesses

Free
GET /api/harnesses

TensorFeed /api/harnesses returns a cross-harness benchmark leaderboard: Claude Code, Cursor, Codex CLI, Aider, OpenHands, Devin, Cline, Windsurf, Amp on SWE-bench Verified, Terminal-Bench, Aider Polyglot, SWE-Lancer.

Multimodal Models

Free
GET /api/multimodal

TensorFeed /api/multimodal returns image generation, video generation, TTS, and STT models with pricing in modality-native units. Sora, Veo, FLUX, ElevenLabs, Whisper, Deepgram. Free.

Embedding Models

Free
GET /api/embeddings

TensorFeed /api/embeddings returns the catalog of production embedding and reranker models: OpenAI, Voyage, Cohere, Google, Mistral, Jina, Nomic, Mixedbread, BAAI. Pricing, dimensions, MTEB. Free.

Inference Provider Matrix

Free
GET /api/inference-providers

TensorFeed /api/inference-providers returns the cross-provider pricing matrix for open-weight models. Llama 4, DeepSeek V4, Mixtral, Qwen across Together, Fireworks, Groq, DeepInfra, OpenRouter, Replicate. Free.

Inference Cheapest

Free
GET /api/inference-providers/cheapest

TensorFeed /api/inference-providers/cheapest returns the top 3 cheapest hosted inference offers for one open-weight model. Sort by blended, input, output, or output TPS. Free.

Compare Models

1 credit
GET /api/premium/compare/models

TensorFeed /api/premium/compare/models compares 2-5 AI models side-by-side with normalized benchmarks, pricing, status, and rankings. 1 credit per call.

Cost Projection

1 credit
GET /api/premium/cost/projection

TensorFeed /api/premium/cost/projection projects a token-usage workload across 1-10 models with daily/weekly/monthly/yearly totals and cheapest-monthly ranking. 1 credit.

Premium LLM-Ready OpenRouter Model

1 credit
GET /api/premium/clean/openrouter/{model_id}

TensorFeed /api/premium/clean/openrouter/{model_id} returns one model from the 367-entry OpenRouter catalog as an LLM-ready fact card. Pricing per million tokens, capability flags, ~99.8% token reduction. 1 credit.

Premium PyPI Packages Momentum

1 credit
GET /api/premium/packages/pypi/momentum

TensorFeed /api/premium/packages/pypi/momentum returns weekly AI/ML PyPI download momentum with derived velocity ratios.

Routing recommendations

History series and snapshots

Attention History (Index)

Free
GET /api/attention/history

TensorFeed /api/attention/history returns the list of dates that have a captured AI Attention Index snapshot. Pair with /api/attention/history/{date} to read one day. Free.

Premium Attention Series

1 credit
GET /api/premium/attention/series

TensorFeed /api/premium/attention/series returns daily AI Attention Index per provider over a requested date range, with first/last/delta/min/max/avg summary. 1 credit per call.

Pricing Series

1 credit
GET /api/premium/history/pricing/series

TensorFeed /api/premium/history/pricing/series returns daily input/output/blended price points for one model with min/max/delta summary. 1 credit. Up to 90 days back.

Benchmark Series

1 credit
GET /api/premium/history/benchmarks/series

TensorFeed /api/premium/history/benchmarks/series returns score evolution for one benchmark on one model with delta in percentage points. 1 credit. 90 days max.

Uptime Rollup

1 credit
GET /api/premium/history/status/uptime

TensorFeed /api/premium/history/status/uptime returns operational/degraded/down day counts and uptime % for a provider over up to 90 days. 1 credit per call.

Premium News Clusters (Full)

1 credit
GET /api/premium/history/news/clusters/full

TensorFeed /api/premium/history/news/clusters/full returns the full untruncated cross-source story cluster set for a date or 30-day range.

Premium News Full

1 credit
GET /api/premium/history/news/full

TensorFeed /api/premium/history/news/full returns the full untruncated daily news snapshot for one date or a 30-day range.

Premium News Source Health

1 credit
GET /api/premium/history/news/source-health

TensorFeed /api/premium/history/news/source-health returns per-source RSS poll reliability series across a date range, max 90 days.

Security: CVE, KEV, EPSS, verified

Macro economic digest

Climate + meteorological data

AI policy timeline

Research velocity + papers

Agents directory and provider deep-dive

Webhook watches

Agent morning brief

Payment flow

Looking for the agent-first overview instead? See /for-ai-agents. For the full payment flow with code examples, see /developers/agent-payments. For use-case-specific integration paths, see /use-cases.