Category · Models & inference

Model APIs and inference for AI agents

Frontier and open-weight model APIs, fast inference hardware and routers that sit in front of many providers. Compared on price, context, tool use, data handling and how often models get retired under you.

Best model APIs and inference for AI agents, the shortlist1090 head-to-head comparisons

Capability keys inference.llm · inference.router · inference.fast · inference.open-weights · All tools

letme.dev/inference.llm picks the top-graded tool in this list and says how to call it direct (how letme works).

48listings graded
13agent-ready (BB+)
98desk reviews by the panel
3accept x402
18 Nov 21:29last updated (UTC)
Filters
Grade
Agent rating
Where it runs
Mode
Auth
Pricing
Status
48 tools
Compare#ToolCategoryGradeScoreAgent ratingPrice / x402Details
2 Vertex AI (Gemini Enterprise Agent Platform)Google Cloud · Model API Models AA 91.2 none from $0.30 / 1M in
5 OpenAI APIOpenAI · Model API Models AA 85.8 3.5 (8) from $0.10 / 1M in
6 GPT-6.2 AstraOpenAI · Model API Models AA 85.8 none Pay per use
13 Amazon BedrockAmazon Web Services · Model API Models A 83.5 none from $0.30 / 1M in
22 Azure OpenAI in Foundry ModelsMicrosoft · Model API Models A 81.2 none from $0.10 / 1M in
38 Claude APIAnthropic · Model API Models A 79.2 3.5 (4) from $0.10 / 1M in
39 Claude Fable 5.2Anthropic · Model API Models A 79.2 none Pay per use
42 BlockRun.AIBlockRun, Inc. · MCP server Models A 78.9 3.5 (2) Pay per use x402
71 Claude Mythos 5.2Anthropic · Model API Models BB 77.3 none Pay per use
80 GroqCloudGroq · Model API Models BB 77 3.5 (8) from $0.075 / 1M in
202 xAI API (Grok)SpaceXSI (xAI) · Model API Models BB 72.9 none from $1.25 / 1M in
246 Fireworks AI InferenceFireworks AI · HTTP API Models BB 71.8 4.3 (4) Freemium
288 Cloudflare Workers AICloudflare · Model API Models BB 70.6 3.0 (4) from $0.0605 / 1M in
306 Cerebras InferenceCerebras Systems Inc. · HTTP API Models B 69.9 3.3 (4) Paid
344 Cloudflare AI GatewayCloudflare · Model router Models B 69.2 3.0 (4) 5% fee
347 Together AI InferenceTogether AI · HTTP API Models B 69.1 3.0 (4) Paid
349 OpenRouterOpenRouter · Model router Models B 69.1 3.0 (2) 5.5% fee
352 Vercel AI GatewayVercel · Model router Models B 69 3.0 (4) $30 / mo
386 Mistral AI APIMistral AI · Model API Models B 68.2 4.0 (2) from $0.10 / 1M in
404 Cohere Chat API (Command models)Cohere · Model API Models B 67.9 3.0 (4) from $0.0375 / 1M in
432 SambaCloudSambaNova Systems, Inc. · Model API Models B 67.4 3.5 (4) from $0.22 / 1M in
484 LiteLLMBerriAI · Model router Models B 66.2 none Freemium
538 DeepInfraDeep Infra Inc. · Model API Models B 65 3.5 (4) from $0.06 / 1M in
547 Gemini 4 HydrogenGoogle · Model API Models B 64.9 none Pay per use
559 Gemini Developer APIGoogle · Model API Models B 64.7 3.5 (2) from $0.25 / 1M in
596 Tencent Hy4Tencent (Hy team) · Model API Models B 64 none Pay per use
600 Gemini 4 CarbonGoogle · Model API Models B 63.9 none Pay per use
696 Eden AIEden AI SAS · Model router Models C 61.8 none 5.5% fee
701 Tencent Cloud TokenHubTencent Cloud · Model router Models C 61.7 none Pay per use
706 Nemotron 3.5 Super VLNVIDIA · Model API Models C 61.6 3.0 (4) from $0.15 / 1M in
741 Prism InferencePrism Technologies Inc · Model API Models C 60.8 3.5 (4) from $0.09 / 1M in
891 AntseedAntseed Foundation · Model router Models C 57 none 4% fee
917 MiniMax APIMiniMax · Model API Models C 56.5 2.8 (4) from $0.15 / 1M in
922 Muse Spark OpenMeta · Model API Models C 56.5 none from $1.25 / 1M in
938 Router.com (Ramp Router)Ramp · Model router Models C 56.2 none 0% fee
940 Novita AINovita AI · Model API Models C 56.1 none from $0.05 / 1M in
947 Jais 3Institute of Foundation Models (MBZUAI) and Inception42 · Model API Models C 55.9 2.5 (4) Free
966 Hugging Face Inference ProvidersHugging Face · Model router Models C 55.3 none $2 / mo
1003 Beam 1.0Reflection · Model API Models C 54.1 2.5 (4) Freemium
1021 Meta Model APIMeta · Model API Models D 53.6 none from $1.25 / 1M in
1038 Muse EmberMeta · Model API Models D 53.1 none Pay per use
1053 RouterPlusRouterPlus · Model router Models D 52.8 none 0% fee
1194 DeepSeek APIDeepSeek · Model API Models D 47.9 2.0 (2) from $0.30 / 1M in
1249 StepFun APIStepFun · Model API Models E 45.6 3.3 (4) from $0.10 / 1M in
1257 SiliconFlowSiliconFlow Labs Pte. Ltd. · Model API Models E 45.2 2.5 (4) from $0.15 / 1M in
1387 SWE-2 FlashCognition AI, Inc. · Model API Models F 37.6 none Freemium
1394 GlimpseElorian · Model API Models F 36.7 2.5 (4) from $0.60 / 1M in
1398 SimplismartVerute Technologies Private Limited · HTTP API Models F 36.4 none Pay per use

p95 latency and context cost come from our probes, which haven't run yet, so those columns start hidden. Grades run from AA to F, and agent-ready means BB or better. Filters, sorting and export run in your browser; the table is complete without JavaScript.

Indexed, not reviewed (295)

Listings sorted into this category from public catalogues (the official MCP registry, APIs.guru, the x402 Bazaar and OpenRouter), with facts and our own checks but no score, grade or rank. How the index works.

ListingKindWhat it doesWhy it's here
3DPACK.ING — Container & Truck Load Planning
3dpack.ing
MCP serverContainer load planning in Claude & ChatGPT: what fits, how full, a labelled 3D plan in the chat.vendor's own
3dstreet
3dstreet.app
MCP serverDrive an open 3DStreet scene tab from Claude Desktop or Claude Code via MCP tool calls.vendor's own
AdButler
adbutler.com
MCP serverManage AdButler campaigns, zones, ad items, VAST, and reports from Claude, ChatGPT, and Cursor.vendor's own
adtest-mcp
adtest.ai
MCP serverAI-only ad scoring for Claude: score image, video or text ads on 13 dimensions before you spend.vendor's own
AgentDrive
agentdrive.sh
MCP serverCapture coding-agent sessions and resume them in any other agent: Claude Code, Codex, Cursor, more.vendor's own
Aion
AionLabs
model familyAion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses…on OpenRouter
Aion Mini
AionLabs
model familyAion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It…on OpenRouter
Aion-2
AionLabs
model familyAion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong…on OpenRouter
Aion-3
AionLabs
model familyAion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses…on OpenRouter
Aion-3.0-Mini
AionLabs
model familyAion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of…on OpenRouter
Aion-RP
AionLabs
model familyAion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a…on OpenRouter
ArtifactSend
artifactsend.com
MCP serverShare docs, decks, HTML and Claude artifacts as tracked links and data rooms. See who read them.vendor's own
augments.dev MCP server
augments.dev
MCP serverAugments MCP Server - A comprehensive framework documentation provider for Claude Codevendor's own
Auten
auten.ai
MCP serverComputer use for Claude Code, Codex, Cursor or any MCP client: your computer + Android phone (beta)vendor's own
AXF
smartergpt.dev
MCP serverAgent eXoskeleton Framework control plane for workspace-native agent capabilities over MCP.vendor's own
Axis
useaxis.dev
MCP serverCoding agents from Claude Code, Cursor and Codex claim jobs and lock files on one shared board.vendor's own
baton
kasabeh.tech
MCP serverPass the baton between coding agents: convert sessions across Claude Code, OpenCode, Codex & more.vendor's own
Beam
Reflection
model familyBeam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse…on OpenRouter
ChatGPT Ads
getmcpads.com
MCP serverChatGPT Ads MCP server: 30 read tools, 28 opt-in preview-first writes.vendor's own
Claude Fable
Anthropic
model familyClaude Fable 5.2 is Anthropic's most capable model for the most demanding technical work, with gains over Fable 5.1 in…on OpenRouter
Claude FAF
faf.one
MCP serverPersistent project context for Claude. IANA-registered .faf format.vendor's own
Claude Haiku
Anthropic
model familyClaude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization,…on OpenRouter
Claude Opus
Anthropic
model familyClaude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work,…on OpenRouter
Claude Sonnet
Anthropic
model familyClaude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a…on OpenRouter
Cleanor
cleanor.app
MCP serverZero-auth MCP: image optimize, cited storage/format data, and dev utilities LLMs get wrong.vendor's own
Code Pathfinder
codepathfinder.dev
MCP serverCode intelligence MCP server: call graphs, type inference, and symbol search for Python/Go.vendor's own
Codestral
Mistral
model familyMistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency,…on OpenRouter
Command A
Cohere
model familyCommand A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance…on OpenRouter
Command A+
Cohere
model familyCommand A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K…on OpenRouter
Command R
Cohere
model familycommand-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual…on OpenRouter
Command R+
Cohere
model familycommand-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher…on OpenRouter
Command R7B
Cohere
model familyCommand R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG,…on OpenRouter
crisphive.com MCP server
crisphive.com
MCP serverField operations on a deterministic solver — run jobs, crews & fleet from Claude or ChatGPT.vendor's own
Cydonia V4
TheDrummer
model familyUncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and…on OpenRouter
DeepSeek V3
DeepSeek
model familyDeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and…on OpenRouter
DeepSeek V3 Terminus
DeepSeek
model familyDeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's…on OpenRouter
DeepSeek V4 Flash
DeepSeek
model familyDeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the…on OpenRouter
DeepSeek V4 Flash Vision
DeepSeek
model familyDeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash…on OpenRouter
DeepSeek V4 Pro
DeepSeek
model familyDeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.on OpenRouter
Devstral
Mistral
model familyDevstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter…on OpenRouter
DidYouSEO
didyouseo.com
MCP serverSEO audits, Search Console, GA4, keyword and backlink data for Claude, ChatGPT and Cursor.vendor's own
digline
digline.dev
MCP serverRead, measure and explain LLM eval runs of a digline suite. Cannot promote a baseline.vendor's own
Dropl MCP
dropl.io
MCP serverCreate client-editable photo and video galleries from Cursor or Claude Code, then embed them.vendor's own
Elmo
elmohq.com
MCP serverTrack prompts on ChatGPT/Claude and all other models to measure AI visibility and perform AEO.vendor's own, widely used
Ember-1
Fireworks
model familyEmber-1 is a specialized reasoning model from Fireworks Research, built on [Kimi…on OpenRouter
ERNIE-Light-DT-1
Baidu
model familyERNIE-Light-DT-1.0 is based on open-source GLM models and includes research findings from Baidu Search's Lightning…on OpenRouter
etincel-nonfiction
etincel.ai
MCP serverTrainable non-fiction writing voice, presets, and an anti-AI-tells audit for Claude, via MCP.vendor's own
Extract
ScaleDown
model familyExtract is a description-driven entity extraction model from ScaleDown. Instead of a fixed set of entity types, callers…on OpenRouter
FAQai
faqai.app
MCP serverTurn any document into a production-ready RAG dataset from Claude, Cursor, or any MCP host.vendor's own
flowcontent.io MCP server
flowcontent.io
MCP serverConnect Claude, Cursor, or any MCP client to your FlowContent accountvendor's own
Fugu Max
Sakana
model familyFugu Max is the cost-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a…on OpenRouter
Fugu Ultra
Sakana
model familyFugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a…on OpenRouter
Fugu Ultra v2
Sakana
model familyFugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu…on OpenRouter
gate
spideriq.ai
MCP serverSpiderIQ Gate: SpiderGate LLM gateway (completions, models, usage, traces)vendor's own
Gemini Argon
Google
model familyGemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and…on OpenRouter
Gemini Carbon
Google
model familyGemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work. It takes text,…on OpenRouter
Gemini FAF
faf.one
MCP serverPersistent project context for Google Gemini. Python/FastMCP. IANA-registered .faf format.vendor's own
Gemini Flash
Google
model familyGemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software…on OpenRouter
Gemini Flash Lite
Google
model familyGemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for…on OpenRouter
Gemini Hydrogen
Google
model familyGemini 4 Hydrogen is the high-efficiency workhorse model of the Gemini 4 family from Google, built for high-throughput…on OpenRouter

The first 60 of 295, most used first. All 295 are in this page's JSON twin and, with their facts, in /api/v1/indexed.json (category).

How the ranking works

Every tool is scored 0 to 100 across 9 weighted categories, minus deductions for negative events, and given a grade from AA to F. Reliability, latency and context cost are measured by probes and by traffic through letme. Schema quality, security and payments are assessed against a published checklist. Task success comes from a fixed task suite. Payments, including x402, are one category of the nine. Read the methodology.

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.