Niches · Model APIs & inference

Run a multi-step tool-calling loop

Four or more companies' docs show a full fit.

9companies, full fit
25companies, fit with a limit
42companies carry the tag
24share of the category's work
12first-hand accounts

What counts as done

Every tool call comes back as a structured tool-call object with a parseable name and arguments, and the echoed assistant turn is accepted on the next request.

Measured, for our own tests: a 30-turn loop finishes without a 400, an empty tool_calls array or the same call repeated more than three times. No docs we read state these figures, so they don't count against a listing here.

How agents ask for it: run this task with my tools until it is done, call the model, run the tool it asks for, send the result back, repeat, drive a coding agent or MCP tools from a model API

Does the job 9

The docs show it meets the test above, and nothing we read says otherwise.

ListingWhy
Amazon Bedrock A
Amazon Web Services, Inc.
Converse returns toolUse blocks with toolUseId, name and input, stopReason tool_use, and toolResult goes back by id; unsupported toolChoice fails with a named ValidationException rather than silently. The Anthropic Messages route serves tool_use natively. source
Claude API A
Anthropic, PBC
tool_use blocks carry name and JSON input, tool_result goes back by id, and interleaved thinking is automatic; acc-24 ran a multi-agent security platform on it and acc-25 ran 20-iteration MCP loops. source
Azure OpenAI in Foundry Models A
Microsoft Corporation
Chat Completions returns tool_calls with id, name and arguments, parallel calls on supporting deployments, and the Responses API is available on the v1 endpoint; every response carries x-ratelimit headers and 429s carry retry-after-ms. source
BlockRun.AI A
BlockRun, Inc.
Chat Completions takes tools and tool_choice (auto, none, required or named), /v1/messages and /v1/responses are also served, usage lists completion tokens including reasoning, and failed calls (400, 402, 429, 5xx) are not charged. source
Cerebras Inference B
Cerebras Systems Inc.
tool_calls with strict constrained decoding, per-model columns for tool_choice, parallel and multi-turn calling, and tool_call_id round trips; the trial tier's request limits apply before the Developer tier. source
DeepInfra B
Deep Infra Inc.
tool_calls with single, parallel and streaming calls on supported models, 200 concurrent requests per model, and fail_fast to get an immediate 429 instead of queueing at capacity. source
Meta Model API D
Meta Platforms, Inc.
Chat Completions returns tool_calls and Responses returns function_call items with previous_response_id carrying reasoning across turns; 3,000 requests and 4M tokens a minute per model, 429s with Retry-After and x-ratelimit headers. source
Mistral AI API B
Mistral AI (RCS Paris 952 418 325)
Chat Completions returns tool_calls with finish_reason tool_calls, tool_choice any forces a call, up to 128 tools per request, and the reasoning guide says to replay the full assistant message including ThinkChunk each turn. source
OpenAI API AA
OpenAI OpCo, LLC
The Responses API returns function_call items with call_id and strict function schemas, reasoning items carry encrypted_content that must be passed back with tool outputs, and x-ratelimit headers plus Retry-After guide backoff. source

Does the job, with a limit 28

It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.

ListingWhy
Antseed C
Antseed Foundation
The proxy serves Chat Completions, Responses and Messages and translates between them, and the guides target Claude Code and OpenCode, but tool-call shape rests on whichever independent seller answers and no tool fidelity is documented. source
Cloudflare AI Gateway B
Cloudflare, Inc.
Provider-native and OpenAI-compatible routes pass tool calls through unchanged, but dynamic routes accept the OpenAI chat shape only and Unified Billing traffic is capped at 200 requests per 60 seconds per gateway. source
Cloudflare Workers AI BB
Cloudflare, Inc.
Models flagged for function calling return a tool_calls array, but text generation is capped at 300 requests a minute and frontier models that need Workers Paid at 20 (50 with prepaid gateway credits), which a 50-call turn can exceed. source
Cohere Chat API (Command models) B
Cohere Inc.
v2 chat returns tool_calls with ids, supports parallel and multi-step calls and documented tool_call_id echoes, but Command A+ and the newer variants stay at trial limits of 20 requests a minute and 1,000 calls a month even on a production key. source
DeepSeek API D
Hangzhou DeepSeek Artificial Intelligence Co., Ltd.
tool_calls with a beta strict mode and documented reasoning_content echo rules, but acc-09 saw deepseek-v4-pro repeat the same git status call for 50 rounds and 8.9M tokens with no provider-side stop and no cache hits. source
Eden AI C
Eden AI SAS
Chat completions take tools and tool_choice across a thousand models, but every account is capped at 10 requests a second shared across keys and reasoning models need max_tokens of 500 or more or return empty. source
Glimpse F
Elorian AI, Inc.
The single Together endpoint lists tools and tool_choice (none, auto, required but not a named function) and 262K context, but Glimpse is a visual reasoning research preview with no first-hand account of a tool loop. source
Fireworks AI Inference BB
Fireworks.ai, Inc.
tool_calls with streaming argument deltas and parallel calls on supporting models, but the rate-limit page says traffic within limits can still be load shed with 503 Service Overloaded, which a 30-turn loop must absorb. source
Gemini Developer API B
Google LLC
Function calls arrive as function_call parts or steps, but thought signatures must be kept and resent in stateless mode; acc-08 saw 400 after the first tool call when a proxy dropped them, and acc-16 saw free-tier sessions stuck on 429. source
GroqCloud BB
Groq LLC
tool_calls with ids that must match on the way back and a per-model support table, but the free plan allows 8K tokens a minute and 1,000 requests a day on gpt-oss-120b, so a 100K-token loop needs the Developer plan. source
Hugging Face Inference Providers C
Hugging Face, Inc.
Tools and tool_choice pass through to the chosen provider, but supports_tools is true on 174 of 247 provider endpoints in the router list, so the guide tells callers to pin a provider with model:provider to cut variance. source
Jais 3 C
Mohamed bin Zayed University of Artificial Intelligence (Institute of Foundation Models), with Inception42 (a G42 company)
vLLM with --enable-auto-tool-choice and --tool-call-parser k2_horizon returns structured tool calls and the card ships a loop example, but every earlier turn must carry reasoning_content or the template errors, and acc-13 and acc-19 show vLLM parsers failing on other reasoning models. source
LiteLLM B
Berrie AI Incorporated
Tool calls pass through in OpenAI shape, but acc-07 got a Qwen3 tool call as raw JSON in content through the proxy (closed not planned) and acc-08 got 400 after the first Gemini tool call when the proxy dropped thought_signature. source
MiniMax API C
Nanonoble Pte. Ltd.
Both formats return structured tool_calls or tool_use blocks and the docs say to echo the full assistant content with thinking blocks; tool_choice is auto only, stop_sequences are ignored, and acc-11 saw OpenAI-shaped tool calls reach Claude Code through a gateway. source
Muse Spark Open C
Meta Platforms, Inc.
Tool calls come back as standard tool_calls only when the server runs the muse reasoning and tool-call parsers (vLLM also needs --enable-auto-tool-choice); reasoning can't be turned off and defaults to xhigh. source
Nemotron 3.5 Super VL C
NVIDIA Corporation
The API reference lists tools, tool_choice, parallel_tool_calls and a separate reasoning_content; acc-20 saw a tool call land in the body with empty tool_calls on the same hosted catalogue, and the trial endpoint is for prototyping only. source
Novita AI C
Novita AI
Chat Completions returns tool_calls, puts reasoning in reasoning_content, carries usage in the last stream chunk and honours stop; tool support is per model and the guide's example model is old, so check the model page first. source
OpenRouter B
OpenRouter, Inc.
Tool calls arrive in OpenAI shape across providers, but routing to tool-capable hosts is best effort unless require_parameters is set; acc-04 saw hosts return function-call markup as text with a 200 and acc-02 a generic 'Provider returned error'. source
Prism Inference C
Prism Technologies Inc
Chat Completions, Responses and Messages carry function tools or tool_use blocks with tool_choice, include_usage and reasoning controls; Responses is stateless with no previous_response_id, and only two models are served. source
Router.com (Ramp Router) C
Ramp Business Corporation
Responses and Messages carry function and custom tools, usage.cost and the serving provider in the body and X-Router-Provider; capability translation means the least capable model in a fallback list bounds tools and context. source
Beam 1.0 C
Reflection AI
tool_calls with finish_reason tool_calls, tool_choice required and parallel calls; every assistant message must be returned with its reasoning_content unchanged or the request fails with 400 missing_required_parameter, and effort defaults to max. source
RouterPlus D
EVO HQ Inc
Chat Completions, Responses and Messages pass tool_calls and tool_use; max_tokens must be sent or the balance hold assumes 32,768 output tokens and can return insufficient_quota, and there is no idempotency key so a retry bills twice. source
SambaCloud B
SambaNova Systems, Inc.
tool_calls with forced tool_choice on Chat Completions, function_call items on a stateless Responses API, and tool_use on Messages; the free tier allows 20 requests a day per model, so a loop needs the Developer tier. source
SiliconFlow E
SiliconFlow Labs Pte. Ltd.
Chat Completions returns tool_calls and a separate reasoning_content with thinking_budget on Qwen3; the function-calling guide's model list is stale (DeepSeek-V2.5) and tool support is per model. source
Together AI Inference B
Together Computer, Inc.
tool_calls with parallel calls on supported models, a reasoning_content the example returns faithfully, and a Messages API with tool_use; tool support is per model and serverless 429s and 503s are best-effort capacity. source
Vercel AI Gateway B
Vercel Inc.
Chat Completions, Responses and Anthropic Messages pass tools and tool_choice, and providerMetadata names the resolved provider; default routing can move a conversation between providers, which the sessionAffinity option exists to limit. source
Vertex AI (Gemini Enterprise Agent Platform) AA
Google LLC
Gemini thinking models return thought signatures that must be preserved across multi-turn and multi-step function calls; the function-calling page itself wasn't found at the paths tried, so tool-call shape rests on the thinking guide. source
xAI API (Grok) BB
SpaceXSI (xAI)
The Responses API returns function_call items and encrypted reasoning to pass back; Chat Completions is deprecated and has no field for encrypted reasoning, so multi-turn tool loops there lose state; per-second limits are RPM divided by 48. source

Couldn't check 2

The docs were closed to us, or silent. These carry no mark either way.

ListingWhy
StepFun API E
STEPFUN TECHNOLOGY (HK) LIMITED
The host platform.stepfun.ai closed the connection on every attempt (curl exit 56, no HTTP status) from this session, so no page was read.
Tencent Cloud TokenHub C
Tencent Cloud Computing (Beijing) Co., Ltd. (腾讯云计算(北京)有限责任公司)
The host cloud.tencent.com closed the connection on every attempt (curl exit 56, no HTTP status) from this session, so no page was read.

Doesn't do this job 2

Listings in the category that do something else, with the reason.

ListingWhy
Simplismart F
Verute Technologies Private Limited
The Llama 3.1 8B OpenAPI file has no tools or tool_choice parameter and the quickstart shows text completion only. source
SWE-2 Flash F
Cognition AI, Inc.
No model API; SWE-2 Flash runs only inside Devin Desktop and Devin CLI, so there is no tool-call object for a harness to parse. source

6 listings in the category were added after this reading and aren't marked yet.

What stops agents finishing

  • tool calls returned as text or inside a reasoning block, so the harness never executes them
  • provider rejects the echoed tool-call turn (missing thought_signature or reasoning_content) so every later request fails
  • model repeats the same tool call indefinitely with no provider-side stop and no cache hits, running up 8.9M tokens

Around it

Before: search.find-url, web-scrapers.page-to-markdown. After: agents.sandbox-run, obs.trace.

Where this comes from

Weight 24 of 100 in Model APIs & inference: 12 of 28 accounts describe a tool loop failing or succeeding on a model API; the most common job in the issues read

The same as data: /api/v1/use-cases/inference.tool-loop.json, or the MCP tool get_use_case with id inference.tool-loop. Other jobs in this category: /api/v1/niches?category=inference.

Draft, read 2026-11-12 from public docs and first-hand accounts, not yet reviewed by a person. A mark says what the docs show, not what a run measured.

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.