1stTop pick
Researched 8d agoGemini 3 Pro
- BFCL
- 72.51%
- Output (from)
- $5.00 / 1M
Best LLMs for JSON / Tool use (2026)
Last refreshed 2026-09-29. Next refresh: weekly.
Best LLMs for JSON / Tool use in 2026. Ranked by BFCL benchmark, with native JSON output and structured output support.
Verdict
Use Gemini 3 Pro for JSON / Tool use today.
GPT-6.1 Sol is the runner-up; compare BFCL against Release.
2ndShortlist
Researched todayGPT-6.1 Sol
- Release
- 2026-09-29
- Output (from)
- $10.00 / 1M
3rdShortlist
Researched 1d agoClaude Sonnet 5.5
- Release
- 2026-09-28
- Output (from)
- $10.00 / 1M
How we rank
JSON / Tool use leaders rank on BFCL first; when Berkeley coverage lags new SKUs, we fall back to τ-bench so fresh agentic models still surface.
- Eligibility — Models with `function_calling` or `tool_use` enabled in seed metadata.
- Primary ranking — BFCL score if present, otherwise τ-bench, then newer release.
- Variant collapse — We keep one row per model family (`familySlug` + parameter tier). When headline scores tie within ±0.5 pt (±10 Elo on Chatbot Arena), we pick the canonical SKU by lowest tracked input price, then GA over preview or limited access, then newest `release`. A folded sibling within the benchmark noise band can show a "Tied within margin" chip on that score cell.
- Pricing — Lowest tracked input(output) for API routes.
New models awaiting benchmark coverage
These source-backed rows qualify for this task page, but they are not scored leaderboard picks until the category benchmark data exists.
| Model | Why it is listed | Status | Tracked price |
|---|---|---|---|
| GPT-6.1 Sol ToolsCode execution | GPT-6.1 Sol reports tool-use capability; keep it separate from the scored tool-use ranking until benchmarks land. | Benchmark pending No tracked BFCL or tau-bench score yet. | In $2.00 / Out $10.00 |
| Claude Sonnet 5.5 Tools | Claude Sonnet 5.5 reports tool-use capability; keep it separate from the scored tool-use ranking until benchmarks land. | Benchmark pending No tracked BFCL or tau-bench score yet. | In $2.00 / Out $10.00 |
| Perceptron Mk1.5 Tools | Perceptron Mk1.5 reports tool-use capability; keep it separate from the scored tool-use ranking until benchmarks land. | Benchmark pending No tracked BFCL or tau-bench score yet. | In $0.15 / Out $1.50 |
| Ember-1 Tools | Ember-1 reports tool-use capability; keep it separate from the scored tool-use ranking until benchmarks land. | Benchmark pending No tracked BFCL or tau-bench score yet. | In $3.00 / Out $15.00 |
| # | Model | Input $/1M | Output $/1M | |
|---|---|---|---|---|
| 1 | Ring-2.6-1T ReasoningTools Signal used: τ-bench 95.32% | $0.07 | $0.63 | |
| 2 | Mistral Medium 3.5 ReasoningVisionTools Signal used: τ-bench 91.4% | $1.50 | $7.50 | |
| 3 | ByteDance Doubao Seed 2.0 Pro VisionTools Signal used: τ-bench 90.4% | $0.47 | $2.37 | |
| 4 | Claude Mythos Preview Invite-onlyReasoningVisionTools Signal used: τ-bench 89.2% | — | — | |
| 5 | LFM2.5 8B A1B ReasoningTools Signal used: τ-bench 88.07% | — | — | |
| 6 | Claude Sonnet 4.6 ReasoningVisionTools Signal used: τ-bench 87.5% | $3.00 | $15.00 | |
| 7 | Command A+ ReasoningVisionTools Signal used: τ-bench 85% | — | — | |
| 8 | Claude Opus 4.6 ReasoningVisionTools Signal used: τ-bench 84.8% | $5.00 | $25.00 | |
| 9 | GLM-5 ReasoningTools Signal used: τ-bench 82.1% | $0.60 | $2.08 | |
| 10 | Qwen3.5-35B-A3B ReasoningTools Signal used: τ-bench 81.2% | $0.14 | $1.00 | |
| 11 | Qwen3.5-122B-A10B ReasoningVisionTools Signal used: τ-bench 79.5% | $0.26 | $2.08 | |
| 12 | Qwen3.5-9B VisionTools Signal used: τ-bench 79.1% | $0.10 | $0.15 | |
| 13 | Qwen3.5-27B ReasoningVisionTools Signal used: τ-bench 79% | $0.20 | $1.56 | |
| 14 | Grok 4.20 ReasoningVisionTools Signal used: τ-bench 78.9% | $1.25 | $2.50 | |
| 15 | GPT-5.4 ReasoningVisionTools Signal used: τ-bench 78.3% | $2.50 | $15.00 | |
| 16 | GPT-5.3-Codex ReasoningVisionTools Signal used: τ-bench 77.8% | $1.75 | $14.00 | |
| 17 | Claude Opus 4.5 ReasoningVisionTools Signal used: BFCL 77.47% | $5.00 | $25.00 | |
| 18 | Qwen3.6-Plus VisionTools Signal used: τ-bench 76.8% | $0.33 | $1.95 | |
| 19 | Qwen3-Max VisionTools Signal used: τ-bench 76.8% | $0.78 | $3.90 | |
| 20 | Gemini 3.1 Pro Preview PreviewVisionTools Signal used: τ-bench 76.5% | $2.00 | $12.00 |
Honorable mentions
Next seats in this ranking. Lines below are from each model's stored description in LLMReference seed data—spot-check the model page before relying on a capability claim.
MiniMax M3.1 Flash Preview (API id MiniMax-M3.1-Flash-Preview) is MiniMax's faster/lighter M3-series multimodal coding model announced for MiniMax Code on 2026-09-27 and made live on Token Plan the same day. First-party docs: 1,000,000-token context; text+image+video inputs to text; agentic reasoning, tool use, and coding; thinking always on with tunable effort low|medium|high|xhigh|max (default max; cannot disable — 400 'requires adaptive thinking'). Availability for now is Token Plan + MiniMax Code only — NOT on pay-as-you-go (paygo price table lists M3/M2.x only; no M3.1 Flash $/MTok row). No public Hugging Face weights/model card for the Flash Preview SKU. Closed-source hosted API — licenseSlug proprietary / weights notReleased.
2026-09-27
Release
Perceptron Mk1.5 is Perceptron's embodied vision-language model released September 25, 2026 (first-party blog). Successor to Mk1 in the Perceptron Mk family: native audio in, video object tracking, web search, sub-agent/tool calls, and stronger visual reasoning; blog cites ~2-5x faster end-to-end vs Mk1. Accepts text, images, video, and audio; emits text plus spatial/temporal annotations (points, boxes, polygons, clips, object tracks). First-party docs: Model ID perceptron-mk1.5; context window 36,864 tokens; max output 8,192; pricing $0.15/M input, $1.50/M output, $0.0375/M cached input. Available via Perceptron Platform + SDK and OpenRouter (perceptron/perceptron-mk1.5). Closed-source hosted API under a proprietary license.
2026-09-25
Release
- #6Ember-1
Ember-1 is Fireworks Research's specialized foundation model announced September 23, 2026, the first model in the Ember series. Built on Kimi K3 and trained by Fireworks (50+ training experiments; Fireworks Serverless Training) to shorten reasoning traces (~40% fewer tokens while holding quality on Fireworks' evaluations and live A/B tests). Fireworks markets Ember-1 as its own model, a Research Preview on Serverless alongside base Kimi K3, and catalogs it as Fireworks Ember rather than a Kimi family member. Fireworks model page: API path accounts/fireworks/models/ember-1; MoE; parameters 2.78T; context length 1040k tokens; image input supported; function calling supported; fine-tuning not supported; serverless supported; kind base model; created 2026-09-22; state Ready; provider Fireworks. Serverless list is $3.00 input / $0.30 cached input / $15.00 output per 1M tokens. No first-party public weights or open license is stated.
2026-09-23
Release
Compare Top Picks
Side-by-side comparison of the top picks by price, benchmark, and API access.
Browse Other Categories
Best LLMs for Code GenerationBest LLMs for RAGBest LLMs for Agents vs Agent Products (2026)Best LLMs for ClassificationBest Open Source LLMsBest Multimodal / Vision LLMsBest LLM for Translation in 2026Best AI Image Models in 2026Best AI Video Models in 2026Best LLMs for Reasoning & MathBest Small Language Models (SLMs)Cheapest LLM APIs You Can Call Right NowBest Long Context LLMsBest Mainstream LLM APIs, RankedBest LLMs for EnterpriseBest Free LLMs You Can Use Right NowBest LLMs for WritingBest LLMs for MarketingBest LLMs for Customer Support