Inference availability
Providers Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.
Report a price
Providers offering Trinity Large Thinking
Provider Provider model ID Context Max output Input Output Cache read Capabilities Docs
N NanoGPT arcee-ai/trinity-large-thinking262.144K
80K
$0.25
$0.9
$0.125
Reasoning Tools Docs ↗
K Kilo Gateway arcee-ai/trinity-large-thinking262.144K
80K
$0.25
$0.8
$0.06
Reasoning Tools Docs ↗
V Vercel AI Gateway arcee-ai/trinity-large-thinking262.1K
80K
$0.25
$0.8
$0.06
Reasoning Tools Docs ↗
O OpenRouter arcee-ai/trinity-large-thinking262.144K
80K
$0.25
$0.8
$0.06
Reasoning Tools Docs ↗
A Arcee trinity-large-thinking262.144K
80K
$0.25
$0.8
$0.06
Reasoning Tools Docs ↗
Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.
Listed rates
Price across providers Input price per million tokens as published by each provider. Bars are drawn from listed rates only — no traffic weighting, since the catalog observes no requests.
Lowest input
$0.25/M
Across 5 priced providers
Median input
$0.25/M
Midpoint of listed rates
Highest input
$0.25/M
Same as the lowest listed rate
Output range
$0.8 – $0.9
Per million output tokens
NanoGPT
$0.25/M
Kilo Gateway
$0.25/M
Vercel AI Gateway
$0.25/M
OpenRouter
$0.25/M
Arcee
$0.25/M
5 providers list the identical $0.25 input rate, so price alone will not separate them — compare context limits, max output, and capabilities above.
Context limits also differ by provider, from 262.1K to 262.144K tokens. Compare the provider table above before choosing on price alone.
Specification
Capabilities Recorded from the source catalog and provider listings.
✓
Reasoning
Yes
✓
Tool calling
Yes
×
Structured output
No
×
Attachments
No
×
Vision input
No
✓
Open weights
Yes
Model family trinity
Knowledge cutoff Not documented
License OpenMDW-1.1
Release date 2026-04-01
Model ID arcee-ai/trinity-large-thinking
Weights:
Hugging Face ↗
Published evaluations
Benchmarks Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.
Benchmark registry
Benchmark profile
IntelligenceIntelligence Index
Coding IndexCoding Index
Agentic IndexAgentic Index
Design Arena: w…Design Arena: website
Design Arena: g…Design Arena: gamedev
Design Arena: c…Design Arena: codecategories
Design Arena: d…Design Arena: dataviz
Design Arena: u…Design Arena: uicomponent
This model — Intelligence Index: 10.8 index (24.3th percentile)
This model — Coding Index: 25.8 index (25.9th percentile)
This model — Agentic Index: 1 index (11.2th percentile)
This model — Design Arena: website: 1137 elo (27.8th percentile)
This model — Design Arena: gamedev: 1079 elo (19.6th percentile)
This model — Design Arena: codecategories: 1117 elo (24.2th percentile)
This model — Design Arena: dataviz: 1098 elo (19.4th percentile)
This model — Design Arena: uicomponent: 1040 elo (15.1th percentile)
Each axis is this model's percentile among the 8 benchmarks it has published results for, measured against every other model with a score on that same benchmark. Percentiles are used because benchmarks do not share a scale — a 60 on one is not a 60 on another. Hover any point for the raw score.
Intelligence Index
#253 of 334
3.8
median 21.4
57.6
Coding Index
#159 of 214
2.7
median 49.3
81.6
Agentic Index
#176 of 201
0.1
median 18.6
57.9
Design Arena: website
#145 of 200
750.0
median 1196.0
1361.0
Design Arena: gamedev
#154 of 191
773.0
median 1189.0
1445.0
Design Arena: codecategories
#143 of 188
788.0
median 1204.5
1389.0
Design Arena: dataviz
#148 of 183
858.0
median 1203.0
1399.0
Design Arena: uicomponent
#155 of 182
762.0
median 1203.5
1381.0
Design Arena: 3d
#129 of 176
837.0
median 1188.5
1467.0
Design Arena: svg
#119 of 128
967.0
median 1181.0
1327.0
Design Arena: asciiart
#105 of 108
989.0
median 1171.0
1354.0
Each strip shows every published score for that benchmark, with this model marked. The lighter shape behind the ticks is the density of results, and the dashed line is the median.
Cost against capability
Price and performance Listed input price plotted against Intelligence Index, the benchmark with the widest published coverage that this model appears in.
0
31
61
$0.01
$0.1
$1
$10
$100
Nova 2 Lite — $0.3/M, score 13.4
Nova Lite 1.0 — $0.059/M, score 6.7
Nova Micro 1.0 — $0.035/M, score 5.9
Amazon: Nova Premier 1.0 — $2.5/M, score 9.2
Nova Pro 1.0 — $0.799/M, score 7.0
Claude Fable 5 — $10/M, score 49.6
Anthropic: Claude Fable 5.1 — $10/M, score 53.4
Anthropic: Claude Fable 5.1 (batch) — $5/M, score 53.4
Anthropic: Claude Fable 5 (batch) — $5/M, score 49.6
Anthropic: Claude Haiku 4.5 — $1/M, score 16.9
Anthropic: Claude Haiku 4.5 (batch) — $0.5/M, score 16.9
Anthropic: Claude Haiku 5.5 — $0.1/M, score 43.4
Anthropic: Claude Haiku 5.5 (batch) — $0.05/M, score 43.4
Anthropic: Claude Opus 4.1 — $15/M, score 22.8
Anthropic: Claude Opus 4.1 (batch) — $7.5/M, score 22.8
Anthropic: Claude Opus 4.5 — $5/M, score 29.1
Anthropic: Claude Opus 4.5 (batch) — $2.5/M, score 29.1
Anthropic: Claude Opus 4.6 — $5/M, score 31.9
Anthropic: Claude Opus 4.6 (batch) — $2.5/M, score 31.9
Anthropic: Claude Opus 4.7 — $5/M, score 40.7
Anthropic: Claude Opus 4.7 (batch) — $2.5/M, score 40.7
Anthropic: Claude Opus 4.8 — $5/M, score 41.8
Anthropic: Claude Opus 4.8 (batch) — $2.5/M, score 41.8
Claude Opus 5 — $5/M, score 50.8
Anthropic: Claude Opus 5.5 — $4/M, score 57.6
Anthropic: Claude Opus 5.5 (batch) — $2/M, score 57.6
Anthropic: Claude Opus 5 (batch) — $2.5/M, score 50.8
Anthropic: Claude Sonnet 4 — $3/M, score 18.9
Anthropic: Claude Sonnet 4.5 — $3/M, score 20.7
Anthropic: Claude Sonnet 4.5 (batch) — $1.5/M, score 20.7
Anthropic: Claude Sonnet 4.6 — $3/M, score 30.1
Anthropic: Claude Sonnet 4.6 (batch) — $1.5/M, score 30.1
Claude Sonnet 5 — $2/M, score 38.2
Anthropic: Claude Sonnet 5.5 — $2/M, score 56.0
Anthropic: Claude Sonnet 5.5 (batch) — $1/M, score 56.0
Anthropic: Claude Sonnet 5 (batch) — $1/M, score 38.2
Trinity Large Thinking — $0.25/M, score 10.8
Command A — $2.5/M, score 13.1
DeepSeek V3 0324 — $0.29/M, score 9.7
DeepSeek V3.1 — $0.19/M, score 13.7
DeepSeek-R1 — $0.58/M, score 11.4
DeepSeek R1 0528 — $0.2/M, score 13.1
DeepSeek: DeepSeek V3.1 Terminus — $0.27/M, score 14.8
DeepSeek V3.2 — $0.209/M, score 21.5
DeepSeek: DeepSeek V3.2 Exp — $0.27/M, score 16.6
DeepSeek V4 Flash — $0.15/M, score 24.4
DeepSeek V4 Flash 0731 — $0.035/M, score 34.3
DeepSeek: DeepSeek V4 Flash 0731 (batch) — $0.11/M, score 34.3
DeepSeek V4 Flash Vision Exp — $0.15/M, score 34.8
DeepSeek V4 Pro — $0.66/M, score 30.4
DeepSeek V4 Pro 0813 — $0.132/M, score 36.0
DeepSeek: DeepSeek V4 Pro 0813 (batch) — $0.66/M, score 36.0
DeepSeek V4.1 Flash — $0.02/M, score 24.7
DeepSeek V4.1 Flash 1017 — $0.15/M, score 39.5
DeepSeek: DeepSeek V4.1 Flash (batch) — $0.05/M, score 24.7
Gemini 2.5 Flash — $0.3/M, score 15.5
Gemini 2.5 Flash-Lite — $0.1/M, score 10.4
Google: Gemini 2.5 Flash Lite (batch) — $0.05/M, score 10.4
Google: Gemini 2.5 Flash (batch) — $0.15/M, score 15.5
Gemini 2.5 Pro — $1.25/M, score 16.1
Google: Gemini 2.5 Pro (batch) — $0.625/M, score 16.1
Gemini 3 Flash Preview — $0.5/M, score 26.3
Google: Gemini 3 Flash Preview (batch) — $0.25/M, score 26.3
Gemini 3.1 Flash Lite Preview — $0.25/M, score 15.6
Gemini 3.1 Pro Preview — $2/M, score 29.7
Google: Gemini 3.1 Pro Preview (batch) — $1/M, score 29.7
Gemini 3.5 Flash — $1.5/M, score 33.6
Gemini 3.5 Flash Lite — $0.3/M, score 22.2
Google: Gemini 3.5 Flash Lite (batch) — $0.15/M, score 22.2
Google: Gemini 3.5 Flash (batch) — $0.75/M, score 33.6
Gemini 3.6 Flash — $0.75/M, score 34.0
Google: Gemini 3.6 Flash (batch) — $0.375/M, score 34.0
Gemini 3.7 Flash — $0.75/M, score 39.6
Google: Gemini 3.7 Flash (batch) — $0.375/M, score 39.6
Gemini 3.8 Flash — $0.75/M, score 40.9
Google: Gemini 3.8 Flash (batch) — $0.375/M, score 40.9
Gemini 4 Argon — $2/M, score 52.6
Google: Gemini 4 Argon (batch) — $1/M, score 52.6
Gemma 3 12B IT — $0.04/M, score 3.8
Gemma 3 27B IT — $0.08/M, score 4.9
Gemma 3 4B IT — $0.04/M, score 4.8
Gemma 4 26B A4B IT — $0.042/M, score 16.7
Gemma 4 31B IT — $0.1/M, score 14.7
Google: Gemma 4 31B (batch) — $0.39/M, score 15.4
IBM: Granite 4.0 Micro — $0.017/M, score 5.1
IBM: Granite 4.2 8B — $0.06/M, score 11.1
Mercury 2 — $0.25/M, score 10.8
Mercury 2.5 — $0.2/M, score 12.3
inclusionAI: Ling-2.6-flash — $0.01/M, score 14.2
Ling 3.0 Flash — $0.021/M, score 20.1
Ling 3.0 Flash Fin — $0.075/M, score 22.6
Ling 3.0 Flash VL — $0.06/M, score 24.6
Ling 3.1 Flash — $0.075/M, score 41.1
inclusionAI: Ring-2.6-1T — $0.075/M, score 31.1
Kwaipilot: KAT-Coder-Pro V2 — $0.3/M, score 33.7
LongCat-2.0 — $0.3/M, score 19.1
Meta: Llama 3.1 70B Instruct — $0.4/M, score 6.6
Meta: Llama 3.1 8B Instruct — $0.05/M, score 6.9
Meta: Llama 3.2 1B Instruct — $0.027/M, score 4.8
Meta: Llama 3.2 3B Instruct — $0.051/M, score 5.7
Meta: Llama 3.3 70B Instruct — $0.1/M, score 7.7
Meta: Llama 4 Maverick — $0.188/M, score 9.3
Meta: Llama 4 Scout — $0.1/M, score 6.5
Muse Glimmer 30B — $0.2/M, score 17.5
Muse Spark 1.1 — $1.25/M, score 33.7
Muse Spark 1.2 — $1.25/M, score 39.6
Muse Spark 1.3 — $1.25/M, score 48.1
Microsoft: Phi 4 — $0.07/M, score 5.9
MiniMax: MiniMax M1 — $0.55/M, score 11.7
MiniMax: MiniMax M2 — $0.255/M, score 18.6
MiniMax: MiniMax M2.1 — $0.3/M, score 20.9
MiniMax: MiniMax M2.5 — $0.3/M, score 22.8
MiniMax: MiniMax M2.7 — $0.3/M, score 22.8
MiniMax: MiniMax M3 — $0.3/M, score 29.2
MiniMax: MiniMax M3.1 Flash — $0.15/M, score 42.7
MiniMax: MiniMax M3 (batch) — $0.3/M, score 29.2
Mistral: Devstral 2 2512 — $0.4/M, score 8.6
Mistral: Ministral 3 14B 2512 — $0.2/M, score 6.0
Mistral: Ministral 3 3B 2512 — $0.1/M, score 4.8
Mistral: Ministral 3 8B 2512 — $0.15/M, score 5.5
Mistral: Ministral 3 8B 2512 (batch) — $0.075/M, score 5.5
Mistral Large — $2/M, score 5.8
Mistral Large 2407 — $2/M, score 7.6
Mistral: Mistral Large 3 2512 — $0.5/M, score 9.3
Mistral: Mistral Large 3 2512 (batch) — $0.25/M, score 9.3
Mistral: Mistral Large 4 — $1.36/M, score 38.4
Mistral: Mistral Medium 3 — $0.4/M, score 9.0
Mistral: Mistral Medium 3.5 — $1.5/M, score 14.2
Mistral: Mistral Medium 3.5 (batch) — $0.75/M, score 14.2
Mistral: Mistral Medium 3.1 — $0.4/M, score 9.2
Mistral: Mistral Medium 3.1 (batch) — $0.2/M, score 9.2
Mistral: Saba — $0.2/M, score 6.5
Mistral: Mistral Small 3 — $0.05/M, score 6.7
Mistral: Mistral Small 4 — $0.15/M, score 11.3
Mistral: Mistral Small 4 (batch) — $0.075/M, score 11.3
Mistral: Mixtral 8x22B Instruct — $2/M, score 5.7
Kimi K2 0711 — $0.4/M, score 12.7
Kimi K2 Instruct 0905 — $0.6/M, score 15.3
Kimi K2 Thinking — $0.4/M, score 22.0
Kimi K2.5 — $0.375/M, score 23.5
Kimi K2.6 — $0.95/M, score 27.0
Kimi K2.7 Code — $0.95/M, score 25.8
MoonshotAI: Kimi K2.7 Code (batch) — $0.475/M, score 43.0
Kimi K3 — $3/M, score 43.6
Kimi K3.1 Pro — $2/M, score 55.1
MoonshotAI: Kimi K3 (batch) — $2.28/M, score 43.6
Nex-N2-Pro — $0.5/M, score 41.7
Hermes 3 405B Instruct — $1/M, score 7.4
Hermes 3 70B Instruct — $0.7/M, score 6.7
Hermes 4 405B — $0.996/M, score 7.5
Nemotron 3 Nano 30B A3B — $0.05/M, score 8.9
Nemotron 3 Super 120B A12B — $0.05/M, score 12.8
Nemotron 3 Ultra 550B A55B — $0.1/M, score 22.9
NVIDIA: Nemotron 3 Ultra (batch) — $0.6/M, score 38.3
Nemotron 3.5 Lightning 30B A3B — $0.025/M, score 12.9
NVIDIA: Nemotron 3.5 Super VL — $0.15/M, score 26.5
GPT-3.5-turbo — $0.5/M, score 5.5
OpenAI: GPT-3.5 Turbo (batch) — $0.25/M, score 5.5
GPT-4 — $30/M, score 6.7
GPT-4 Turbo — $10/M, score 7.0
OpenAI: GPT-4 Turbo (batch) — $5/M, score 7.0
GPT-4.1 — $2/M, score 12.7
GPT-4.1 mini — $0.4/M, score 10.2
OpenAI: GPT-4.1 Mini (batch) — $0.2/M, score 10.2
GPT-4.1 nano — $0.1/M, score 7.8
OpenAI: GPT-4.1 Nano (batch) — $0.05/M, score 7.8
OpenAI: GPT-4.1 (batch) — $1/M, score 12.7
GPT-4o (2024-05-13) — $5/M, score 7.3
GPT-4o (2024-08-06) — $2.5/M, score 7.7
GPT-4o (2024-11-20) — $2.5/M, score 8.4
GPT-4o mini — $0.15/M, score 6.7
OpenAI: GPT-4o-mini (batch) — $0.075/M, score 6.7
GPT-5 — $1.25/M, score 23.0
GPT-5 Mini — $0.25/M, score 20.6
OpenAI: GPT-5 Mini (batch) — $0.125/M, score 20.6
GPT-5 Nano — $0.05/M, score 13.0
OpenAI: GPT-5 Nano (batch) — $0.025/M, score 13.0
GPT-5.1 — $1.25/M, score 24.7
GPT-5.1 Codex — $1.07/M, score 23.7
GPT-5.1 Codex mini — $0.22/M, score 20.4
OpenAI: GPT-5.1 (batch) — $0.625/M, score 24.7
GPT-5.2 — $1.75/M, score 30.4
GPT-5.2 Codex — $0.14/M, score 28.5
OpenAI: GPT-5.2 (batch) — $0.875/M, score 30.4
GPT-5.3 Codex — $1.75/M, score 32.5
GPT-5.4 — $2.5/M, score 39.0
GPT-5.4 mini — $0.75/M, score 24.1
OpenAI: GPT-5.4 Mini (batch) — $0.375/M, score 24.1
GPT-5.4 nano — $0.2/M, score 20.7
OpenAI: GPT-5.4 Nano (batch) — $0.1/M, score 20.7
OpenAI: GPT-5.4 (batch) — $1.25/M, score 39.0
GPT-5.5 — $5/M, score 38.4
OpenAI: GPT-5.5 (batch) — $2.5/M, score 38.4
GPT-5.6 Luna — $0.2/M, score 37.3
OpenAI: GPT-5.6 Luna (batch) — $0.1/M, score 37.3
GPT-5.6 Sol — $4/M, score 47.0
OpenAI: GPT-5.6 Sol (batch) — $2/M, score 47.0
GPT-5.6 Terra — $2/M, score 42.1
OpenAI: GPT-5.6 Terra (batch) — $1/M, score 42.1
OpenAI: GPT-5 (batch) — $0.625/M, score 23.0
GPT-6 Astra — $10/M, score 52.7
OpenAI: GPT-6 Astra (batch) — $5/M, score 52.7
GPT-6 Luna — $0.1/M, score 38.1
OpenAI: GPT-6 Luna (batch) — $0.05/M, score 38.1
GPT-6 Sol — $2/M, score 47.6
OpenAI: GPT-6 Sol (batch) — $1/M, score 47.6
GPT-6.1 Sol — $2/M, score 51.8
OpenAI: GPT-6.1 Sol (batch) — $1/M, score 51.8
GPT OSS 120B — $0.03/M, score 11.6
OpenAI: gpt-oss-120b (batch) — $0.03/M, score 11.6
GPT OSS 20B — $0.018/M, score 10.0
OpenAI: gpt-oss-20b (batch) — $0.024/M, score 10.0
o1 — $15/M, score 15.2
o1-pro — $150/M, score 12.4
o3 — $2/M, score 20.2
o3-mini — $1.1/M, score 12.5
OpenAI: o3 Mini High — $1.1/M, score 11.0
OpenAI: o3 Mini High (batch) — $0.55/M, score 15.7
OpenAI: o3 Mini (batch) — $0.55/M, score 12.5
o3-pro — $20/M, score 21.9
OpenAI: o3 (batch) — $1/M, score 20.2
o4-mini — $1.1/M, score 16.7
OpenAI: o4 Mini (batch) — $0.55/M, score 16.7
Sonar — $1/M, score 7.7
Sonar Pro — $3/M, score 7.6
Sonar Reasoning Pro — $2/M, score 11.8
Qwen2.5 72B Instruct — $0.36/M, score 7.7
Qwen2.5 Coder 32B Instruct — $0.66/M, score 6.7
Qwen: Qwen3 14B — $0.12/M, score 6.7
Qwen: Qwen3 235B A22B — $0.455/M, score 9.5
Qwen: Qwen3 235B A22B Instruct 2507 — $0.09/M, score 12.0
Qwen: Qwen3 235B A22B Thinking 2507 — $0.45/M, score 12.7
Qwen: Qwen3 30B A3B — $0.12/M, score 7.6
Qwen: Qwen3 30B A3B Instruct 2507 — $0.09/M, score 7.5
Qwen: Qwen3 30B A3B Thinking 2507 — $0.2/M, score 9.8
Qwen: Qwen3 32B — $0.08/M, score 7.3
Qwen: Qwen3 8B — $0.117/M, score 7.3
Qwen: Qwen3 Coder 480B A35B — $0.3/M, score 11.9
Qwen: Qwen3 Coder 30B A3B Instruct — $0.07/M, score 9.6
Qwen: Qwen3 Coder Next — $0.12/M, score 9.2
Qwen: Qwen3 Max — $0.78/M, score 15.6
Qwen: Qwen3 Max Thinking — $0.78/M, score 21.3
Qwen: Qwen3 Next 80B A3B Instruct — $0.09/M, score 9.6
Qwen: Qwen3 Next 80B A3B Thinking — $0.15/M, score 11.2
Qwen: Qwen3 VL 235B A22B Instruct — $0.21/M, score 9.9
Qwen: Qwen3 VL 235B A22B Thinking — $0.4/M, score 13.4
Qwen: Qwen3 VL 30B A3B Instruct — $0.15/M, score 7.9
Qwen: Qwen3 VL 30B A3B Thinking — $0.29/M, score 9.5
Qwen: Qwen3 VL 32B Instruct — $0.104/M, score 11.9
Qwen: Qwen3 VL 8B Instruct — $0.25/M, score 7.3
Qwen: Qwen3 VL 8B Thinking — $0.18/M, score 8.2
Qwen: Qwen3.5-122B-A10B — $0.4/M, score 17.7
Qwen: Qwen3.5-27B — $0.27/M, score 22.9
Qwen: Qwen3.5-35B-A3B — $0.14/M, score 19.3
Qwen: Qwen3.5 397B A17B — $0.5/M, score 21.4
Qwen: Qwen3.5-9B — $0.17/M, score 13.3
Qwen: Qwen3.5-9B (batch) — $0.17/M, score 21.8
Qwen: Qwen3.6 27B — $0.25/M, score 21.4
Qwen: Qwen3.6 35B A3B — $0.1/M, score 18.2
Qwen: Qwen3.6 Max Preview — $1.027/M, score 28.4
Qwen: Qwen3.6 Plus — $0.325/M, score 27.0
Qwen: Qwen3.7 Max — $1.475/M, score 29.5
Qwen: Qwen3.7 Plus — $0.32/M, score 25.2
Qwen: Qwen3.7 Plus (batch) — $0.23/M, score 25.2
Qwen: Qwen3.8 2.4T A95B — $2/M, score 39.9
Qwen: Qwen3.8 2.4T A95B (batch) — $2/M, score 39.9
Qwen: Qwen3.8 27B — $0.2/M, score 33.7
Qwen: Qwen3.8 Max — $2/M, score 53.4
Qwen: Qwen3.8 Max (0902) — $2/M, score 45.4
Reka Flash 3 — $0.1/M, score 6.4
Step 3.5 Flash — $0.105/M, score 17.0
Step 3.7 Flash — $0.202/M, score 19.5
Step 5 Preview — $1.046/M, score 43.7
Hy3 preview — $0.18/M, score 25.3
Inkling — $1/M, score 25.0
Inkling Small — $0.58/M, score 25.7
Thinking Machines: Inkling Small (batch) — $0.5/M, score 26.1
Thinking Machines: Inkling (batch) — $1/M, score 25.0
Solar Mini 4 — $0.1/M, score 24.1
Upstage: Solar Pro 3 — $0.15/M, score 7.8
Solar Pro 4 — $0.3/M, score 28.2
SpaceXAI: Grok 4.20 — $1.25/M, score 25.7
SpaceXAI: Grok 4.3 — $1.25/M, score 24.9
SpaceXAI: Grok 4.3 (batch) — $1/M, score 24.9
SpaceXAI: Grok 4.5 — $2/M, score 38.8
SpaceXAI: Grok 4.6 — $2/M, score 44.3
SpaceXAI: Grok 4.7 — $2/M, score 46.4
SpaceXAI: Grok Build 0.1 — $1/M, score 27.2
MiMo-V2.5 — $0.14/M, score 21.8
MiMo-V2.5-Pro — $0.435/M, score 26.0
MiMo-V2.6-Flash — $0.14/M, score 37.9
MiMo-V2.6-Pro — $0.435/M, score 46.3
Z.ai: GLM 4.5 — $0.6/M, score 12.8
Z.ai: GLM 4.5 Air — $0.13/M, score 11.1
Z.ai: GLM 4.5V — $0.6/M, score 7.6
Z.ai: GLM 4.6 — $0.55/M, score 18.5
Z.ai: GLM 4.6V — $0.3/M, score 11.2
Z.ai: GLM 4.7 — $0.54/M, score 22.2
Z.ai: GLM 4.7 Flash — $0.061/M, score 14.9
Z.ai: GLM 5 — $1/M, score 27.9
Z.ai: GLM 5 Turbo — $1.2/M, score 26.6
Z.ai: GLM 5.1 — $1.4/M, score 26.1
Z.ai: GLM 5.2 — $0.034/M, score 33.7
Z.ai: GLM 5.2 (batch) — $0.7/M, score 33.7
Z.ai: GLM 5.3 — $0.091/M, score 44.8
Z.ai: GLM 5.3 Flash — $0.15/M, score 41.8
Z.ai: GLM 5.3 Flash (batch) — $0.05/M, score 41.8
Z.ai: GLM 5.3 (batch) — $0.45/M, score 44.8
Z.ai: GLM 5V Turbo — $1.2/M, score 23.5
Trinity Large Thinking
Input price per million tokens (log scale)
Index
The stepped line is the efficient frontier: at each price, the best score available for that money or less. A model sitting on it is not being beaten by anything cheaper. Price is log-scaled because listed rates span four orders of magnitude. Only models with both a listed price and a score on this benchmark can appear.
Catalog activity
Change log Field-level changes detected between successful source imports.
Full change log
Oct 24, 2026 Max Output Tokens 80000 → 262144
Oct 24, 2026 Context Length 262144 → 524288
Oct 24, 2026 Price Completion 0.7999999999999999 → 0.9
Oct 24, 2026 Max Output Tokens 262144 → 80000
Oct 24, 2026 Context Length 524288 → 262144
Oct 24, 2026 Price Completion 0.9 → 0.7999999999999999
Oct 24, 2026 Max Output Tokens 80000 → 262144
Oct 24, 2026 Context Length 262144 → 524288
Oct 24, 2026 Price Completion 0.7999999999999999 → 0.9
Oct 24, 2026 Max Output Tokens 262144 → 80000
Provenance
Sources & verification Every figure on this page traces back to one of these records.
Methodology
Last verified Oct 24, 2026
Status Source-linked
Confidence Medium
Catalog source Models.dev
Public API
Use this record Fetch the complete source-linked model record. No key, no account, no rate-limited tier.
API documentation
Endpoint Copy
GET https://modelbench.lol/api/v1/models/arcee-ai/trinity-large-thinkingcurl Copy
curl "https://modelbench.lol/api/v1/models/arcee-ai/trinity-large-thinking"
Common questions
Frequently asked questions Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.
What is Trinity Large Thinking?
Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use. It is published by Arcee Ai and catalogued here from Models.dev.
How much does Trinity Large Thinking cost?
Listed input pricing starts at $0.25 per million tokens from NanoGPT.
What is the context length of Trinity Large Thinking?
Trinity Large Thinking accepts up to 524.288K tokens of context and returns up to 262.144K output tokens.
Does Trinity Large Thinking support tool calling and structured output?
Provider catalogs list support for tool calling, and reasoning.
Which providers serve Trinity Large Thinking?
5 providers list this model: NanoGPT, Kilo Gateway, Vercel AI Gateway, OpenRouter, Arcee.
Are the weights for Trinity Large Thinking open?
Yes. The weights are published and downloadable from Hugging Face under the OpenMDW-1.1 license.
When was Trinity Large Thinking released?
The catalog records a release date of 2026-04-01, last verified Oct 24, 2026.
OpenRouter