HASTATAgent stack guide Models
Model catalogue
A server-filtered distinct-model index with every provider offer preserved.
Fresh · fetched 2026-08-17T02:11:57.739Z · Models.dev(opens in a new tab)
2237 distinct modelsLowest reported provider price in USD per 1M tokens; unavailable is not free.
| Model | Context / output | Capabilities | Lowest input | Providers |
|---|---|---|---|---|
| DeepSeek-V3.1deepseek-v3.1 | 164KOutput 164K | Tool callingReasoningJSONOpen weights | $0.20out $0.70 | 15fresh |
| DeepSeek-R1-0528deepseek-r1-0528 | 164KOutput 164K | Tool callingReasoningJSONOpen weights | $0.40out $1.70 | 14fresh |
| Gemini 2.5 Flash 0520gemini-2.5-flash-preview-05-20 · gemini | 1.05MOutput 200K | Tool callingReasoningImage inputJSON | $0.14out $0.60 | 2fresh |
| Gemini 2.5 Flash Lite Previewgemini-2.5-flash-lite-preview-06-17 · gemini | 1.05MOutput 64K | Tool callingReasoningImage inputJSON | $0.090out $0.36 | 2fresh |
| Gemini 2.5 Pro Preview 0605gemini-2.5-pro-preview-06-05 · gemini | 1.05MOutput 200K | Tool callingReasoningImage inputJSON | $1.13out $9.00 | 2fresh |
| nova-2-litenova-2-lite | 1MOutput 1M | Tool callingReasoningImage inputJSON | $0.30out $2.50 | 2fresh |
| GLM 4.5 Airglm-4.5-air | 128KOutput 128K | Tool callingReasoningJSONOpen weights | $0.10out $0.29 | 18fresh |
| DeepSeek V3.1 Terminusdeepseek-v3.1-terminus · deepseek | 164KOutput 164K | Tool callingReasoningJSONOpen weights | $0.25out $0.70 | 11fresh |
| Qwen3 8Bqwen3-8b · qwen | 128KOutput 128K | Tool callingReasoningJSONOpen weights | $0.060out $0.060 | 8fresh |
| Qwen3 14Bqwen3-14b · qwen | 128KOutput 131K | Tool callingReasoningJSONOpen weights | $0.070out $0.24 | 7fresh |
| Claude Sonnet 4.5 Thinkingclaude-sonnet-4-5-20250929-thinking · claude-sonnet | 1MOutput 64K | Tool callingReasoningImage inputJSON | $3.00out $15.00 | 2fresh |
| DeepSeek/DeepSeek-V3.2-Expdeepseek/deepseek-v3.2-exp | 160KOutput 64K | Tool callingReasoningJSONOpen weights | $0.22out $0.33 | 5fresh |
| Gemini 2.5 Flash Previewgemini-2.5-flash-preview-09-2025 · gemini | 1.05MOutput 64K | Tool callingReasoningImage inputJSON | $0.30out $2.50 | 2fresh |
| Meta Llama 4 Scout 17B 16Ellama-4-scout · llama | 1.31MOutput 64K | Tool callingImage inputJSONOpen weights | $0.00out $0.00 | 5fresh |
| Qwen 3 235B A22Bqwen3-235b-a22b | 128KOutput 32K | Tool callingReasoningJSONOpen weights | $0.20out $0.50 | 9fresh |
| Gemini 2.5 Pro Preview 06-05google/gemini-2.5-pro-preview · gemini | 1.05MOutput 64K | Tool callingReasoningImage inputJSON | $1.25out $10.00 | 2fresh |
| OpenAI o4-mini highopenai/o4-mini-high · o-mini | 200KOutput 100K | Tool callingReasoningImage inputJSON | $1.10out $4.40 | 3fresh |
| nova-micro-v1nova-micro-v1 | 128KOutput 128K | Tool callingReasoningImage inputJSON | $0.035out $0.14 | 4fresh |
| Magistral Mediummagistral-medium-latest · magistral-medium | 128KOutput 16K | Tool callingReasoningImage inputJSONOpen weights | $2.00out $5.00 | 3fresh |
| DeepSeek R1 Distill Llama 70Bdeepseek-r1-distill-llama-70b · deepseek-thinking | 128KOutput 128K | Tool callingReasoningJSONOpen weights | $0.030out $0.13 | 7fresh |
| Llama-3.1-8B-Instructllama-3.1-8b-instruct · llama | 128KOutput 128K | Tool callingReasoningJSONOpen weights | $0.00out $0.00 | 12fresh |
| Llama 3.2 3B Instructllama-3.2-3b-instruct · llama | 128KOutput 128K | Tool callingReasoningJSONOpen weights | $0.00out $0.00 | 10fresh |
| Qwen3.8 27B TEEqwen/qwen3.8-27b-tee · qwen | 256KOutput 64K | Tool callingReasoningImage inputJSONOpen weights | $0.40out $3.00 | 1fresh |
| Dots3-Note Previewdots-studio/dots-3-note-preview | 384KOutput 384K | Tool callingReasoningImage inputJSONOpen weights | $0.10out $0.20 | 1fresh |
| Dots3-Note Previewdots-studio/dots-3-note-preview:free | 512KOutput 512K | Tool callingReasoningImage inputJSON | $0.00out $0.00 | 2fresh |
| Gemini 3.7 Flashgemini-3-7-flash · gemini-flash | 1MOutput 64K | Tool callingReasoningImage inputJSON | $1.88out $9.38 | 1fresh |
| Qwen3.8 27Bqwen3-8-27b · qwen | 256KOutput 32K | Tool callingReasoningImage inputJSONOpen weights | $0.17out $0.50 | 1fresh |
| Qwen3.8 27B Thinkingqwen3.8-27b:thinking · qwen | 256KOutput 32K | Tool callingReasoningImage inputJSONOpen weights | $0.40out $3.00 | 1fresh |
| Gemini 3.7 Flashvertex/gemini-3.7-flash@us · gemini-flash | 1.05MOutput 64K | Tool callingReasoningImage inputJSON | $0.75out $3.75 | 1fresh |
| Grok 4.6grok-4-6 · grok | 500KOutput 500K | Tool callingReasoningImage inputJSON | $2.00out $6.00 | 2fresh |
| Nemotron 3.5 Lightning 30B A3Bnemotron-3.5-lightning-30b-a3b · nemotron | 1MOutput 256K | Tool callingReasoningJSONOpen weights | $0.00out $0.00 | 2fresh |
| Sakana Namazusakana/sakana-namazu | 256KOutput 64K | Tool callingReasoningImage inputJSON | $0.95out $4.00 | 2fresh |
| Muse Spark 1.2muse-spark-1-2 · muse | 1.05MOutput 128K | Tool callingReasoningImage inputJSON | $1.25out $4.25 | 1fresh |
| Qwen3.8 Maxqwen3-8-max · qwen | 1MOutput 128K | Tool callingReasoningImage inputJSON | $2.00out $6.00 | 1fresh |
| Qwen3.5 122B-A10B FP8qwen/qwen3.5-122b-a10b-fp8 · qwen | 200KOutput 64K | Tool callingReasoningImage inputJSONOpen weights | $0.50out $3.97 | 1fresh |
| DeepSeek V4 Flashumans-deepseek-v4-flash-0731 · deepseek-flash | 1.05MOutput 384K | Tool callingReasoningJSONOpen weights | $0.00out $0.00 | 2fresh |
| Inkling Smalldeepinfra/thinkingmachines/inkling-small · ling | 512KOutput 1.05M | Tool callingReasoningImage inputJSONOpen weights | $0.45out $1.20 | 1fresh |
| Claude Opus 5claude-opus-5@eu · claude-opus | 1MOutput 128K | Tool callingReasoningImage inputJSON | $5.50out $27.50 | 1fresh |
| Fugu Ultra v1.1sakana/fugu-ultra-v1.1 · fugu | 1MOutput 16K | Tool callingReasoningImage inputJSON | $5.25out $31.50 | 1fresh |
| Qwen3 Next 80B A3B Instructqwen3-next-80b-a3b-instruct | 256KOutput 256K | Tool callingImage inputJSONOpen weights | $0.00out $0.00 | 19fresh |
| Laguna S 2.1laguna-s-2.1 · laguna | 1.05MOutput 128K | Tool callingReasoningOpen weights | $0.00out $0.00 | 6fresh |
| Gemini 3.5 Flash Litevertex/gemini-3.5-flash-lite@us · gemini-flash-lite | 1.05MOutput 64K | Tool callingReasoningImage inputJSON | $0.30out $2.50 | 1fresh |
| Gemini 3.5 Flash Litevertex/gemini-3.5-flash-lite@eu · gemini-flash-lite | 1.05MOutput 64K | Tool callingReasoningImage inputJSON | $0.30out $2.50 | 1fresh |
| Gemini 3.6 Flashvertex/gemini-3.6-flash@eu · gemini-flash | 1.05MOutput 64K | Tool callingReasoningImage inputJSON | $0.75out $3.75 | 1fresh |
| Gemini 3.6 Flashvertex/gemini-3.6-flash@us · gemini-flash | 1.05MOutput 64K | Tool callingReasoningImage inputJSON | $0.75out $3.75 | 1fresh |
| Kimi K3-256Kk3-256k · kimi-k3 | 256KOutput 128K | Tool callingReasoningImage inputJSONOpen weights | $0.00out $0.00 | 1fresh |
| Qwen3.7 Flashqwen3-7-flash · qwen | 1MOutput 64K | Tool callingReasoningImage inputJSON | $0.030out $0.13 | 1fresh |
| Agentic Chatduo-chat-gpt-5-6-sol · gpt-sol | 1.05MOutput 128K | Tool callingReasoningImage inputJSON | $0.00out $0.00 | 1fresh |
| Agentic Chatduo-chat-gpt-5-6-luna · gpt-luna | 1.05MOutput 128K | Tool callingReasoningImage inputJSON | $0.00out $0.00 | 1fresh |
| Agentic Chatduo-chat-gpt-5-6-terra · gpt-terra | 1.05MOutput 128K | Tool callingReasoningImage inputJSON | $0.00out $0.00 | 1fresh |