HASTATAgent stack guide Models
Model catalogue
A server-filtered distinct-model index with every provider offer preserved.
Fresh · fetched 2026-08-17T08:12:22.311Z · 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 |
|---|---|---|---|---|
| Claude 4 Sonnet Thinkingclaude-sonnet-4-thinking · claude-sonnet | 1MOutput 64K | Tool callingReasoningImage inputJSON | $3.00out $15.00 | 1fresh |
| Claude 4 Sonnet Thinkingclaude-sonnet-4-thinking:64000 · claude-sonnet | 1MOutput 64K | Tool callingReasoningImage inputJSON | $3.00out $15.00 | 1fresh |
| Claude 4 Sonnet Thinkingclaude-sonnet-4-thinking:8192 · claude-sonnet | 1MOutput 64K | Tool callingReasoningImage inputJSON | $3.00out $15.00 | 1fresh |
| Claude 4 Sonnet Thinkingclaude-sonnet-4-thinking:32768 · claude-sonnet | 1MOutput 64K | Tool callingReasoningImage inputJSON | $3.00out $15.00 | 1fresh |
| Claude Sonnet 4 (latest)claude-sonnet-4@eu · claude-sonnet | 1MOutput 64K | Tool callingReasoningImage inputJSON | $3.00out $15.00 | 1fresh |
| GPT-4.1 minigpt-4.1-mini · gpt-mini | 1.05MOutput 1.05M | Tool callingImage inputJSON | $0.36out $1.40 | 24fresh |
| GPT-4.1 nanogpt-4.1-nano · gpt-nano | 1.05MOutput 1.05M | Tool callingImage inputJSON | $0.080out $0.26 | 21fresh |
| GPT-4.1gpt-4.1 · gpt | 1.05MOutput 1.05M | Tool callingImage inputJSON | $1.80out $7.20 | 26fresh |
| Llama 4 Scout 17B 16E Instructllama-4-scout-17b-16e-instruct · llama | 320KOutput 128K | Tool callingImage inputJSONOpen weights | $0.10out $0.30 | 6fresh |
| Claude Sonnet 3.7claude-3-7-sonnet-20250219 · claude-sonnet | 200KOutput 64K | Tool callingReasoningImage inputJSON | $3.00out $15.00 | 2fresh |
| DeepSeek V4 Proumans-deepseek-v4-pro-0813 · deepseek-thinking | 1.05MOutput 384K | Tool callingReasoningJSON | $0.00out $0.00 | 2fresh |
| Grok 4.6xai/grok-latest · grok | 500KOutput 500K | Tool callingReasoningImage inputJSON | $2.00out $6.00 | 1fresh |
| NVIDIA Nemotron 3.5 Lightning 30Bnvidia-nemotron-3-5-lightning-30b-a3b · nemotron | 1MOutput 32K | Tool callingReasoningJSONOpen weights | $0.10out $0.25 | 1fresh |
| DeepSeek V4 Flash 0731 Fastdeepseek-v4-flash-0731-fast · deepseek-flash | 1MOutput 32K | Tool callingReasoningJSONOpen weights | $0.35out $0.70 | 1fresh |
| MAI-Code-1.1-Flashmai-code-1.1-flash · mai | 256KOutput 128K | Tool callingReasoningImage inputJSON | $0.20out $1.20 | 1fresh |
| Nvidia Nemotron 3.5 Lightning Thinkingnvidia/nemotron-3.5-lightning:thinking · nemotron | 1MOutput 64K | Tool callingReasoningJSONOpen weights | $0.050out $0.20 | 1fresh |
| Muse Glimmer 30Bmuse-glimmer-30b-tr · muse | 128KOutput 128K | Tool callingReasoningImage inputJSONOpen weights | $2.00out $5.00 | 1fresh |
| InclusionAI Ling 3.0 Flashling-3.0-flash · ling | 256KOutput 256K | Tool callingReasoningOpen weights | $0.021out $0.063 | 5fresh |
| Qwen3.8 Max Thinkingqwen3.8-max:thinking · qwen | 991KOutput 128K | Tool callingReasoningImage inputJSON | $2.00out $6.00 | 1fresh |
| DeepSeek V4 Flash 0731 TEEdeepseek-ai/deepseek-v4-flash-0731-tee · deepseek-flash | 1.05MOutput 128K | Tool callingReasoningJSONOpen weights | $0.14out $0.28 | 1fresh |
| DeepSeek V4 Flash Latestdeepseek/deepseek-v4-flash-latest · deepseek | 1.05MOutput 384K | Tool callingReasoningJSONOpen weights | $0.14out $0.28 | 1fresh |
| DeepSeek V4 Flash Latest~deepseek/deepseek-v4-flash-latest · deepseek | 1.31MOutput 256K | Tool callingReasoningJSON | $0.060out $0.12 | 2fresh |
| DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731:thinking · deepseek-flash | 1MOutput 128K | Tool callingReasoningJSONOpen weights | $0.14out $0.28 | 1fresh |
| DeepSeek V4 Flash 0731deepseek-v4-flash-0731@eu · deepseek-flash | 1.05MOutput 128K | Tool callingReasoningJSONOpen weights | $0.14out $0.28 | 1fresh |
| MiMo V2.5 Proxiaomi/mimo-v2.5-pro-crof · mimo-v2.5-pro | 1MOutput 128K | Tool callingReasoningJSONOpen weights | $0.40out $0.80 | 1fresh |
| MiMo V2.5 Pro Thinkingxiaomi/mimo-v2.5-pro-crof:thinking · mimo-v2.5-pro | 1MOutput 128K | Tool callingReasoningJSONOpen weights | $0.40out $0.80 | 1fresh |
| Qwen3.7 Flash Thinkingqwen3.7-flash:thinking · qwen | 961KOutput 64K | Tool callingReasoningImage inputJSON | $0.030out $0.13 | 1fresh |
| GPT-5.6 Lunadatabricks-gpt-5-6-luna · gpt-luna | 400KOutput 128K | Tool callingReasoningImage inputJSON | $1.00out $6.00 | 1fresh |
| Laguna XS 2.1laguna-xs-2.1 · laguna | 256KOutput 32K | Tool callingReasoningOpen weights | $0.00out $0.00 | 5fresh |
| MiMo V2 Omnimimo-v2-omni · mimo-v2-omni | 265KOutput 265K | Tool callingReasoningImage inputOpen weights | $0.14out $0.28 | 3fresh |
| GLM 5.2zai-org-glm-5-2 · glm | 1MOutput 128K | Tool callingReasoningJSONOpen weights | $1.40out $4.40 | 1fresh |
| GLM 5.2z-ai/glm-5.2-free · glm | 1MOutput 128K | Tool callingReasoningJSONOpen weights | $0.00out $0.00 | 1fresh |
| GLM 5.2 FP4glm-5.2-fp4 · glm | 1.05MOutput 128K | Tool callingReasoningJSONOpen weights | $1.12out $4.40 | 1fresh |
| GLM 5.2 TEEzai-org/glm-5.2-tee · glm | 1.05MOutput 64K | Tool callingReasoningJSONOpen weights | $1.25out $3.95 | 1fresh |
| GLM 5.2 Thinkingzai-org/glm-5.2:thinking · glm | 1.05MOutput 128K | Tool callingReasoningJSONOpen weights | $0.42out $1.32 | 1fresh |
| GLM 5.2 Thinking TEEtee/glm-5.2:thinking · glm | 1.05MOutput 128K | Tool callingReasoningJSONOpen weights | $1.40out $4.60 | 1fresh |
| GLM-5.2databricks-glm-5-2 · glm | 1MOutput 128K | Tool callingReasoningJSONOpen weights | $1.40out $4.40 | 1fresh |
| GLM-5.2glm-5.2@eu · glm | 1.05MOutput 128K | Tool callingReasoningJSONOpen weights | $1.20out $4.20 | 1fresh |
| GLM-5.2 Cavemanglm-5.2-caveman · glm | 1MOutput 128K | Tool callingReasoningJSONOpen weights | $1.25out $5.02 | 1fresh |
| GLM-5.2 Caveman Liteglm-5.2-caveman-lite · glm | 1MOutput 128K | Tool callingReasoningJSONOpen weights | $1.25out $5.02 | 1fresh |
| GLM-5.2 Caveman Ultraglm-5.2-caveman-ultra · glm | 1MOutput 128K | Tool callingReasoningJSONOpen weights | $1.25out $5.02 | 1fresh |
| GLM-5.2 Honeyglm-5.2-honey · glm | 1MOutput 128K | Tool callingReasoningJSONOpen weights | $1.25out $5.02 | 1fresh |
| GLM-5.2 Honey Liteglm-5.2-honey-lite · glm | 1MOutput 128K | Tool callingReasoningJSONOpen weights | $1.25out $5.02 | 1fresh |
| GLM-5.2 Honey Ultraglm-5.2-honey-ultra · glm | 1MOutput 128K | Tool callingReasoningJSONOpen weights | $1.25out $5.02 | 1fresh |
| GLM-5.2 Ponytailglm-5.2-ponytail · glm | 1MOutput 128K | Tool callingReasoningJSONOpen weights | $1.25out $5.02 | 1fresh |
| GLM-5.2 Ponytail Liteglm-5.2-ponytail-lite · glm | 1MOutput 128K | Tool callingReasoningJSONOpen weights | $1.25out $5.02 | 1fresh |
| GLM-5.2 Ponytail Ultraglm-5.2-ponytail-ultra · glm | 1MOutput 128K | Tool callingReasoningJSONOpen weights | $1.25out $5.02 | 1fresh |
| GLM5.2-Fastglm5.2-fast · glm | 1.05MOutput 128K | Tool callingReasoningJSONOpen weights | $3.00out $10.25 | 1fresh |
| GLM-5.1glm-5-1 · glm | 202KOutput 128K | Tool callingReasoningJSONOpen weights | $0.00out $0.00 | 2fresh |
| GLM 5V Turboz-ai-glm-5v-turbo · glm | 200KOutput 32K | Tool callingReasoningImage inputJSON | $1.50out $5.00 | 1fresh |