HASTATAgent stack guide inferx
InferX
All current catalogue offerings from this provider. Documentation remains authoritative.
Fresh · fetched 2026-08-17T02:11:57.739Z · Models.dev(opens in a new tab)
12 offerings
| Model | Context / output | Capabilities | Lowest input | Providers |
|---|---|---|---|---|
| DeepSeek V4 Flashdeepseek-v4-flash · deepseek-flash | 1.05MOutput 1.05M | Tool callingReasoningJSONOpen weights | $0.00out $0.00 | 55fresh |
| Qwen3-Embedding-8Bqwen3-embedding-8b · qwen | 40KOutput 32K | Open weights | $0.00out $0.00 | 7fresh |
| Qwen3.6 35B A3B FP8qwen3.6-35b-a3b-fp8 · qwen | 256KOutput 256K | Tool callingReasoningImage inputJSONOpen weights | $0.00out $0.00 | 5fresh |
| Qwen3 Coder Next FP8qwen3-coder-next-fp8 · qwen | 256KOutput 256K | Tool callingJSONOpen weights | $0.00out $0.00 | 2fresh |
| Agents-A1agents-a1 | 262KOutput 100K | Tool callingReasoningImage inputOpen weights | $0.00out $0.00 | 1fresh |
| Qwen3-Coder-Next-FP8-no-thinkingqwen3-coder-next-fp8-no-thinking · qwen | 260KOutput 64K | Tool callingJSONOpen weights | $0.00out $0.00 | 1fresh |
| Qwen3.6 27B FP8qwen3.6-27b-fp8 · qwen | 256KOutput 64K | Tool callingReasoningImage inputJSONOpen weights | $0.00out $0.00 | 1fresh |
| Ornith-1.0-35B-FP8ornith-1.0-35b-fp8 · ornith | 262KOutput 100K | Tool callingReasoningImage inputOpen weights | $0.00out $0.00 | 1fresh |
| Qwen3.6-35B-A3B-fp8-no-thinkingqwen3.6-35b-a3b-fp8-no-thinking · qwen | 262KOutput 64K | Tool callingImage inputJSONOpen weights | $0.00out $0.00 | 1fresh |
| Gemma 4 31B IT FP8gemma-4-31b-it-fp8 · gemma | 256KOutput 32K | Tool callingReasoningImage inputJSONOpen weights | $0.00out $0.00 | 1fresh |
| mimo-v25mimo-v25 · mimo | 1MOutput 100K | Tool callingReasoningImage inputOpen weights | $0.00out $0.00 | 1fresh |
| Devstral-2-123B-Instruct-2512-int4-AutoRounddevstral-2-123b-instruct-2512-int4-autoround · devstral | 128KOutput 128K | Tool callingOpen weights | $0.00out $0.00 | 1fresh |