HASTATAgent stack guide Models
Model catalogue
A server-filtered distinct-model index with every provider offer preserved.
Fresh · fetched 2026-08-17T14:14:03.963Z · Models.dev(opens in a new tab)
2233 distinct modelsLowest reported provider price in USD per 1M tokens; unavailable is not free.
| Model | Context / output | Capabilities | Lowest input | Providers |
|---|---|---|---|---|
| Doubao Seed 2.0 Prodoubao-seed-2.0-pro | 256KOutput 128K | Tool callingReasoningImage input | $0.45out $2.24 | 3fresh |
| Step 3.5 Flashstep-3-5-flash | 256KOutput 128K | Tool callingReasoningJSONOpen weights | $0.10out $0.30 | 1fresh |
| GLM 5 Thinkingzai-org/glm-5:thinking · glm | 200KOutput 128K | Tool callingReasoningJSONOpen weights | $0.50out $2.55 | 1fresh |
| GLM 5 Originalzai-org/glm-5-original · glm | 200KOutput 128K | Tool callingReasoningJSONOpen weights | $1.00out $3.20 | 1fresh |
| GLM 5 Original Thinkingzai-org/glm-5-original:thinking · glm | 200KOutput 128K | Tool callingReasoningJSONOpen weights | $1.00out $3.20 | 1fresh |
| Qwen3 Max Thinkingqwen/qwen3-max-thinking · qwen | 256KOutput 64K | Tool callingReasoningJSON | $0.78out $3.90 | 2fresh |
| GLM 4.7 Flashglm-4-7-flash · glm-flash | 200KOutput 128K | Tool callingReasoningJSONOpen weights | $0.00out $0.00 | 1fresh |
| GLM 4.7 Flash Originalzai-org/glm-4.7-flash-original · glm | 200KOutput 128K | Tool callingReasoningJSONOpen weights | $0.070out $0.40 | 1fresh |
| GLM-4.7zai-org/glm-4.7-maas · glm | 200KOutput 128K | Tool callingReasoningJSONOpen weights | $0.60out $2.20 | 1fresh |
| Qwen3 Coder 480B A35B Instructqwen3-coder-480b-a35b-instruct | 256KOutput 256K | Tool callingJSONOpen weights | $0.00out $0.00 | 15fresh |
| Kimi-K2-0905kimi-k2-0905 · kimi-k2 | 256KOutput 256K | Tool callingJSONOpen weights | $0.00out $0.00 | 8fresh |
| MiniMax M1 80Kminimaxai/minimax-m1-80k · minimax | 1MOutput 128K | Tool callingReasoningOpen weights | $0.55out $2.20 | 3fresh |
| Qwen3 235B A22B FP8qwen3-235b-a22b-fp8 · qwen | 40KOutput 20K | Tool callingReasoningJSONOpen weights | $0.20out $0.80 | 3fresh |
| GLM 4.7 Originalzai-org/glm-4.7-original · glm | 200KOutput 64K | Tool callingReasoningJSONOpen weights | $0.60out $2.20 | 1fresh |
| GLM 4.7 Original Thinkingzai-org/glm-4.7-original:thinking · glm | 200KOutput 64K | Tool callingReasoningJSONOpen weights | $0.60out $2.20 | 1fresh |
| GLM 4.7 Thinkingzai-org/glm-4.7:thinking · glm | 200KOutput 64K | Tool callingReasoningJSONOpen weights | $0.20out $0.80 | 1fresh |
| GLM-4.7zai.glm-4.7 · glm | 200KOutput 128K | Tool callingReasoningJSONOpen weights | $0.60out $2.20 | 1fresh |
| Devstral 2devstral-2512 · devstral | 256KOutput 256K | Tool callingJSONOpen weights | $0.40out $2.00 | 6fresh |
| GLM-4.6V FlashXglm-4.6v-flashx · glm | 128KOutput 16K | Tool callingReasoningImage inputJSON | $0.040out $0.40 | 1fresh |
| Grok-4.1-Fast-Reasoningxai/grok-4.1-fast-reasoning · grok | 2MOutput 1M | Tool callingReasoningImage input | $0.20out $0.50 | 2fresh |
| GPT-5.1openai/gpt-5.1-2025-11-13 · gpt | 1MOutput 32K | Tool callingReasoningJSON | $1.25out $10.00 | 1fresh |
| Kimi K2 Thinkingmoonshotai/kimi-k2-thinking-maas · kimi-thinking | 256KOutput 256K | Tool callingReasoningJSONOpen weights | $0.60out $2.50 | 1fresh |
| Kimi K2 Thinking Turbokimi-k2-thinking-turbo · kimi-thinking | 256KOutput 256K | Tool callingReasoningOpen weights | $1.15out $8.00 | 4fresh |
| nemotron-nano-v2-12bnemotron-nano-v2-12b | 128KOutput 128K | Tool callingReasoningImage inputJSON | $0.24out $0.71 | 1fresh |
| Nemotron-nano 12b v2-vlnemotron-nano-12b-v2-vl · nemotron | 128KOutput 128K | Tool callingReasoningImage inputOpen weights | $0.00out $0.00 | 3fresh |
| GLM 4.6 Thinkingz-ai/glm-4.6:thinking · glm | 200KOutput 64K | Tool callingReasoningJSONOpen weights | $0.35out $1.40 | 1fresh |
| Qwen3 Omni 30B A3B Thinkingqwen/qwen3-omni-30b-a3b-thinking | 64KOutput 16K | Tool callingReasoningImage inputJSONOpen weights | $0.25out $0.97 | 1fresh |
| x-AI/Grok-4-Fastx-ai/grok-4-fast | 2MOutput 2M | Tool callingReasoningImage input | $0.20out $0.50 | 2fresh |
| Kimi K2kimi-k2 | 256KOutput 256K | Tool callingJSONOpen weights | $0.00out $0.00 | 8fresh |
| NVIDIA Nemotron Nano 9B v2nvidia.nemotron-nano-9b-v2 · nemotron | 128KOutput 128K | Tool callingReasoningJSONOpen weights | $0.060out $0.23 | 2fresh |
| Qwen3 235B A22B Instructqwen/qwen3-235b-a22b-instruct-2507-maas · qwen | 256KOutput 16K | Tool callingReasoningJSONOpen weights | $0.22out $0.88 | 1fresh |
| Claude 3.7 Sonnetclaude-3.7-sonnet | 200KOutput 128K | Tool callingReasoningImage input | $3.00out $15.00 | 3fresh |
| GPT OSS 120Bdatabricks-gpt-oss-120b · gpt-oss | 128KOutput 32K | Tool callingReasoningJSONOpen weights | $0.072out $0.28 | 2fresh |
| GPT OSS 20Bdatabricks-gpt-oss-20b · gpt-oss | 128KOutput 32K | Tool callingReasoningJSONOpen weights | $0.050out $0.20 | 2fresh |
| Codestral 2508codestral-2508 · mistral | 256KOutput 256K | Tool callingJSONOpen weights | $0.30out $0.90 | 5fresh |
| Llama 3.3 Nemotron Super 49B v1.5llama-3.3-nemotron-super-49b-v1.5 · nemotron | 128KOutput 128K | Tool callingReasoningJSONOpen weights | $0.00out $0.00 | 2fresh |
| OpenAI o3 Deep Researchopenai/o3-deep-research · o | 200KOutput 100K | Tool callingReasoningImage input | $9.00out $36.00 | 3fresh |
| Gemma 3n E4b Itgoogle/gemma-3n-e4b-it | 128KOutput 32K | Tool callingImage inputJSONOpen weights | $0.00out $0.00 | 4fresh |
| pixtral-large-2502pixtral-large-2502 | 128KOutput 128K | Tool callingReasoningImage inputJSON | $1.99out $5.98 | 1fresh |
| Mistral Medium 3mistral-medium-2505 · mistral-medium | 128KOutput 128K | Tool callingImage inputJSON | $0.40out $2.00 | 5fresh |
| llama-3.1-nemotron-ultra-253b-v1llama-3.1-nemotron-ultra-253b-v1 | 128KOutput 128K | Tool callingReasoningJSONOpen weights | $0.00out $0.00 | 2fresh |
| Qwen: QvQ Maxqvq-max · qwen | 128KOutput 8K | Tool callingReasoningImage inputOpen weights | $1.15out $4.59 | 3fresh |
| GPT-4ogpt-4o-2024-11-20 · gpt | 128KOutput 16K | Tool callingImage inputJSON | $2.50out $10.00 | 8fresh |
| GPT-4ogpt-4o · gpt | 128KOutput 128K | Tool callingImage inputJSON | $2.50out $10.00 | 21fresh |
| GPT-4ogpt-4o-2024-08-06 · gpt | 128KOutput 16K | Tool callingImage inputJSON | $2.50out $10.00 | 7fresh |
| GPT-4o minigpt-4o-mini · gpt-mini | 128KOutput 128K | Tool callingImage inputJSON | $0.14out $0.54 | 20fresh |
| OpenAI GPT-4o miniopenai-gpt-4o-mini · gpt-mini | 128KOutput 16K | Tool callingReasoningImage inputJSON | $0.15out $0.60 | 1fresh |
| GPT-4ogpt-4o-2024-05-13 · gpt | 128KOutput 4K | Tool callingImage inputJSON | $5.00out $15.00 | 5fresh |
| GPT-4 Turbogpt-4-turbo · gpt | 128KOutput 4K | Tool callingImage inputJSON | $9.00out $27.00 | 14fresh |
| Holo3-35B-A3Bholo3-35b-a3b | 64KOutput 64K | Tool callingReasoningImage inputJSONOpen weights | $0.25out $1.80 | 1fresh |