Model provider
AI/ML API
Explore models served by AI/ML API.
172models
Pricing & endpoints
177 offers · USD per million tokens| Model | Provider | Model ID | Context | Output | Input / output · 1M | Reasoning | Tools | Structured | Route |
|---|---|---|---|---|---|---|---|---|---|
| Hermes 3 70B Instruct | AI/ML API | nousresearch/hermes-3-llama-3.1-70b | 131,072 | 16,384 | $0.96278 / $0.96278 | No | No | Yes | View route |
| Gemini 3.8 Flash | AI/ML API | google/gemini-3.8-flash | 1,048,576 | 65,536 | $0.975 / $4.875 | Yes | Yes | Yes | View route |
| Gemini 3.7 Flash | AI/ML API | google/gemini-3.7-flash | 1,048,576 | 65,536 | $0.975 / $4.875 | Yes | Yes | Yes | View route |
| Gemini 3.8 Flash | AI/ML API | google/gemini-3-8-flash | 1,048,576 | 65,536 | $0.975 / $4.875 | Yes | Yes | Yes | View route |
| Weaver (alpha) | AI/ML API | mancer/weaver | 8,000 | 2,000 | $1.03155 / $1.3754 | No | No | No | View route |
| Nova Pro 1.0 | AI/ML API | amazon/nova-pro-v1 | 300,000 | 5,120 | $1.10032 / $4.40128 | No | Yes | No | View route |
| Morph V3 Fast | AI/ML API | morph/morph-v3-fast | 81,920 | 38,000 | $1.10032 / $1.65048 | No | No | No | View route |
| Aion-RP 1.0 (8B) | AI/ML API | aion-labs/aion-rp-llama-3.1-8b | 32,768 | 32,768 | $1.10032 / $2.20064 | No | No | No | View route |
| Hy4 preview | AI/ML API | tencent/hy4-preview | 1,048,576 | 64,000 | $1.147084 / $3.439875 | Yes | Yes | — | View route |
| Relace Apply 3 | AI/ML API | relace/relace-apply-3 | 256,000 | 128,000 | $1.16909 / $1.71925 | No | No | No | View route |
| DeepSeek V4 Pro | AI/ML API | deepseek/deepseek-v4-pro | 1,000,000 | 384,000 | $1.17 / $3.51 | Yes | Yes | Yes | View route |
| Morph V3 Large | AI/ML API | morph/morph-v3-large | 262,144 | 131,072 | $1.23786 / $2.61326 | No | No | Yes | View route |
| Sonar | AI/ML API | perplexity/sonar | 128,000 | 100,000 | $1.30 / $1.30 | No | No | — | View route |
| Llama-3.3-70B-Instruct | AI/ML API | meta-llama/Llama-3.3-70B-Instruct-Turbo | 128,000 | 127,000 | $1.352 / $1.352 | No | Yes | — | View route |
| Gemma 4 31B IT | AI/ML API | google/gemma-4-31b-it | 256,000 | 16,384 | $1.361646 / $2.049346 | Yes | Yes | Yes | View route |
| Hermes 3 405B Instruct | AI/ML API | nousresearch/hermes-3-llama-3.1-405b | 131,072 | 16,384 | $1.3754 / $1.3754 | No | No | Yes | View route |
| Relace Search | AI/ML API | relace/relace-search | 256,000 | 128,000 | $1.3754 / $4.1262 | No | Yes | No | View route |
| Inkling | AI/ML API | thinkingmachines/inkling | 1,048,576 | 1,048,576 | $1.3754 / $5.57037 | Yes | Yes | — | View route |
| Claude Haiku 4.5 (latest) | AI/ML API | anthropic/claude-haiku-4.5 | 200,000 | 64,000 | $1.3754 / $6.877 | Yes | Yes | — | View route |
| Step 5 Preview | AI/ML API | stepfun/step-5-preview | 1,000,000 | 64,000 | $1.3754 / $3.71358 | Yes | Yes | Yes | View route |
| Qwen3-Coder 480B-A35B Instruct | AI/ML API | alibaba/qwen3-coder-480b-a35b-instruct | 262,000 | 65,536 | $1.3754 / $6.705075 | No | Yes | — | View route |
| Kimi K2 Instruct 0905 | AI/ML API | moonshotai/kimi-k2-0905 | 262,144 | 98,304 | $1.3754 / $4.1262 | No | Yes | — | View route |
| o3-mini | AI/ML API | openai/o3-mini | 200,000 | 100,000 | $1.43 / $5.72 | Yes | Yes | Yes | View route |
| GLM-5-Turbo | AI/ML API | z-ai/glm-5-turbo | 262,144 | 131,072 | $1.56 / $5.20 | Yes | Yes | Yes | View route |
| GLM-5V-Turbo | AI/ML API | z-ai/glm-5v-turbo | 202,752 | 131,072 | $1.56 / $5.20 | Yes | Yes | — | View route |
| X-Ai/Grok-4-Fast-Non-Reasoning | AI/ML API | x-ai/grok-4-fast-non-reasoning | 2,000,000 | 1,999,000 | $1.625 / $3.25 | No | Yes | No | View route |
| Grok 4.20 (Non-Reasoning) | AI/ML API | x-ai/grok-4-20-0309-non-reasoning | 2,000,000 | 1,999,000 | $1.625 / $3.25 | No | Yes | Yes | View route |
| GPT-5.1 | AI/ML API | openai/gpt-5-1 | 400,000 | 128,000 | $1.625 / $13.00 | Yes | Yes | Yes | View route |
| Muse Spark 1.1 | AI/ML API | meta/muse-spark-1.1 | 1,048,576 | 131,072 | $1.71925 / $5.84545 | Yes | Yes | Yes | View route |
| Muse Spark 1.3 | AI/ML API | meta/muse-spark-1.3 | 1,048,576 | 131,072 | $1.71925 / $5.84545 | Yes | Yes | Yes | View route |
| Muse Spark 1.2 | AI/ML API | meta/muse-spark-1.2 | 1,048,576 | 131,072 | $1.71925 / $5.84545 | Yes | Yes | Yes | View route |
| GLM-5.2 | AI/ML API | zhipu/glm-5.2 | 1,000,000 | 131,072 | $1.82 / $5.72 | Yes | Yes | Yes | View route |
| GLM-5.3 | AI/ML API | zhipu/glm-5.3 | 1,024,000 | 131,072 | $1.82 / $5.72 | Yes | Yes | Yes | View route |
| GPT-5 | AI/ML API | openai/gpt-5 | 400,000 | 128,000 | $1.891175 / $15.1294 | Yes | Yes | Yes | View route |
| Gemini 3.6 Flash | AI/ML API | google/gemini-3.6-flash | 1,048,576 | 65,536 | $1.95 / $9.75 | Yes | Yes | Yes | View route |
| Llama 3.1 Euryale 70B v2.2 | AI/ML API | sao10k/l3.1-euryale-70b | 131,072 | 16,384 | $1.99488 / $1.99488 | No | Yes | Yes | View route |
| Mistral Medium 3.5 | AI/ML API | mistralai/mistral-medium-3-5 | 262,144 | 209,715 | $2.0631 / $10.3155 | Yes | Yes | Yes | View route |
| GPT-5.4 mini | AI/ML API | openai/gpt-5.4-mini | 400,000 | 128,000 | $2.0631 / $12.3786 | Yes | Yes | Yes | View route |
| Gemini Flash Latest | AI/ML API | google/gemini-flash-latest | 1,048,576 | 65,536 | $2.0631 / $12.3786 | Yes | Yes | Yes | View route |
| Qwen Max | AI/ML API | alibaba/qwen-max | 32,000 | 8,192 | $2.08 / $8.32 | No | Yes | — | View route |
81–120 of 177
Prices, limits and configurations apply to each serving offer. Open a model for its complete specifications and provider comparison.