Listings
All listings: Together AI
Every listing for the models on page 9 of 14 of Together AI, including each model's other versions and routes. Back to Together AI
Sold by Together AI
25 listings on this page sold by Together AI.
Select a score for details.
About these columns
- llminfo IQ
- llminfo IQ (capability index). How llminfo IQ is computed
- Coding IQ
- llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
- Value
- Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
| Model | llminfo IQ | Coding IQ | Input $/1M | Output $/1M | Max Input Tokens | Value |
|---|---|---|---|---|---|---|
Trinity Mini πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.045 | $0.15 | 128K | βNot enough data yet |
Arize AI Qwen 2 1.5B Instructarize-ai/qwen-2-1.5b-instructarize-ai/qwen-2-1.5b-instruct | βNot enough data yet | βNot enough data yet | $0.10 | $0.10 | 33K | βNot enough data yet |
Llama-3-8B-Instruct-Lite πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.10 | $0.10 | βNot published by the provider | βNot enough data yet |
Salesforce Llama Rank V1 (8B) πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.10 | $0.10 | 8K | βNot enough data yet |
together-ai-up-to-4b Pricing tierThis is a separate pricing tier or billing meter that a provider lists under its own name, not a different model. | βNot enough data yet | βNot enough data yet | $0.10 | $0.10 | βNot published by the provider | βNot enough data yet |
RNJ-1 Instruct Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | βNot enough data yet | βNot enough data yet | $0.15 | $0.15 | 33K | βNot enough data yet |
Llama 3.1 8B Instruct Turbo πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | βNot enough data yet | βNot enough data yet | $0.18 | $0.18 | 131K | 24.9Poor value (24.9). Costs more per task than its benchmark results predict. A fair amount of data behind it. |
llama-3-8b-instruct-turbo πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | βNot enough data yet | βNot enough data yet | $0.18 | $0.18 | βNot published by the provider | βNot enough data yet |
alpaca-7b πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.20 | $0.20 | βNot published by the provider | βNot enough data yet |
CodeLlama-7b-Instruct-hf πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.20 | $0.20 | βNot published by the provider | βNot enough data yet |
GPT-JT-Moderation-6B πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.20 | $0.20 | βNot published by the provider | βNot enough data yet |
Meta Llama 3 8B Instruct Reference πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.20 | $0.20 | 8K | βNot enough data yet |
Nous-Capybara-7B-V1p9 πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.20 | $0.20 | βNot published by the provider | βNot enough data yet |
OLMo-7B πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.20 | $0.20 | βNot published by the provider | βNot enough data yet |
OLMo 7B Instruct πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.20 | $0.20 | βNot published by the provider | βNot enough data yet |
OLMo-7B-Twin-2T πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.20 | $0.20 | βNot published by the provider | βNot enough data yet |
Ripple 65B Preview NewReleased 4 Nov 2026 | βNot enough data yet | βNot enough data yet | $0.20cache read $0.02 | $0.60 | 131K | βNot enough data yet |
| βNot enough data yet | βNot enough data yet | $0.20 | $0.20 | βNot published by the provider | βNot enough data yet | |
StripedHyena-Hessian-7B πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.20 | $0.20 | βNot published by the provider | βNot enough data yet |
StripedHyena Nous 7B πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.20 | $0.20 | βNot published by the provider | βNot enough data yet |
together-ai-4.1b-8b Pricing tierThis is a separate pricing tier or billing meter that a provider lists under its own name, not a different model. | βNot enough data yet | βNot enough data yet | $0.20 | $0.20 | βNot published by the provider | βNot enough data yet |
| βNot enough data yet | βNot enough data yet | $0.20 | $0.20 | βNot published by the provider | βNot enough data yet | |
CodeLlama-13b-Instruct-hf πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.225 | $0.225 | βNot published by the provider | βNot enough data yet |
Nous-Hermes-Llama2-13b πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.225 | $0.225 | βNot published by the provider | βNot enough data yet |
Whisper Large V3 πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | βNot enough data yet | βNot enough data yet | $0.27 | $0.85 | βNot published by the provider | 55.6Good value (55.6). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
Run by Together AI
2 listings on this page where Together AI runs the model. Another provider sells these listings.
Select a score for details.
About these columns
- llminfo IQ
- llminfo IQ (capability index). How llminfo IQ is computed
- Coding IQ
- llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
- Value
- Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
| Model | Provider | llminfo IQ | Coding IQ | Input $/1M | Output $/1M | Max Input Tokens | Value |
|---|---|---|---|---|---|---|---|
RNJ-1 Instruct Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | βNot enough data yet | βNot enough data yet | $0.15 | $0.15 | 33K | βNot enough data yet | |
Ripple 65B Preview NewReleased 4 Nov 2026 | βNot enough data yet | βNot enough data yet | $0.20cache read $0.02 | $0.60 | 131K | βNot enough data yet |