Inference provider
Together AI API pricing: every model, compared
We track 31 Together AI prices that other providers also sell. Together AI has the lowest listed price for 7 of them; for the rest, the table shows how much more you pay than at the cheapest provider.
Standard list prices in USD. Last price change Oct 25, 2026. Together AI's official pricing page. How we rank.
LLMs, most widely offered first
Together AI LLM prices vs the cheapest provider
| Model | Rank | Cheapest elsewhere | Input / 1M | Output / 1M | Context |
|---|---|---|---|---|---|
| gpt-oss-120b | #7 of 18 | W&B Inference (CoreWeave)you pay 304% more here | $0.15 | $0.60 | 131K |
| GLM-5.2 | #4 of 13 | DeepInfrayou pay 85% more here | $1.40 | $4.40 | 1M |
| GLM-5.3 | #4 of 12 | DeepInfrayou pay 28% more here | $1.40 | $4.40 | 1M |
| GLM-5.3-Flash | #1 of 11 | Together AI is cheapest | $0.15 | $0.50 | 1M |
| Kimi K3 | #3 of 9 | SiliconFlowyou pay 11% more here | $3.00 | $15.00 | 1M |
| DeepSeek V4 Pro 0813 | #3 of 8 | DeepInfrayou pay 22% more here | $1.32 | $3.96 | 1M |
| DeepSeek-V3 | #7 of 8 | SiliconFlowyou pay 186% more here | $1.25 | $1.25 | 66K |
| DeepSeek-V4.1-Flash | #3 of 8 | DeepInfrayou pay 150% more here | $0.30 | $1.20 | 1M |
| DeepSeek V4.1 Flash 1017 | #2 of 7 | DeepInfrayou pay 150% more here | $0.30 | $1.20 | 1M |
| Llama 3.2 3B Instruct | #4 of 7 | Lambdayou pay 243% more here | $0.06 | $0.06 | 131K |
| MiniMax-M3 | #3 of 7 | W&B Inference (CoreWeave)you pay 27% more here | $0.30 | $1.20 | 524K |
| DeepSeek-R1-0528 | #5 of 6 | Lambdayou pay 1233% more here | $3.00 | $7.00 | 164K |
| Qwen2.5-72B-Instruct | #6 of 6 | Nebius Token Factoryyou pay 508% more here | $1.20 | $1.20 | 33K |
| GLM-4.6 | #4 of 5 | DeepInfrayou pay 14% more here | $0.60 | $2.20 | 203K |
| Llama 3.2 1B Instruct | #2 of 5 | Novita AIyou pay 200% more here | $0.06 | $0.06 | 131K |
| Qwen3.8 2.4T A95B | #1 of 5 | Together AI is cheapest | $2.00 | $6.00 | 1M |
| Kimi K2 Instruct | #4 of 4 | DeepInfrayou pay 71% more here | $1.00 | $3.00 | - |
| llama-3.1-405b-instruct | #3 of 4 | Nebius Token Factoryyou pay 133% more here | $3.50 | $3.50 | 4K |
| MiniMax-M2.7 | #2 of 4 | DeepInfrayou pay 20% more here | $0.30 | $1.20 | 197K |
| Qwen3.7 Max | #2 of 4 | Novita AIyou pay 20% more here | $1.50 | $4.50 | 1M |
| Qwen3.8 Flash | #2 of 4 | DeepInfrayou pay 28% more here | $0.15 | $0.47 | 1M |
| Inkling | #2 of 3 | DeepInfrayou pay 2% more here | $1.00 | $4.05 | 524K |
| MiniMax-M3.1-Flash | #1 of 3 | Together AI is cheapest | $0.15 | $0.60 | 1M |
| Qwen3.5 9B | #3 of 3 | DeepInfrayou pay 69% more here | $0.17 | $0.25 | 262K |
| Qwen3.7 Plus | #1 of 3 | Together AI is cheapest | $0.32 | $1.28 | 1M |
| Beam 1.0 501B A23B | #1 of 2 | Together AI is cheapest | $0.40 | $1.20 | 1M |
| ministral-3-14b-instruct-2512 | #1 of 2 | Together AI is cheapest | $0.20 | $0.20 | 262K |
| mistral-7b-instruct-v0.3 | #2 of 2 | OVHcloud AI Endpointsyou pay 79% more here | $0.20 | $0.20 | 33K |
| muse-glimmer-30b | #2 of 2 | DeepInfrayou pay 21% more here | $0.35 | $1.50 | 131K |
| qwen-v2.5-14b-instruct | #2 of 2 | Fireworks AIyou pay 300% more here | $0.80 | $0.80 | 33K |
| Qwen3.6 Plus | #1 of 2 | Together AI is cheapest | $0.50 | $3.00 | 1M |
Rank and difference use the blended price (3 input : 1 output tokens). Equal prices share a rank.
Ranked for your volume
gpt-oss-120b monthly cost by provider
Change the monthly tokens and the ranking updates instantly, using each provider's standard list price.
More requirements: caching, context, features, provider
| Provider | Estimated / month | Input / 1M | Output / 1M | Cached input / 1M | Context |
|---|---|---|---|---|---|
1 W&B Inference (CoreWeave)lowest for your volumePricing page | $0.64 | $0.03 | $0.17 | Not listed | 131,000 |
2 DeepInfraPricing page | $0.71 | $0.037 | $0.17 | Not listed | 131,072 |
3 Novita AIPricing page | $1.00 | $0.05 | $0.25 | Not listed | 131,072 |
4 SiliconFlowPricing page | $1.40 | $0.05 | $0.45 | Not listed | 131,000 |
5 OVHcloud AI EndpointsBilled in EUR: €0.08 input, €0.40 output per 1M tokens. USD at the ECB rate of Oct 30, 2026 (1.1172).Pricing page | $1.79 | $0.0894 | $0.4469 | Not listed | 131,000 |
6 BasetenPricing page | $2.00 | $0.10 | $0.50 | $0.10 | 128,072 |
7 Amazon BedrockPricing page | $2.70 | $0.15 | $0.60 | Not listed | 128,000 |
8 Fireworks AIPricing page | $2.70 | $0.15 | $0.60 | $0.015 | 131,072 |
9 Microsoft Azure AI FoundryPricing page | $2.70 | $0.15 | $0.60 | Not listed | 131,072 |
10 Nebius Token FactoryPricing page | $2.70 | $0.15 | $0.60 | Not listed | 131,072 |
Input volume includes the cached share, not an additional token volume. This is a list-price estimate, not a quote: cache-write charges, cache eligibility/TTL, batch discounts, long-context surcharges, regional pricing and taxes are excluded. Check the provider's terms for your workload before switching.
Ranked #1? Show it on your site
Together AI has the lowest blended list price (3 input : 1 output tokens) for these models. The badge states that basis, updates daily and always shows the current rank, whatever it is; ranking is by price only.
<a href="https://aiselect.online/models/glm-5-3-flash"><img src="https://aiselect.online/badge/glm-5-3-flash/together.svg" alt="GLM-5.3-Flash API price ranking on AISelect" height="20"></a>
<a href="https://aiselect.online/models/qwen3-8-2-4t-a95b"><img src="https://aiselect.online/badge/qwen3-8-2-4t-a95b/together.svg" alt="Qwen3.8 2.4T A95B API price ranking on AISelect" height="20"></a>
<a href="https://aiselect.online/models/minimax-m3-1-flash"><img src="https://aiselect.online/badge/minimax-m3-1-flash/together.svg" alt="MiniMax-M3.1-Flash API price ranking on AISelect" height="20"></a>Compare more
Other providers
Alibaba Cloud Model Studio, Amazon Bedrock, Anthropic, Baseten, Cloudflare Workers AI, Cohere, DeepInfra, DeepSeek, fal, Fireworks AI, FriendliAI, Google Cloud Vertex AI, Google Gemini API, IBM watsonx.ai, Lambda, Microsoft Azure AI Foundry, Mistral AI, Moonshot AI, Nebius Token Factory, Novita AI, Nscale, OpenAI, Oracle Cloud Generative AI, OVHcloud AI Endpoints, Perplexity, Replicate, SambaNova, Scaleway, SiliconFlow, W&B Inference (CoreWeave), xAI, Z.ai