AI pricing · November 2026
Together AI API pricing
| Provider | Cached in | Context | ||||
|---|---|---|---|---|---|---|
| Qwen3.8 Flash | Together AIopen model | $0.150 | $0.470 | — | 1M | $2.44 |
| GPT-OSS 120B | Together AIopen model | $0.150 | $0.600 | — | 131K | $2.70 |
| DeepSeek V4 Pro 0813 | Together AIopen model | $1.32 | $3.96 | $0.130 | 1M | $21.12 |
| GLM-5.3 | Together AIopen model | $1.40 | $4.40 | $0.260 | 1M | $22.80 |
Cached input and batch discounts
| Model | Input $/1M | Cached input $/1M | Cache saving | Batch |
|---|---|---|---|---|
| DeepSeek V4 Pro 0813 | $1.32 | $0.13 | 90% off | — |
| GPT-OSS 120B | $0.15 | — | — | — |
| Qwen3.8 Flash | $0.15 | — | — | — |
| GLM-5.3 | $1.40 | $0.26 | 81% off | — |
What a typical workload costs
An app that sends 1,000 requests a day, each with a 2,000-token prompt and a 500-token answer, uses 60M input and 15M output tokens in 30 days. If 1,500 of those prompt tokens are the same system prompt and context every time, prompt caching bills 45M of them at the cached rate (cache writes and storage not included).
| Model | Per month | With caching |
|---|---|---|
| DeepSeek V4 Pro 0813 | $139 | $85.05 |
| GPT-OSS 120B | $18.00 | — |
| Qwen3.8 Flash | $16.05 | — |
| GLM-5.3 | $150 | $98.70 |
Closest-priced models from other providers
Matched on a 3:1 mix of input to output tokens. Open models are compared with every provider.
| Together AI model | In / out $/1M | Closest elsewhere |
|---|---|---|
| DeepSeek V4 Pro 0813 | $1.32 / $3.96 | DeepSeek V4 Pro (DeepSeek) $1.32 / $3.96 · Claude Haiku 4.5 (Anthropic) $1 / $5 |
| GPT-OSS 120B | $0.15 / $0.60 | Mistral Small 4 (Mistral) $0.15 / $0.60 · GPT-OSS 120B (Groq) $0.15 / $0.60 |
| Qwen3.8 Flash | $0.15 / $0.47 | Mistral Small 4 (Mistral) $0.15 / $0.60 · GPT-OSS 120B (Groq) $0.15 / $0.60 |
| GLM-5.3 | $1.40 / $4.40 | GLM 5.3 (Fireworks AI) $1.40 / $4.40 · Claude Haiku 4.5 (Anthropic) $1 / $5 |
Source: Together AI pricing, checked 2026-11-02. To price a real prompt, paste it into the token counter.
FAQ
How much does the Together AI API cost?+
Together AI charges per token. On 2026-11-02 its official pricing page listed, per 1M tokens: DeepSeek V4 Pro 0813 $1.32 input / $3.96 output, GPT-OSS 120B $0.15 input / $0.60 output, Qwen3.8 Flash $0.15 input / $0.47 output and GLM-5.3 $1.40 input / $4.40 output.
What is the cheapest Together AI model?+
Qwen3.8 Flash: $0.15 per 1M input tokens and $0.47 per 1M output tokens. For the example workload on this page (30,000 requests a month) that is about $16.05 a month, against $150 on GLM-5.3, the most expensive Together AI model here.
Does Together AI have prompt caching or cheaper cached input?+
Yes. Cached input tokens cost $0.13 on DeepSeek V4 Pro 0813 (90% less than regular input) and $0.26 on GLM-5.3 (81% less than regular input).
Does Together AI offer a batch discount?+
This page has no batch price for Together AI models; check the official pricing page linked below for asynchronous or off-peak options.
How does DeepSeek V4 Pro 0813 compare on price with other AI APIs?+
At $1.32 input / $3.96 output per 1M tokens, the closest-priced models from other providers are DeepSeek V4 Pro (DeepSeek, $1.32 / $3.96) and Claude Haiku 4.5 (Anthropic, $1 / $5). Price per token isn't the whole bill: compare quality on your own prompts, and how many tokens each model uses for the same task.
How current are these prices?+
They were copied from Together AI's official pricing page on 2026-11-02, and the month in this page's title is that check date. Prices change often, so confirm on the official page before you commit to a budget.
Other providers
Claude API pricing · OpenAI API pricing · Gemini API pricing · Grok API pricing · Mistral API pricing · DeepSeek API pricing · Groq API pricing · Fireworks AI API pricing · All AI model prices compared