Pricingby GlyphLlama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization.
Ways to buy 2
| Way to buy | Input | Output | In / out per 1M | Cached | Vs cheapest |
|---|---|---|---|---|---|
bf16 | $0.05 | $0.33 | $0.05 / $0.33Cheapest | n/a | Cheapest |
Default region | $0.051 | $0.335 | $0.051 / $0.335+2% vs cheapest | n/a | +2% vs cheapest |
USD per 1M tokens. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $11.60 direct.
Kong AI Gateway$11.60+0%
LiteLLM$11.60+0%
Eden AI$12.24+5.5%
OpenRouter$12.24+5.5%
Cloudflare AI GatewayNot offeredNot offered
HeliconeNot offeredNot offered
Neon AI GatewayNot offeredNot offered
RequestyNot offeredNot offered
Vercel AI GatewayNot offeredNot offered
A dash: not on that gateway's own model list. No published token fee: Martian Gateway, Portkey, TrueFoundry AI Gateway.
Related models
| In / out per 1M | Cheapest route | |||||||
|---|---|---|---|---|---|---|---|---|
Meta · 1M | $1.25 | $4.25 | $1.25 / $4.25 | $2 | 1M | on Modal | · | Muse Spark Open is a coding-optimized open-weight model. |
Meta · 1M | $4 | $20 | $4 / $20 | $8 | 1M | Lab list price | · | Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. |
Meta · 1M | $1.25 | $4.25 | $1.25 / $4.25 | $2 | 1M | Lab list price | · | Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. |
Meta · 1M | $0.1 | $0.2 | $0.1 / $0.2 | $0.125 | 1M | Lab list price | · | Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and early-stage agentic, multi-agent, and coding workflows. |
DeepSeek · 1MCheapest: $0.081 on Particle AI (us-flex) | $0.15 | $0.6 | $0.15 / $0.6 | $0.262 | 1M | $0.081 on Particle AI (us-flex) | · | DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name. |
DeepSeek · 1M | $0.045 | $0.3 | $0.045 / $0.3 | $0.109 | 1M | on InferenceNet (fp8) | · | DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. |
Anthropic · 1M | $0.1 | $0.5 | $0.1 / $0.5 | $0.2 | 1M | Lab list price | · | Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. |
Cohere · 128K | $0.08 | Free | $0.08 / Free | $0.06 | 128K | Lab list price | · | Embed 5 Fast is the lower-latency, cost-efficient tier of Cohere's Embed 5 family of multimodal embedding models (about 1B parameters). |
About Llama 3.2 3B Instruct
Takes text in and returns text. First listed Sep 23, 2026. Up to 118K output tokens. Blended price $0.12 per 1M tokens at 3 input to 1 output. Model id llama-3-2-3b-instruct.
Price history
No list-price history: this model is sold by hosts rather than its lab.
Questions
How much does Llama 3.2 3B Instruct cost?
$0.05 per million input tokens and $0.33 per million output tokens.
What is the context window of Llama 3.2 3B Instruct?
131K tokens, with up to 118K tokens of output.
Where is Llama 3.2 3B Instruct cheapest?
Of 2 routes tracked, Parasail is cheapest at $0.05 input and $0.33 output per million tokens.