As of August 20, 2026, Inkling-Small is 16% cheaper per million tokens than Llama 3.1 405B Instruct. Inkling-Small is $0.30 / $1.20 per million input/output tokens versus Llama 3.1 405B Instruct at $0.89 / $0.89. Sources: https://thinkingmachines.ai and https://llama.meta.com/
Sources: Thinking Machines Lab pricing (https://thinkingmachines.ai); Meta pricing (https://llama.meta.com/)
Inkling-Small
Thinking Machines
Input
$0.30
Output
$1.20
Llama 3.1 405B Instruct
Meta
Input
$0.89
Output
$0.89
Token pricing, specs, and benchmarks side by side
Inkling-SmallLlama 3.1 405B InstructVerdict
Inkling-Small offers both lower pricing and stronger benchmark performance across the board, making it the clear value leader in this comparison.
As of August 20, 2026, Inkling-Small is 16% cheaper on blended LLM API pricing. Inkling-Small costs $0.30 per million input tokens and $1.20 per million output tokens ($1.50 blended 1M-in + 1M-out). Llama 3.1 405B Instruct costs $0.89 / $0.89 per million tokens ($1.78 blended). Sources: https://thinkingmachines.ai and https://llama.meta.com/. The cheapest LLM for your app still depends on how many output tokens you generate.
Inkling-Small Thinking Machines Lab API pricing is $0.30 input and $1.20 output per million tokens via Thinking Machines Lab. Llama 3.1 405B Instruct Meta API pricing is $0.89 input and $0.89 output per million tokens via Meta. Use those four numbers, not ChatGPT Plus or Claude Pro subscription prices, when you are comparing APIs.
Inkling-Small has a published SWE-bench Verified score of 80.2%. Llama 3.1 405B Instruct does not have that eval on this page yet.
Inkling-Small supports a 256K token context window, while Llama 3.1 405B Instruct supports 128K tokens. Inkling-Small offers a larger context window. Filling a larger window bills more input tokens, so the cheaper-per-million model can still cost more on long documents.
Inkling-Small leads on 5 of 5 shared benchmarks versus Llama 3.1 405B Instruct's 0 wins. Check the comparison table for GPQA Diamond, SWE-bench, MMLU, HLE, and the other evals we track. Token price and benchmark score together are the usual LLM comparison, not either number alone.
Both Inkling-Small and Llama 3.1 405B Instruct are production API models. For cost-sensitive production traffic, Inkling-Small has better economics on the blended 1M-in + 1M-out scale. For maximum capability, weight the benchmark table for your domain. Many production stacks route cheap models for drafts and a frontier model for the hard turn, which is usually cheaper than sending everything to the expensive API.
Yes. Call Inkling-Small through Thinking Machines Lab and Llama 3.1 405B Instruct through Meta with separate API keys, or through a gateway that already wraps both. Keep prompts in tokens, not characters, when you estimate the invoice. AnotherWrapper templates can swap providers without rewriting auth and billing.
List rates are the latest published Thinking Machines Lab API pricing and Meta API pricing, quoted per million tokens. Official rate sheets: https://thinkingmachines.ai and https://llama.meta.com/. Prompt caching, batch APIs, and committed-use discounts can change the invoice. Benchmark scores are from official publications and independent evals, updated as new numbers land.
Inkling-Small supports up to 256K output tokens per request, while Llama 3.1 405B Instruct supports up to 128K output tokens. Output tokens are usually the expensive half of API pricing, so a higher max output cap is a capability, not a discount.
Llama 3.1 405B Instruct has a measured throughput of approximately 42 tokens/second. Throughput data for Inkling-Small is not yet available. Throughput (tokens per second) and time-to-first-token are why two models with the same per-million-token price can still feel different in chat and agents.
Use the model pickers at the top of this LLM comparison. Search any model in the index and the URL updates. Open Inkling-Small or Llama 3.1 405B Instruct from the sidebar for the single-model API pricing page, or go back to the LLM pricing table to sort by cheapest blended cost.
This comparison covers API pricing, context window, throughput, and benchmark scores. Inkling-Small costs $0.30/M input and $1.20/M output via Thinking Machines Lab. Llama 3.1 405B Instruct costs $0.89/M input and $0.89/M output.
Rank both on the LLM leaderboard, SWE-bench, and Humanity's Last Exam.
The index
280 models across 33 providers. Search or jump to a lab — every model page stays linked here.
Next step
Auth, billing, and the API layer are already decided. Fork 8 finished AI apps, or have us build the first version with you.
