Llama 2 70B
Llama 2 70B is worth evaluating for coding and classification when its provider route and context window match the workload.
Use it for
- Teams evaluating coding and classification
- Workloads that can use a 4k context window
- Buyers comparing 1 tracked provider route
Do not use it for
- Vision or document-understanding workloads
- Strict JSON or tool-calling flows
- Family
- Llama 2
- Released
- 2023-07-18
- Context
- 4k
- Parameters
- 70B
- Architecture
- Decoder Only
- Knowledge cutoff
- 2022-09
- Specialization
- general
- Openness
- Open weights
- License
- Llama 2 CommunityCommercial use: conditional
- Weights
- Available
- Code
- Unknown
- Training
- Fine-tuned
Large-scale open-source AI for social technologies.
Cheapest of 1 route · Fireworks AI
About
Llama 2 70B is a state-of-the-art generative text model developed by Meta, featuring 70 billion parameters and optimized for dialogue applications. It utilizes an advanced transformer architecture and has been fine-tuned using supervised learning and RLHF. Pretrained on 2 trillion tokens from diverse public sources, it outperforms many open-source chat models and competes with popular closed-source models in terms of helpfulness and safety. The model is designed for commercial and research applications in English, focusing on assistant-like chat functionalities. It accepts text input and generates text output, making it suitable for various natural language processing tasks .
Llama 2 70B is an open-weight model in the Llama 2 family. The structured metadata tracks a 4k-token context window. This page tracks provider routes through Fireworks AI, with the cheapest tracked route listed at $0.9 input and $0.9 output per 1M tokens. Headline tracked benchmarks include Google-Proof Q&A 39.1, HellaSwag 88.2, and HumanEval 56.2.
Top use-case fit: coding, agents, and build tasks
Coding
Q/$ C1 relevant benchmark in the decision map.
Classification
Q/$ C2 relevant benchmarks in the decision map.
Provider price ladder
Compare API pricing across 1 providers for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| Fireworks AI | $0.900 | $0.900 | Serverless |
Available via routers & gateways(1)
Capabilities
No model capability flags are currently sourced.
Benchmark peer barsfor Coding
Benchmark scores(4)
| Benchmark | Score | Version | Evaluation | Source |
|---|---|---|---|---|
| Google-Proof Q&A | 39.1 | diamondObserved 2026-03-06 | — | Source |
| HellaSwag | 88.2 | 10-shotObserved 2026-03-06 | — | Source |
| HumanEval | 56.2 | pass@1Observed 2026-03-06 | — | Source |
| Massive Multitask Language Understanding | 68.9 | 5-shotObserved 2026-03-06 | — | Source |
Migration checks
No linked migration route is available for this model yet.
Frequently asked questions
What is the context window of Llama 2 70B?
Llama 2 70B has a context window of 4k tokens.
How much does Llama 2 70B cost?
Llama 2 70B is available at $0.9/1M input tokens through Fireworks AI.
When was Llama 2 70B released?
Llama 2 70B was released on 2023-07-18.
Which providers offer Llama 2 70B?
Llama 2 70B is available from 1 provider: Fireworks AI.
What benchmarks has Llama 2 70B been tested on?
Llama 2 70B has been evaluated on 4 benchmarks, including Google-Proof Q&A, HellaSwag, HumanEval, Massive Multitask Language Understanding.
Large-scale open-source AI for social technologies.
Cheapest of 1 route · Fireworks AI