llama-3.3-70b-versatile
Groq · chat model
llama-3.3-70b-versatile is listed here as a chat model from Groq. This page shows simple API pricing, token limits, and capability flags so you can compare it with similar options.
Input
$0.5900 / 1M tokens
Output
$0.7900 / 1M tokens
Cached input
N/A
Context
32.8K
Quick read
Best for
Use this page when you need a fast view of cost, context size, and supported features before testing the model in your own workload.
Things to verify
Always check the provider page for discounts, cache pricing, region rules, and any model limits that may not appear in public metadata.
Pricing
| Item | Price |
|---|---|
| Input | $0.5900 / 1M tokens |
| Output | $0.7900 / 1M tokens |
| Embedding | $0.5900 / 1M tokens |
Token limits
Context window
32.8K
Max input tokens
128.0K
Max output tokens
32.8K
Max tokens
32.8K
Capabilities
| Capability | Supported |
|---|---|
| Vision | — |
| Function calling | ✅ |
| Parallel function calling | — |
| Tool choice | ✅ |
| Prompt caching | — |
| Reasoning | — |
| Response schema | — |
| System messages | — |
| Audio input | — |
| Audio output | — |
| Web search | — |
| PDF input | — |
| Video input | — |
Benchmarks
Most benchmark rows are attached to the base model family rather than this provider route. Open benchmark explorer
| Benchmark | Score | Metric | Scope | Checked | Source |
|---|---|---|---|---|---|
| MMLU (CoT) | 86.0 | macro_avg/acc | Base model: Llama 3.3 (Llama-3.3 70B Instruct) | 2026-05-31 | Link |
| MMLU-Pro (CoT) | 68.9 | macro_avg/acc | Base model: Llama 3.3 (Llama-3.3 70B Instruct) | 2026-05-31 | Link |
| GPQA Diamond | 50.5 | acc | Base model: Llama 3.3 (Llama-3.3 70B Instruct) | 2026-05-31 | Link |
| HumanEval | 88.4 | pass@1 | Base model: Llama 3.3 (Llama-3.3 70B Instruct) | 2026-05-31 | Link |
| MATH (CoT) | 77.0 | sympy_intersection_score | Base model: Llama 3.3 (Llama-3.3 70B Instruct) | 2026-05-31 | Link |
| MMLU (CoT) | 86.0 | macro_avg/acc | Base model: Llama 3.3 (Llama-3.3 70B Instruct) | 2026-05-31 | Link |
| MMLU-Pro (CoT) | 68.9 | macro_avg/acc | Base model: Llama 3.3 (Llama-3.3 70B Instruct) | 2026-05-31 | Link |
| IFEval | 92.1 | Base model: Llama 3.3 (Llama-3.3 70B Instruct) | 2026-05-31 | Link | |
| HumanEval | 88.4 | pass@1 | Base model: Llama 3.3 (Llama-3.3 70B Instruct) | 2026-05-31 | Link |
Sources
| Source links | |
| Pricing data | LiteLLM model cost map |
| Synced at | 2026-05-28 |
Similar models
This list is ranked by overall similarity. Use filters to emphasize the lens that matters most for the replacement you are making.
Comparing from
| Model | Cost | Input shape | Features | Context | Why it is close |
|---|---|---|---|---|---|
| llama-3.3-70b-versatile Groq | In $0.5900 / 1M tokens Out $0.7900 / 1M tokens |
Output: unknown | Function callingTool choice | 32.8K | Current model Reference row |
| Model | Cost | Input shape | Features | Context | Why it is close |
|---|---|---|---|---|---|
| Mixtral-8x7B-Instruct-v0.1 deepinfra | In $0.4000 / 1M tokens Out $0.4000 / 1M tokens | text
Output: text | Function callingTool choice | 32.8K | Partial I/O overlap Overall 52% |
| DeepSeek-R1-0528-Turbo deepinfra | In $1.0000 / 1M tokens Out $3.0000 / 1M tokens | text
Output: text | Function callingTool choice | 32.8K | Partial I/O overlap Overall 48% |
| moonshot-v1-32k moonshot | In $1.0000 / 1M tokens Out $3.0000 / 1M tokens |
Output: unknown | Function callingTool choice | 32.8K | Partial I/O overlap Overall 48% |
| moonshot-v1-32k-0430 moonshot | In $1.0000 / 1M tokens Out $3.0000 / 1M tokens |
Output: unknown | Function callingTool choice | 32.8K | Partial I/O overlap Overall 48% |
| qwen3-coder-480b-a35b-instruct-maas vertex_ai-qwen_models | In $1.0000 / 1M tokens Out $4.0000 / 1M tokens |
Output: unknown | Function callingTool choice | 32.8K | Partial I/O overlap Overall 47% |
| Qwen3-235B-A22B deepinfra | In $0.1800 / 1M tokens Out $0.5400 / 1M tokens | text
Output: text | Function callingTool choice | 41.0K | Partial I/O overlap Overall 47% |
| llama-3.3-70b vercel_ai_gateway | In $0.7200 / 1M tokens Out $0.7200 / 1M tokens | text
Output: text | Function callingTool choice | 8.2K | Partial I/O overlap Overall 46% |
| llama3.1-70b cerebras | In $0.6000 / 1M tokens Out $0.6000 / 1M tokens |
Output: unknown | Function callingTool choice | 128.0K | Partial I/O overlap Overall 46% |
| Llama-3.1-Nemotron-70B-Instruct deepinfra | In $0.6000 / 1M tokens Out $0.6000 / 1M tokens | text
Output: text | Function callingTool choice | 131.1K | Partial I/O overlap Overall 46% |
| DeepSeek-V3 deepinfra | In $0.3800 / 1M tokens Out $0.8900 / 1M tokens | text
Output: text | Function callingTool choice | 163.8K | Partial I/O overlap Overall 44% |
| Llama-3.3-70B-Instruct azure_ai | In $0.7100 / 1M tokens Out $0.7100 / 1M tokens | text
Output: text | Function callingTool choice | 2.0K | Partial I/O overlap Overall 43% |
| codestral vercel_ai_gateway | In $0.3000 / 1M tokens Out $0.9000 / 1M tokens | text
Output: text | Function callingTool choice | 4.0K | Partial I/O overlap Overall 41% |
| gpt-3.5-turbo Azure | In $0.5000 / 1M tokens Out $1.5000 / 1M tokens | text
Output: text | Function callingTool choice | 4.1K | Partial I/O overlap Overall 40% |
| gpt-35-turbo Azure | In $0.5000 / 1M tokens Out $1.5000 / 1M tokens | text
Output: text | Function callingTool choice | 4.1K | Partial I/O overlap Overall 40% |
| llama-3-70b vercel_ai_gateway | In $0.5900 / 1M tokens Out $0.7900 / 1M tokens | text
Output: text | Tool choice | 8.2K | Partial I/O overlap Overall 36% |
| llama-3-70b-instruct OpenRouter | In $0.5900 / 1M tokens Out $0.7900 / 1M tokens | text
Output: text | Tool choice | 8.0K | Partial I/O overlap Overall 36% |
| mistral.mixtral-8x7b-instruct-v0:1 Bedrock | In $0.5900 / 1M tokens Out $0.9100 / 1M tokens | text
Output: text | Tool choice | 8.2K | Partial I/O overlap Overall 35% |
| gpt-oss-120b Groq | In $0.1500 / 1M tokens Out $0.6000 / 1M tokens |
Output: unknown | Function callingTool choice | 32.8K | Same provider Overall 34% |
| qwen3-32b Groq | In $0.2900 / 1M tokens Out $0.5900 / 1M tokens |
Output: unknown | Function callingTool choice | 131.0K | Same provider Overall 33% |
| kimi-k2-instruct-0905 Groq | In $1.0000 / 1M tokens Out $3.0000 / 1M tokens |
Output: unknown | Function callingTool choice | 16.4K | Same provider Overall 32% |
| gpt-35-turbo-16k-0613 Azure | In $3.0000 / 1M tokens Out $4.0000 / 1M tokens | text
Output: text | Function callingTool choice | 4.1K | Partial I/O overlap Overall 31% |
| llama-3.1-8b-instant Groq | In $0.0500 / 1M tokens Out $0.0800 / 1M tokens |
Output: unknown | Function callingTool choice | 8.2K | Same provider Overall 31% |
| gemma-7b-it Groq | In $0.0500 / 1M tokens Out $0.0800 / 1M tokens |
Output: unknown | Function callingTool choice | 8.2K | Same provider Overall 31% |
| gpt-oss-20b Groq | In $0.0750 / 1M tokens Out $0.3000 / 1M tokens |
Output: unknown | Function callingTool choice | 32.8K | Same provider Overall 29% |
| llama-3-70b-instruct novita | In $0.5100 / 1M tokens Out $0.7400 / 1M tokens | text
Output: text | Tool choice | 8.0K | Partial I/O overlap Overall 28% |
| gpt-4 Azure | In $30.0000 / 1M tokens Out $60.0000 / 1M tokens | imagetext
Output: text | Function callingTool choice | 4.1K | Partial I/O overlap Overall 27% |
| gpt-4-0613 Azure | In $30.0000 / 1M tokens Out $60.0000 / 1M tokens | text
Output: text | Function callingTool choice | 4.1K | Partial I/O overlap Overall 27% |
| L3.1-70B-Euryale-v2.2 deepinfra | In $0.6500 / 1M tokens Out $0.7500 / 1M tokens | text
Output: text | Low overlap | 131.1K | Partial I/O overlap Overall 22% |
| L3.3-70B-Euryale-v2.3 deepinfra | In $0.6500 / 1M tokens Out $0.7500 / 1M tokens | text
Output: text | Low overlap | 131.1K | Partial I/O overlap Overall 22% |
No models match this filter.