Gemma 7B IT
Gemma by Google, an innovative open-source LLM, leverages advanced text-to-text technology for tasks like question answering, summarization, and reasoning. Gemma 7B, a high-performing variant, offers English language proficiency in various text generation applications. Gemma 1.1 7B (IT) introduces novel RLHF alignment method, enhancing quality, coding capabilities, instruction following, and conversation quality. This version also addresses multi-turn conversation bugs and refrains from always starting responses with a specific phrase.
Model card on Hugging Face- Input / output price
- $0.4312 / $1.12 per 1M
- Context
- 8K tokens
- Released
- Feb 21, 2024
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
One provider serves this model, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Featherless featherless/gemma-7b-it | $0.4312/M | $1.12/M |
Pricing
USD per 1M tokens on Featherless, after gateway discounts.
- Input
- $0.4312 per 1M
- Output
- $1.12 per 1M
- Cache read
- $0.30 per 1M
Cost by volume
Total cost from 0 to 1T tokens.
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Output speed
Higher is better0.4tokens/sacross providers
Response latency
Lower is better7.6sacross providers
Benchmarks
5 published scores from 2 sources, each linked to where it was published.
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| HumanEvalhuggingface.co | 32.3% | huggingface.co | Feb 21, 2024 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| GSM8Khuggingface.co | 46.4% | huggingface.co | Feb 21, 2024 |
| MATHhuggingface.co | 24.3% | huggingface.co | Feb 21, 2024 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| MMLUhuggingface.co | 64.3% | huggingface.co | Feb 21, 2024 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LMArena EloLMArena | 1138 Elo · #190 of 191 | LMArena | Nov 19, 2026 |
Apps
Use Gemma 7B IT in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
Gemma 7B IT FAQ
Short answers, built from the data on this page.
Gemma 7B IT is a model from Google Gemini AI, released on Feb 21, 2024. Gemma by Google, an innovative open-source LLM, leverages advanced text-to-text technology for tasks like question answering, summarization, and reasoning. Gemma 7B, a high-performing variant, offers English language proficiency in various text generation applications. Gemma 1.1 7B (IT) introduces novel RLHF alignment method, enhancing quality, coding capabilities, instruction following, and conversation quality. This version also addresses multi-turn conversation bugs and refrains from always starting responses with a specific phrase.
On the Respan gateway, Gemma 7B IT costs $0.4312 per 1M input tokens and $1.12 per 1M output tokens on Featherless, after gateway discounts.
Gemma 7B IT is served by Featherless.
Gemma 7B IT accepts up to 8K tokens of context.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "gemma-7b-it". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Gemma 7B IT has 5 published benchmark scores, including HumanEval 32.3%, GSM8K 46.4%, and MMLU 64.3%. Each score links to where it was published; the data is collected by Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.