Google's thinking model lets developers set a reasoning budget from 0 to 24,576 tokens per request, creating a 6x cost spread between instant responses at $0.60/1M output and full chain-of-thought at $3.50/1M. With thinking enabled, it scores 88.0% on AIME 2024 and 60.4% on SWE-bench Verified, while running at 214.7 tokens per second.
Discover the power and diversity of large language models available with Telnyx. Explore the options below to find the perfect model for your project.
Check out our helpful tools to help get you started.
Gemini 2.5 Flash is available with free usage limits through Google AI Studio. Production API access through Vertex AI and inference providers involves usage-based pricing.
Gemini 2.5 Flash introduces a "thinking" mode for step-by-step reasoning, significantly improving performance on math, coding, and analysis tasks over 2.0 Flash. It is available through and other inference platforms.
Gemini 2.5 Flash scores 88.4% on Global-MMLU-Lite and 88.0% on AIME 2024 with its thinking budget enabled. Its Arena ELO of 1,411 places it above GPT-4.1 (1,413 is close) and near Qwen3 235B (1,422) on the same sheet. The controllable thinking budget from 0 to 24,576 tokens creates a 6x cost spread, allowing developers to trade reasoning depth for latency per request.
Running Gemini 2.5 Flash through Telnyx Inference costs $0.30 per million input tokens and $2.50 per million output tokens (non-thinking). Processing 1,000,000 reasoning tasks at 2,000 tokens each would cost approximately $2,800, with the tunable thinking budget allowing developers to reduce cost by up to 6x on simpler queries.
| Organization | Model Name | Tasks | Languages Supported | Context Length | Parameters | Model Tier | License |
|---|---|---|---|---|---|---|---|
| Telnyx | DeepSeek-V4-Flash-0731 | text generation | English | 1,048,576 | 284.0B | unlisted | mit |
| Telnyx | DeepSeek-V4.1-Flash | text generation | English | 1,048,576 | 552.0B | small | mit |
| gemma-2b-it | text generation | English | 8,192 | 2.5B | small | gemma | |
| gemma-4-26B-A4B-it | text to-text | Multilingual | 262,144 | 25.8B | small | apache-2.0 | |
| gemma-4-31B-it | text generation | Multilingual | 131,072 | 30.7B | small | apache-2.0 | |
| meta-llama | Llama-3.3-70B-Instruct | text generation | Multilingual | 99,000 | 70.6B | large | llama3.3 |
| meta-llama | Meta-Llama-3.1-70B-Instruct | text generation | Multilingual | 99,000 | 70.6B | large | llama3.1 |
| meta-llama | Meta-Llama-3.1-8B-Instruct | text generation | Multilingual | 131,072 | 8.0B | small | llama3.1 |
| minimaxai | MiniMax-M2.7 | text generation | Multilingual | 200,000 | 0 | large | minimaxai |
| minimaxai | MiniMax-M3-MXFP8 | text generation | Multilingual | 1,000,000 | 428.0B | small | minimax-community |
| moonshotai | Kimi-K2.5 | text generation | Multilingual | 256,000 | 1.0T | large | modified-mit |
| moonshotai | Kimi-K2.6 | text generation | Multilingual | 262,144 | 1.0T | medium | modified-mit |
| moonshotai | Kimi-K3 | text generation | English | 1,000,000 | 2.8M | large | MIT Modified |
| nvidia | personaplex-7b-v1 | speech to-speech | English | 3,000 | 7.0B | small | nvidia-open-model-license |
| poolside | Laguna-S-2.1 | text generation | English | 1,048,576 | 117.6B | unlisted | OpenMDW-1.1 |
| Qwen | Qwen3-235B-A22B | text generation | English | 32,768 | 235.1B | large | apache-2.0 |
| Telnyx | Qwen3.8-27B | text generation | English | 262,144 | 27.0B | small | Apache 2.0 |
| zai-org | GLM-5.1-FP8 | text generation | Multilingual | 202,752 | 753.9B | large | mit |
| zai-org | GLM-5.2 | text generation | English | 1,000,000 | 753.9B | medium | MIT |
| Telnyx | GLM-5.3 | text generation | English | 1,048,576 | 753.0B | medium | glm-5.3 |
| zai-org | GLM-5.3-Flash | text generation | English | 1,048,576 | 320.0B | small | mit |
| anthropic | claude-haiku-4-5 | text generation | Multilingual | 400,000 | 0 | large | openai |
| gemini-2.5-flash | text generation | Multilingual | 400,000 | 0 | large | openai | |
| gemini-3.7-flash | text generation | Multilingual | 400,000 | 0 | large | openai | |
| groq | gpt-oss-120b | text generation | Multilingual | 400,000 | 0 | large | openai |
| openai | gpt-4.1 | text generation | Multilingual | 400,000 | 0 | large | openai |
| openai | gpt-4o | text generation | Multilingual | 400,000 | 0 | large | openai |
| openai | gpt-4o-mini | text generation | Multilingual | 400,000 | 0 | large | openai |
| openai | gpt-5 | text generation | Multilingual | 400,000 | 0 | large | openai |
| openai | gpt-5.1 | text generation | Multilingual | 400,000 | 0 | large | openai |
| openai | gpt-5.2 | text generation | Multilingual | 400,000 | 0 | large | openai |
| openai | gpt-5.4 | text generation | Multilingual | 400,000 | 0 | large | openai |
| openai | gpt-5.4-mini | text generation | Multilingual | 400,000 | 0 | large | openai |
| openai | gpt-5.6-luna | text generation | Multilingual | 400,000 | 0 | large | openai |
| openai | gpt-5.6-sol | text generation | Multilingual | 400,000 | 0 | large | openai |
| openai | gpt-live-1 | speech to-speech | Multilingual | 400,000 | 0 | large | openai |
Yes, Gemini 2.5 Flash is Google's latest production model, optimized for speed and cost while supporting extended reasoning. It is documented in Google's model reference.
Gemini 2.5 Flash excels at high-throughput production tasks including code generation, document analysis, and multimodal processing. Its thinking mode enables complex reasoning when needed while maintaining low latency for simpler tasks.
Gemini 2.5 Flash is competitive with GPT-4o on many benchmarks while being optimized for higher throughput. Its native multimodal capabilities and thinking mode make it strong for real-time applications.
Thinking mode enables Gemini 2.5 Flash to reason step-by-step before generating a response, improving accuracy on complex problems. It can be toggled on or off through the API, allowing you to trade latency for quality.
