magistral-medium-2506
Mistral · chat model
Input
$2.0000 / 1M tokens
Output
$5.0000 / 1M tokens
Cached input
N/A
Context
40.0K
Pricing
| Item | Raw value (per token) | Normalized |
|---|---|---|
| Input | 0.000002 | $2.0000 / 1M tokens |
| Output | 0.000005 | $5.0000 / 1M tokens |
| Embedding | 0.000002 | $2.0000 / 1M tokens |
Token limits
Context window
40.0K
Max input tokens
40.0K
Max output tokens
40.0K
Max tokens
40.0K
Capabilities
| Capability | Supported |
|---|---|
| Vision | No |
| Function calling | Yes |
| Parallel function calling | No |
| Tool choice | Yes |
| Prompt caching | No |
| Reasoning | Yes |
| Response schema | Yes |
| System messages | No |
| Audio input | No |
| Audio output | No |
| Web search | No |
| PDF input | No |
| Video input | No |
Similar models
Models with comparable pricing in the same mode (chat).
| Model | Provider | Input | Output | Context | Coding | Features |
|---|---|---|---|---|---|---|
| magistral-medium-2509 | Mistral | $2.0000 / 1M tokens | $5.0000 / 1M tokens | 40.0K | N/A | Tools Reasoning |
| magistral-medium-1-2-2509 | Mistral | $2.0000 / 1M tokens | $5.0000 / 1M tokens | 40.0K | N/A | Tools Reasoning |
| magistral-medium-latest | Mistral | $2.0000 / 1M tokens | $5.0000 / 1M tokens | 40.0K | N/A | Tools Reasoning |
| kimi-latest | moonshot | $2.0000 / 1M tokens | $5.0000 / 1M tokens | 131.1K | N/A | Vision Tools |
| kimi-latest-128k | moonshot | $2.0000 / 1M tokens | $5.0000 / 1M tokens | 131.1K | N/A | Vision Tools |
| moonshot-v1-128k | moonshot | $2.0000 / 1M tokens | $5.0000 / 1M tokens | 131.1K | N/A | Tools |
Sources
| Pricing source | LiteLLM model cost map |
| Synced at | 2026-05-27 |
| Manual review | Not reviewed |
Raw LiteLLM fields
{
"input_cost_per_token": 0.000002,
"litellm_provider": "mistral",
"max_input_tokens": 40000,
"max_output_tokens": 40000,
"max_tokens": 40000,
"mode": "chat",
"output_cost_per_token": 0.000005,
"source": "https://mistral.ai/news/magistral",
"supports_assistant_prefill": true,
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true
}